The continuous emergence of new entities, relations, triples, and multimodal information drives the dynamic evolution of multimodal knowledge graph (MMKG). However, existing MMKG embedding models follow a static setting, where training from scratch for growing MMKG wastes learned knowledge, while fine-tuning on new knowledge easily leads to catastrophic forgetting, severely limiting their applicability in real-world scenarios. To address this, we propose a multimodal continual representation learning framework (MoFot) for growing MMKG. Unlike existing static multimodal embedding methods, MoFot focuses on alleviating catastrophic forgetting rather than retraining to adapt to new knowledge. Specifically, MoFot effectively mitigates catastrophic forgetting caused by parameter updates and differing forgetting rates across modalities through a multimodal collaborative modulation mechanism. The mechanism ensures consistent retention of previously learned multimodal knowledge across snapshots through multimodal weight modulation and multimodal feature modulation. MoFot outperforms existing MMKG embedding, KG continual learning, and MMKG inductive models. Experimental results demonstrate that MoFot not only avoids forgetting but also enhances old knowledge by learning new knowledge, achieving adaptation to new knowledge while mitigating forgetting of old knowledge.

The IoT-based Healthcare Industry 5.0 offers intelligent solutions that utilize numerous sensors, generating massive amounts of data. These healthcare data with composite properties can be represented by high-order tensors, which enables the application of tensor multi-way analytics to uncover the latent features in data. However, existing tensor decomposition techniques often face challenges of limited interpretability and weak robustness, which constrain their application in the healthcare industry. To mitigate these challenges, this paper introduces a novel Bayesian Tensor Interpolative Decomposition (BTID) model, which is an extension of the concept of matrix interpolative decomposition and is designed to efficiently and interpretably analyze multi-way tensors. The proposed model performs low-rank approximation using a subset of the original data and employs the Bayesian learning approach to infer the weight matrices, thereby ensuring theoretical interpretability. Additionally, a hierarchical prior is incorporated within this model to address the complexities of the data and enhance model robustness. Finally, a clustering-driven strategy is developed to construct the skeleton matrix, ensuring its physical interpretability while facilitating the CP rank estimation. The BTID model has been comprehensively evaluated on synthetic and healthcare datasets, where the experimental outcomes confirm its superior accuracy, robustness, and interpretability compared with traditional tensor decomposition methods.

Multi-modal Time Series (MTS) is a vital ingredient to Predictive Multi-modal Artificial Intelligence (PMAI). MTS systems capture varying temporal modalities and their inherent dependencies for their accurate analytics. However, efficiently exploring these cross-modalities relationships is a challenging research due to their complexity facets and information redundancies. MTS patterns' pairwise similarity measures precede PMAI. Multi-modal Dynamic Time Warping (MDTW) is frequently explored to quantify similar MTS. Yet, it's reliant on the orthogonal conditioned local similarity measures that ignore the contributions of MTS' underlying structural relationships in the warping process and, hence, susceptible to unrealistic matching. This paper addresses the setbacks by recommending a scalable MTS recognition model, named Tensor-Slices Distance (TSD)-based MDTW (TSD-MDTW), that's subsequently advanced to two more distinct models termed Weighted modality and TSD (WmTSD-MDTW) and TSD-Mahalanobis (TSDMaha-MDTW). To quantify an alignment's cost, TSD-MDTW incorporates intrinsic spatial dependencies between modalities' coordinates, while WmTSD-MDTW relaxes information redundancies through weighing modalities based on information richness, whereas TSDMaha-MDTW embodies modalities dependencies and their coordinates' innate spatial dependencies. Besides, it proposes a scalable Tensor-based DTW (TDTW) model that re-formulates MDTW into multiple dimensions that are found paralleling warping processes. Theoretical and empirical experimental results on MTS multi-modal datasets encompassing load patterns and meteorological modalities reveal TDTW's efficiency and proposals' superior performances in terms of cluster compactness and separation over MDTW employing the state-of-the-art local similarity measures.

Tucker decomposition approximates the original tensor using a set of factor matrices and a core tensor, thereby reducing the storage and computational cost. Existing incremental Tucker decomposition techniques have limitations in efficiency and are not applicable to diverse dynamic incremental tensors. This paper proposes a dynamic incremental Tucker decomposition method based on heterogeneous computing, which efficiently handles complex dynamic tensors while preserving computational efficiency. Specifically, the target optimization function of Tucker decomposition is reconstructed to decouple the intrinsic correlation between factor matrix rows and fixed tensor dimensions, and the optimal solutions for the factor matrix rows are derived. This enables the algorithm to adapt to arbitrary forms of incoming incremental data, including time-series tensors, without recalculating existing data, thus enhancing data utilization efficiency. Then, a lightweight precision optimization strategy is introduced, which iteratively updates factor matrix rows using the most element-rich dimensions of each tensor order based on recorded observable data volumes. This strategy improves precision while significantly reducing computational costs. Furthermore, a task-characteristic-based heterogeneous computing scheduling strategy is proposed. By extracting highly parallelizable intermediate operators and leveraging the high throughput of GPUs, the algorithm is accelerated, leading to a 10 to 40 times speedup in incremental tensor decomposition compared to state-of-the-art methods, while maintaining accuracy.

High-density NAND flash memory, such as quadruple-level cell (QLC) flash, has has been widely adopted in emerging storage systems. However, its limited endurance and performance challenges necessitate novel solutions. Voltage-based write-once memory (WOM-v) codes have demonstrated their effectiveness in extending flash memory lifespan by reducing the erase count of flash blocks. Concurrently, secure deletion is essential to ensure data privacy in flash-based storage systems. Existing secure deletion approaches—encryption-based, erasure-based, and scrubbing-based—often face limitations such as susceptibility to deciphering or significant performance overheads. Additionally, the inherent “big block problem” in high-density flash memory complicates garbage collection (GC), further degrading system performance. To address these challenges, this paper proposes WOM-FTL, a flash translation layer (FTL) that integrates secure deletion and garbage collection (GC) with WOM-v codes to enhance both security and performance. WOM-FTL classifies request data into four categories based on access frequency and privacy requirements: hot-secure (HS), cold-secure (CS), hot-unsecure (HU) and cold-unsecure (CU). Additionally, WOM-FTL divides each block into several equal-sized sub-blocks and further classifies them into top sub-blocks and bottom sub-blocks according to their data storage characteristics. When a secure data deletion command is issued to the storage device, WOM-FTL leverages unsecure data (HU and CU) to overwrite the secure data (HS and CS). Furthermore, WOM-FTL allocates different types of request data to the corresponding sub-blocks, creating a data allocation pattern that is both scrubbing-friendly and GC-friendly. Experimental results demonstrate that WOM-FTL improves the I/O performance of storage systems by 60.91% compared to state-of-the-art solutions, providing a significant advancement in secure and efficient management of high-density flash memory.

Recently, most image segmentation methods exhibit an extreme trade-off between performance and efficiency, resulting in approaches with high performance typically having low computational efficiency, while efficient methods compromise on segmentation accuracy. To address this dual challenge, this study introduces a simple yet efficient segmentation framework based on Multi-scale Prototype matching and visual Sparse Attention mechanisms (MPSA), which is a transformer-based architecture designed to optimize the balance between performance and efficiency. The proposed MPSA integrates a novel lightweight cross-attention mechanism and prototype selection and filtering strategy to accurately correlate category queries with corresponding visual objects with a multi-scale Feature Pyramid Network (FPN). Within the pixel decoder, our Axial Convolution Enhanced (ACE) module mitigates lost global context by combining depth-wise separable convolutions with deformable convolutions, thereby recovering global semantics while preserving fine-grained spatial details. Through this innovative design, MPSA demonstrates outstanding performance in both semantic and panoptic segmentation tasks across multiple datasets. Remarkably, MPSA achieves surprising 83.9% mIoU with only 114M parameters on the Cityscapes dataset while compared to some state-of-the-art architectures, highlighting its ability to deliver exceptional results with significantly reduced resource consumption. Our code is released at https://github.com/zxqing01/MPSA.

Blockchain-enabled digital currency systems, referred to as blockchains for brevity, have become an important method for asset management. Additionally, numerous efforts have been made to facilitate asset swap between two different blockchains, further enhancing asset circulation. However, few works address the general scenario in which one trader swaps assets from$n_{1}$different blockchains with another trader using assets from$n_{2}$different blockchains, referred to as$n_{1} \sim n_{2}$swap. This paper proposes OSwap, the first$n_{1} \sim n_{2}$swap scheme that ensures atomicity without relying on synchronous blockchain communication. By leveraging third-party steps fromverifiable witness encryption based on threshold signatures(VweTS), OSwap allows privacy-conscious traders to swap assets independently, without interactive third-party involvement. It also integratesverifiable timed discrete logarithmschemes to support asset redemption under abnormal cases, maintaining atomicity and indistinguishability. We formally prove the security of OSwap under the universal composable framework with static corruption. We compare OSwap with the closest existing scheme for successful$n_{1} \sim n_{2}$swap, where the trader holding assets on$n_{1}$blockchains pays the counterparty holding assets on$n_{2}$blockchains first. The comparison demonstrates that OSwap reduces the number of required transactions from$2n_{1} + 2n_{2}$to$n_{1} + 2n_{2}$, while also supporting a broader range of signature types. Moreover, when fewer than 4 third parties are involved and both$n_{2}$and the threshold value in VweTS are set to 1, OSwap achieves lower running time cost.

With the advancement of heterogeneous computing technique, efficient model inferences designed for various domains have been successfully developed upon real-time embedded platforms. For those applications (e.g., drones and autonomous driving) demanding both highly parallel computation via Graphics Processing Units (GPUs) and strict timeliness constraints, effective scheduling of real-time activities upon heterogeneous systems remains challenging. With the intrinsic and intricate interferences among tasks (contending for the GPU resources) being considered, we first investigate two resource-cognizant utilization bounds for partitioned-EDF (Earliest Deadline First) scheduling under suspension-oblivious (i.e., busy-waiting) paradigm, and then explore their non-monotonicities. Based on the insights gained from the bounds, we further propose SP-RA-TMA (Spatial-Partitioning and Resource-Aware Task Mapping Algorithm) for periodic tasks executing upon CPU-GPU systems. Specifically, several blocking-oriented approaches for appropriate vGPU-to-core partition and feasible task-to-core mapping are introduced, in order to tighten the bound of blocking overheads for tasks and effectively alleviate the negative effects of GPU resource competitions for better schedulability of task set and balanced system workload. Finally, the synthetic and empirical experiment results demonstrate the practicability of SP-RA-TMA that can achieve a higher acceptance ratio (e.g., 80% more) compared to the existing partitioned/dynamic schemes.

Cross-chain transfer significantly enhances asset management among multiple blockchains. While existing cross-chain transfer schemes facilitate transferring asset ownership of users between a source blockchain and a target blockchain, they do not consider a complex scenario involvingmsource blockchains and one target blockchain (termedm∼1 cross-chain transfer). Furthermore, the variants of existing schemes for this scenario fail to concurrently achieve atomicity, unlinkability, and practical properties such as transaction aggregability, and non-collateralization, posing substantial limitations. To bridge this gap, we propose ShiftHub, the firstm∼1 cross-chain transfer scheme that simultaneously fulfills the above desired properties. ShiftHub guarantees atomicity and transaction aggregability by integratingexchange protocolswith a novelt-message-clustered redeem protocol. Unlinkability is achieved by additionally incorporating commonly used assumptions such as fixed-amount transfers, while the need for sender collateralization is eliminated by enabling the reuse of locked assets. Compatible with any blockchains that employadaptor signaturesorBLS signaturesfor transaction authentication, ShiftHub requires only signature verification and timelock functionalities on chain, ensuring near-universal blockchain compatibility. We formally prove the security of ShiftHub under static corruption using the universal composability framework. Extensive evaluation shows that ShiftHub offers superior performance over the existing scheme variant with the closest underlying protocols to ShiftHub, in terms of both off-chain and on-chain overhead, when completingm∼1 cross-chain transfer. Particularly, ShiftHub reduces the number of required transactions by (2m− 1)/3m.

Using DNN (Deep Neural Networks) models to obtain high Quality of Services (QoS) through the cloud has become increasingly popular nowadays. Users want to use DNN by their edges (such as smartphones) anytime and anywhere. For most small and medium-sized enterprises, cloud computing resources are limited. Temporary exhaustion of resources may cause obvious service delay. For users, if all tasks are done locally, the battery capacity of the edge is too small to support such huge computing tasks. To remove this contradiction, we propose a Tensor-based Lyapunov DNN Offloading Control (TLDOC) strategy. First, we offload DNN computational tasks to cloud-fog-edge from an overall perspective. That is, layers in DNN are considered as basic offloadable objects. Second, we provide an original tensor-based Lyapunov equation and the entire process is derived in the tensor space. Lastly, we consider more key limiting factors (e.g., cellular data and remaining edge energy) to achieve better QoS. Via above contributions, our strategy reduces service delay and energy consumption for DNN cloud-fog-edge orchestration. Our experiments include two parts - detail and comparison. The experimental detail verifies that TLDOC strategy is practical and stable. Compared experiments show that our strategy could provide better QoS than existing methods on efficiency and energy saving.

Along with the development of the Industrial Internet of Things, human activity recognition (HAR) has received widespread attention in many fields. Support Vector Machine (SVM), is widely used by researchers for human activity recognition. However, the inherent difference of signal properties from different sensors and various orientations is potentially lost when using the vector-based SVM for human activity recognition. What's more, the outlier sensitivity problem of the standard SVM reduces the accuracy of human activity recognition. To tackle this problem, we present a tensor-based feature representation model and a weighted support tensor machine (WSTM) for human activity recognition. Specifically, tensor-based representations are first used to model features from different sensors and various orientations to retain the latent relationship. In addition, the weighted support tensor machine is proposed to classify the human activities in tensor space while avoiding the outlier sensitivity problem. Experimental results demonstrate the proposed WSTM algorithm.

Accurate cross-modality cardiac image segmentation is essential for effectively diagnosing and treating heart disease. Different imaging modalities help to determine suitable pre-procedure planning. However, most methods face the difficulty of spatial-temporal confounding, where the anatomy element and modality element of cardiac images are intertwined across both spatial and temporal dimensions. It is derived from the imaging diversity and structure diversity of cardiac images. The spatial-temporal confounding hinders knowledge transfer between cardiac images on different modalities. In this paper, we propose a novel dynamic causal learning (DCL) to solve spatial-temporal confounding. The DCL explores multi-dimensional causal intervention to consider not only the causal relationship between images and labels, but also the causality in time dimension and space dimension. It integrates historical optimal interventions and facilitates the transfer of this knowledge across temporal contexts. In addition, the DCL utilizes the diffusion mechanism to further ensure that the extracted anatomy element remains causal invariant, improving model performance across multiple imaging modalities. Extensive experiments on cross-modality cardiac images (MR, CT, and US) demonstrate the effectiveness of the DCL (mean Dice = 0.951), outperforming other advanced segmentation methods. DCL is freely accessible at https://github.com/asdww0721ww/DCL.

Generating motion sequences conforming to a target style while adhering to the given content prompts requires accommodating both the content and style. In existing methods, the information usually only flows from style to content, which may cause conflict between the style and content, harming the integration. Differently, in this work we build a bidirectional control flow between the style and the content, also adjusting the style towards the content, in which case the style-content collision is alleviated and the dynamics of the style is better preserved in the integration. Moreover, we extend the stylized motion generation from one modality, i.e. the style motion, to multiple modalities including texts and images through contrastive learning, leading to flexible style control on the motion generation. To further boost the performance, we advance the motion diffusion to motion-aligned temporal latent diffusion by developing a novel motion VAE. Extensive experiments demonstrate that our method significantly outperforms previous methods across different datasets, while also enabling multimodal signals control. The code of our method will be made publicly available.

Tensor decomposition is a powerful tool for data analysis and has been extensively employed in the field of hyperspectral-multispectral image fusion (HMF). Existing tensor decomposition-based fusion methods typically rely on disruptive data vectorization/reshaping or impose rigid constraints on the arrangement of factor tensors, hindering the preservation of spatial-spectral structures and the modeling of cross-dimensional correlations. Although recent advances utilizing the Fully-Connected Tensor Network (FCTN) decomposition have partially alleviated these limitations, the process of reorganizing data into higher-order tensors still disrupts the intrinsic spatial-spectral structure. Furthermore, these methods necessitate extensive manual parameter tuning and exhibit limited robustness against noise and spatial degradation. To alleviate these issues, we propose the Bayesian FCTN (BFCTN) method. Within this probabilistic framework, a hierarchical sparse prior that characterizing the sparsity of physical elements, establishes connections between the factor tensors. This framework explicitly models the intrinsic physical coupling among spatial structures, spectral signatures, and local scene homogeneity. For model learning, we develop a parameter estimation method based on Variational Bayesian inference (VB) and the Expectation-Maximization (EM) algorithm, which significantly reduces the need for regularization parameter tuning. Extensive experiments demonstrate that BFCTN not only achieves state-of-the-art fusion accuracy and strong robustness but also exhibits practical applicability in complex real-world scenarios. The source code is available at: https://github.com/LinsongShan/BFCTN.

Text-based visual question answering (TextVQA) aims to answer questions by understanding scene text in images. However, many current methods overly depend on the accuracy of Optical Character Recognition (OCR) systems, while overlooking the significance of visual objects. They tend to perform poorly when the question involves the relationships between visual objects and scene text. To address the above issues, we focus on raising the status of visual objects and innovatively propose a hierarchical semantic reasoning network (CT-HSR) based on the cascade transformer architecture, achieving fine-grained cross-modal reasoning and visual semantic enhancement. Specifically, the visual representations containing rich semantic information of the question modality are obtained through the cross-modal transformer-based vision-language pre-training model firstly. Then, the uni-modal transformer for unified modality encoding module is utilized to capture visual objects that are more semantically related to OCR texts. In addition, we further alleviate the cross-modal noise interference through the feature filtering strategy. Finally, we better align the three modalities by introducing TextVQA pre-training tasks and generate prediction answers through multi-step iterative prediction during fine-tuning. Extensive experiments on the TextVQA, ST-VQA, and OCR-VQA datasets have demonstrated the effectiveness of our proposed model compared to the state-of-the-art methods. The code will be released at https://github.com/FTFWO/CT-HSR .

Recently, the research on fairness in recommendation systems has garnered widespread attention. Moreover, numerous fair recommendation models have been developed for scenarios with limited sensitive information, thereby alleviating the issue of missing sensitive information. However, the performance of these methods still tends to decline significantly when sensitive attributes are extremely scarce. In this paper, we propose FairCL, a novel fair recommendation framework designed to perform effectively under limited sensitive attribute information. FairCL features a contrastive learning-based sensitive attribute encoder that can be integrated with existing fair recommendation algorithms. By leveraging both collaborative information and item side information, we predict unknown sensitive attributes and apply contrastive learning for sensitive attribute modeling. Furthermore, we theoretically demonstrate how FairCL can be integrated with mutual information-based and adversarial learning-based fairness algorithms. Extensive experiments on three real-world datasets show that FairCL significantly enhances fairness, even when only a small portion of users' sensitive attributes are known. The code and data are at: https://anonymous.4open.science/r/CL-for-FairRec-000A/.

With the widespread adoption of mobile devices, an increasing number of users are engaging in social interactions through these devices. Mobile social networks have thus emerged in response. Existing research has shown that utilizing mobile social relations can effectively enhance the performance of recommendation systems. However, most studies only exploit single social relations such as pairwise relations, overlooking the effect of high-order complexity of user relations which contain some potentially beneficial information. What's more, they ignore the impact of the trusters who provide some potential feedbacks in the mobile social network. Therefore, this paper proposes our framework H2TRec using hypergraph convolution in the pretraining stage to learn high-order neighbor information in the mobile social network and utilizing the metapath-based GAT to model users' bidirectional trust relations. First, mobile social communities are partitioned by random walk based on the fusion graph which consolidates all different nodes and relations. Second, each mobile social community is represented as a hyperedge to construct the hypergraph and the high-order neighbor prior knowledge is learned using hypergraph convolution. Third, implicit relations are mined and the metapath-based GAT is utilized to model the preferences of users and items. Notably, unlike previous work, we consider mobile users' out-degree and in-degree features, which enhance the user embeddings. Additionally, a loss term aiming to improve centrality is added to make the preference features of mobile social communities more prominent. Extensive experiments on five popular real-world datasets demonstrate that our H2TRec can improve precision compared with state-of-the-art methods. We release the source code athttps://github.com/kangkang-yun/H2TRec.

Large language models in deep learning have numerous parameters, requiring significant storage space and computational resources. Compression techniques are highly effective in addressing these challenges. With the development of hardware like Graphics Processing Unit (GPU), Tensor Core can accelerate low-precision matrix multiplication but achieve acceleration for sparse matrices is challenging. Due to its sparsity, the utilization of Tensor Cores is relatively low. To address this, we propose the based onTensorCoreCompressedSparseRow format (TC-CSR), which facilitates data loading on GPUs and matrix operations on Tensor Cores. Based on this format, we designed block Sparse Matrix-Matrix Multiplication (SpMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM) kernels, which are common operations in deep learning. Utilizing these designs, we achieved a$\mathbf {1.41\times }$speedup on Sputnik in scenarios of moderate sparsity and a$\mathbf {1.38\times }$speedup with large-scale highly sparse matrices. Benefit from our design, we achieved a$\mathbf {1.75\times }$speedup in end-to-end inference with sparse Transformers and save memory.

Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications, since the target network might contain additional classes that are not present in the source. In this work, we study a more realistic open-set cross-network node classification (O-CNNC) problem, where the target network contains all the known classes in the source and further contains several target-private classes unseen in the source. Borrowing the concept from open-set domain adaptation, all target-private classes are defined as an additional “unknown” class. To address the challenging O-CNNC problem, we propose an unknown-excluded adversarial graph domain alignment (UAGA) model with a separate-adapt training strategy. Firstly, UAGA roughly separates known classes from unknown class, by training a graph neural network encoder and a neighborhood-aggregation node classifier in an adversarial framework. Then, unknown-excluded adversarial domain alignment is customized to align only target nodes from known classes with the source, while pushing target nodes from unknown class far away from the source, by assigning positive and negative domain adaptation coefficient to known class nodes and unknown class nodes. Extensive experiments on real-world datasets demonstrate significant outperformance of the proposed UAGA over state-of-the-art methods on O-CNNC.

Dynamic Searchable Symmetric Encryption (DSSE) allows secure searches over a dynamic encrypted database but suffers from inherent information leakage. Existing passive attacks against DSSE rely on persistent leakage monitoring to infer leakage patterns, whereas this work targets intermittent observation - a more practical threat model. We propose Peekaboo - a new universal attack framework - and the core design relies on inferring the search pattern and further combining it with auxiliary knowledge and other leakage. We instantiate Peekaboo over the SOTA attacks, Sap (USENIX' 21) and Jigsaw (USENIX' 24), to derive their ''+'' variants (Sap+ and Jigsaw+). Extensive experiments demonstrate that our design achieves >0.9 adjusted rand index for search pattern recovery and ∼90% query accuracy vs. FMA's ∼30% (CCS' 23). Peekaboo's accuracy scales with observation rounds and the number of observed queries but also it resists SOTA countermeasures, with >40% accuracy against file size padding and >80% against obfuscation.

In the era of rapid development of social media, social recommendation systems as hybrid recommendation systems have been widely applied. Existing methods capture interest similarity between users to filter out interestirrelevant relations in social networks that inevitably decrease recommendation accuracy, however, limited research has a focus on the mutual influence of semantic information between the social network and the user-item interaction network for further improving social recommendation. To address these issues, we introduce a social recommendation model with robust graph denoising-augmentation fusion and multi-semantic Modeling(Burger). Specifically, we firstly propose to construct a social tensor in order to smooth the training process of the model. Then, a graph convolutional network and a tensor convolutional network are employed to capture user's item preference and social preference, respectively. Considering the different semantic information in the user-item interaction network and the social network, a bi-semantic coordination loss is proposed to model the mutual influence of semantic information. To alleviate the interference of interest-irrelevant relations on multi-semantic modeling, we further use Bayesian posterior probability to mine potential social relations to replace social noise. Finally, the sliding window mechanism is utilized to update the social tensor as the input for the next iteration. Extensive experiments on three real datasets show Burger has a superior performance compared with the state-of-the-art models.

Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP’s pretraining on static image-text pairs. This work introduces LaMP, a novel Language-Motion Pretraining model, which transitions from a language-vision to a more suitable language-motion latent space. It addresses key limitations by generating motion-informative text embeddings, significantly enhancing the relevance and semantics of generated motion sequences. With LaMP, we advance three key tasks: text-to-motion generation, motion-text retrieval, and motion captioning through aligned language-motion representation learning. For generation, LaMP instead of CLIP provides the text condition, and an autoregressive masked prediction is designed to achieve mask modeling without rank collapse in transformers. For retrieval, motion features from LaMP’s motion transformer interact with query tokens to retrieve text features from the text transformer, and vice versa. For captioning, we finetune a large language model with the language-informative motion features to develop a strong motion captioning model. In addition, we introduce the LaMP-BertScore metric to assess the alignment of generated motions with textual descriptions. Extensive experimental results on multiple datasets demonstrate substantial improvements over previous methods across all three tasks. Project page: https://aigc3d.github.io/LaMP

Transformer-based text-image matching model, known as CLIP, has garnered significant attention owing to its exceptional performance in text-image retrieval tasks and downstream applications. However, the interpret-ability of CLIP remains underexplored. Existing interpretation methods for Transformers often struggle with incomplete and unreliable attributions within the image and text modalities, respectively. In this paper, we propose a fine-grained interpretation method, termed Class Activation Values (CAV), to provide lucid and faithful visual explanations for CLIP-based text-image retrievals. Specifically, we systematically perform multi-scale accumulation and fusion of class-specific gradients and activation value features to generate high-definition explanations for the image encoder. Furthermore, we present element-wise gradient-based weights to attribute fine-grained relevance between value features and output similarity within the text encoder. The proposed CAV is capable of simultaneously rendering detailed and credible explanations due to its precise feature attribution. Extensive qualitative and quantitative experiments are conducted on the ImageNet-1k and MS COCO datasets, and the experimental results demonstrate that CAV outperforms state-of-the-art interpretation methods in both faithfulness and localization assessments across image and text modalities.

The continual emergence of new entities and relations drives the dynamic expansion of knowledge graphs (KG). In the face of such growing KG, relearning from scratch wastes acquired knowledge, while learning solely from new snapshots leads to model forgetting of old knowledge. Existing methods focus on lifelong learning in growing KG through transfer and regularize embeddings. However, extensive entity updates to adapt to new snapshots introduce conflicts between old and new knowledge, thereby resulting in the inevitable occurrence of knowledge forgetting. To address these challenges, we propose the Evolutionary Relation Path Passing (ERPP) model for lifelong knowledge graph embedding, aiming to shift from knowledge forgetting to knowledge accumulation, thereby achieving accurate long-term prediction. Specifically, we propose a snapshot conditional relation path passing strategy to generate expressive representations that better adapt to snapshots compared to the transferred embeddings in existing methods. Subsequently, we propose a relation inheritance and evolution mechanism across snapshots and continue relation path passing in next snapshots. This allows ERPP to avoid inevitable catastrophic forgetting from frequent entity embedding updates. ERPP outperforms SOTA models in 35 scenarios, with average improvements of 11.1% in long-term prediction and 12.9% in knowledge transfer. Moreover, ERPP makes a breakthrough in achieving knowledge positive accumulation, in contrast to the negative forgetting of existing models. To the best of our knowledge, ERPP is the first model to realize knowledge accumulation. Our code is available at https://anonymous.4open.science/r/ERPP-6D66.

Blockchain-enabled digital currency systems have typically operated in isolation, lacking necessary mechanisms for seamless interconnection. Consequently, transferring assets across distinct currency systems remains a complex challenge, with existing schemes often falling short in ensuring security, privacy, and practicality. This paper proposes P2C2T - a privacy-preserving cross-chain transfer scheme. It is the first scheme to address atomicity, unlinkability, indistinguishability, non-collateralization, and required functionalities across diverse currency systems. P2C2T is based on threshold anonymous atomic locks (TA2L), also proposed by us, serving as the cornerstone for guaranteeing atomic cross-chain transfer while obscuring the payment relationships between users. By combining TA2L with verifiable timed discrete logarithm schemes, P2C2T renders cross-chain transactions indistinguishable from regular intra-chain ones. Notably, P2C2T eliminates the collateralization of senders and imposes minimal requirements on underlying blockchains, specifically on the ability to verify signatures. We substantiate the security of TA2L based on a proposed cryptographic notion called threshold blind conditional signatures and demonstrate the security of P2C2T through necessary proofs. Additionally, we compare the performance of P2C2T with an existing scheme that has properties closest to P2C2T. The comparison reveals that P2C2T reduces overhead by at least 85.488% in terms of running time, communication cost, and storage cost when completing a cross-chain transfer. We further conduct cross-chain transfers and intra-chain payments using the Bitcoin testnet and Litecoin testnet to illustrate the privacy and practicality of P2C2T.

Multimodal Knowledge Graphs (MMKG) models integrate multimodal contexts to improve link prediction performance. All existing MMKG models follow the transductive setting with a fixed predefined set, meaning that all the entities, relations, and multimodal information in the test graph are observed during training. This hinders their generalization to real-world MMKG with unseen entities and relations. Intuitively, a MMKG model trained on DBpedia cannot infer on Freebase. To address above limitations, we make the first attempt towards inductive learning for MMKG and propose a multimodal Inductive MMKG model (IndMKG) that is universal and transferable to any MMKG. Distinct from existing transductive methods, our model does not rely on specific trained embeddings; instead, IndMKG generates adaptive embeddings conditioned on any new MMKG via multimodal prototypes. Specifically, we construct class-adaptive prototypes to appropriately characterize the multimodal feature distribution of the given graph and equip IndMKG with robust adaptability to multimodal information across MMKGs. In addition, IndMKG learns non-specific structural embeddings based on meta relations. Such strategies tackle the challenge of notable multimodal feature discrepancies in cross-graph induction and allow the pre-trained IndMKG model to effectively zero-shot generalize to any MMKG. The strong performance in both inductive and transductive settings, across more than 20+ different scenarios, confirms the effectiveness and robustness of IndMKG. Our code is released at https://github.com/MMKGer/IndMKG/.

ABSTRACT A total of 12 papers were accepted for the special issue on the topic of ‘New Technologies of Artificial Intelligence in Convergence ICT’. Recently, as the convergence of artificial intelligence continues to occur in various fields, various technologies are emerging. In this paper, 12 papers introduce AI utilisation technologies in various fields such as smart city, security, medical, economy, healthcare and electricity.

With the continuous advancement of intelligent vehicle technology, the image data generated by vehicles has become increasingly critical in various applications, including driver assistance, traffic monitoring, and safety warning systems. However, this growing reliance on image data also raises pressing concerns regarding its security and privacy protection. Searchable encryption technology, as an effective means to protect data security, shows significant potential for application in the field of intelligent vehicles. In this paper, we propose a novel Privacy-pReserving Image Searchable Encryption Scheme (PRISE) to address the security and privacy challenges associated with image data in intelligent vehicles. The PRISE scheme employs Multilinear Principal Component Analysis (MPCA) to extract data features and integrates symmetric encryption and matrix encryption techniques to ensure image privacy protection. To enhance search efficiency, we utilize a Mahalanobis distance-based fuzzy C-means (FCM) clustering method, which accelerates the search process on the cloud server. We conducted comprehensive experiments to evaluate our proposed scheme, and the results were consistent with our analytical findings, confirming the security of our approach. Comparative experiments with existing schemes demonstrated that our proposed method achieves higher accuracy while maintaining a comparable query time.

As a prevalent computing paradigm, graph computing provides an effective service strategy for the analysis of big data within the Internet of Everything (IoE), particularly for clustering graph-structured data in the IoE. Among various methods, graph contrastive clustering, which is devoted to revealing the intrinsic structure of graphs and efficiently grouping nodes into distinct clusters by contrasting positive-negative counterparts, has attracted widely attention in recent years. However, the existing methods seriously ignore the graph topology and node attributes when setting positive and negative sample pairs, which further leads to node semantic inconsistency. To this end, we design a novel tensor representation-based multiview contrastive graph representation learning framework, including adaptive data augmentation, high-confidence sample pairs construction, and a simple yet effective self-optimizing module guided by clustering objective function, to address issues of graph contrastive learning in ignoring complementary information among the topology and attributes. Specifically, by jointly modeling the graph structure and multiview node attributes, the new proposed clustering model can concurrently mine both hard positive and negative samples, and dynamically enhance the weight allocation of the hard samples during the learning process. Then leveraging the characteristics of graph-structured data, we incorporate a small subset of nodes with the highest similarity as additional positive samples to improve the discriminative power of the proposed model. Furthermore, a self-optimizing clustering module is introduced to enhance the algorithm’s performance. Experimental results on four commonly used IoE-related data sets validate that our proposed approach can achieve state-of-the-art clustering performance.

Coverage maximization under full connection constraints involves many factors and poses huge challenge in mobile wireless sensor networks. Most of research works on this issue are based on the disk model, which have high complexity and long iterations, and therefore cannot be applied to dynamic complex networks. In this paper, the problem of confident information coverage maximization under full connectivity constraints (CIC-CC) is defined based on the confident information coverage model (CIC). To address this problem, a 3-stage connectivity constrained coverage maximization algorithm (3-CCC) is proposed with the time complexity of O(T*n2). 3-CCC contains three stages: maximizing coverage (MC), full connectivity (FC), and maximizing connectivity constrained coverage (MCCC). These three stages can be used in whole or in part to achieve coverage maximization with connectivity constraints depending on the network state. The stable matching mechanism, greedy algorithm, and Q-learning are utilized to improve the algorithm’s efficiency. Experiments show that the proposed algorithm has good performance in terms of iteration number, running time, and coverage rate.

Industrial Internet of Things (IIoT) is evolving toward decentralization and autonomous operation. Nodes in decentralized IIoT collaboratively sense data and communicate to participate in meta-computing and provide diverse intelligent services. Area coverage reliability evaluates the information collaborative intelligence sensing and communication capabilities of nodes in decentralized IIoT for a target area. It serves as a crucial performance evaluation metric for the meta-computing and intelligent services of decentralized IIoT. Existing area coverage reliability evaluation algorithms do not consider the dynamic node states in decentralized IIoT, and overlook the capability of nodes to collaborate in meta-computing. To address these issues, this article proposes a novel confident information coverage (CIC)-based area coverage reliability metric (CACREL), which comprehensively considers node multistate, node collaboration, network coverage rate, and network connectivity. To effectively evaluate CACREL, a CIC-based coverage reliability evaluation algorithm (CACR) is proposed. Specifically, CACR transforms complex networks into grid networks and utilizes a coverage table (CT) to describe different coverage states of each grid, which reduces the complexity of the area coverage reliability evaluation. Additionally, CACR employs a reliable path algorithm to converge the CT of each grid to the sink node based on grid connectivity. Simulation results demonstrate that the proposed CACR can accurately evaluate the area coverage reliability of decentralized IIoT and enhance its service performance.

The rapid development and usage of digital technologies in modern intelligent systems and applications bring critical challenges on data security and privacy. It is essential to allow cross-organizational data sharing to achieve smart service provisioning, while preventing unauthorized access and data leak to ensure end users’ efficient and secure collaborations. Federated Learning (FL) offers a promising pathway to enable innovative collaboration across multiple organizations. However, more stringent security policies are needed to ensure authenticity of participating entities, safeguard data during communication, and prevent malicious activities. In this paper, we propose a Decentralized Federated Graph Learning (FGL) with Lightweight Zero Trust Architecture (ZTA) model, named DFGL-LZTA, to provide context-aware security with dynamic defense policy update, while maintaining computational and communication efficiency in resource-constrained environments, for highly distributed and heterogeneous systems in next-generation networking. Specifically, with a re-designed lightweight ZTA, which leverages adaptive privacy preservation and reputation-based aggregation together to tackle multi-level security threats (e.g., data-level, model-level, and identity-level attacks), a Proximal Policy Optimization (PPO) based Deep Reinforcement Learning (DRL) agent is introduced to enable the real-time and adaptive security policy update and optimization based on contextual features. A hierarchical Graph Attention Network (GAT) mechanism is then improved and applied to facilitate the dynamic subgraph learning in local training with a layer-wise architecture, while a so-called sparse global aggregation scheme is developed to balance the communication efficiency and model robustness in a P2P manner. Experiments and evaluations conducted based on two open-source datasets and one synthetic dataset demonstrate the usefulness of our proposed model in terms of training performance, computational and communication efficiency, and model accuracy, compared with other four state-of-the-art methods for next-generation networking security in modern distributed learning systems.

Due to the particularity of the marginal environment, edge-based autonomous systems face significant risks associated with security operations. Traffic anomaly detection in edge-based autonomous systems has become increasingly crucial for ensuring the security of these systems. Existing works lack consideration of the relationship between traffic attributes and anomaly types. In particular, existing solutions struggle with detecting anomalies that primarily manifest statistical signs in only a few attributes. To address this, we propose a nonnegative factorization-based attribute residual summary and a nonparametric statistic framework for adaptive security monitoring in edge-based autonomous systems. Specifically, the nonnegative factorization, which depends on the multiplicative update rules, is introduced to extract attribute features. Using the tensor linear representation, the attribute residual summary is built, which depicts the statistic discrepancy well even if only a few of traffic attributes are affected, to implement adaptive security monitoring for various attacks in edge-based autonomous systems. Then, a nonparametric statistic framework is developed, which achieves the real-time detection by accumulating and comparing each statistic evidence. Extensive experiments with real-world traffic trace datasets validate the adaptivity, accuracy, real-time performance, and superiority of our method, particularly in dealing with anomalies that exhibit statistical signs in only a few traffic attributes.

The equipment digital twins (EDTs) for discrete manufacturing should be calibrated quickly to avoid irreversible physical damage to the equipment caused by biased control commands. Therefore, an online credibility assessment method for EDTs is urgently needed. However, existing assessment approaches consume too much time, and thus could not reveal dynamic faults in time. In this paper, the dynamic relationship between online evolution and actual applications of EDTs is investigated. Then, two steps are proposed to accelerate the assessment process significantly. One involves pre-constructing a performance-deviation-agent (PDA), and the other involves dynamically fitting the application-time-window (ATW) probability distribution. The methodology is applicable to discrete manufacturing processes. The dynamic credibility of EDT evolution process can be updated after every iteration of the model evolution. Sorting manufacturing equipment was used as a case study to demonstrate the effectiveness of this method. The time consumption was reduced by 90% compared with traditional assessment methods in the case.

With the explosion of social media platforms, a substantial amount of data is generated from social information network. Tensor-based multi-modal clustering methods have been widely applied in various scenarios of social information network by mining potential correlative relationships from large-scale heterogeneous data. Nevertheless, the accuracy and efficiency of tensor-based multi-modal clustering methods are seriously restricted by noise data and the curse of dimensionality. Therefore, this paper presents a Tucker-based multi-modal clustering (TuMC) and an improved TuMC (ITuMC) to enhance the accuracy and efficiency of multi-modal clustering. First, we propose two Tucker-based attribute weight ranking learning approaches to calculate weight tensor efficiently. Then, we present a calculation approach for Tucker-based selective weighted tensor distance (SWTD) and a TuMC method. Meanwhile, an ITuMC method is explored by optimizing the calculation efficiency of the SWTD to further improve clustering speed. Finally, we present a Tucker-based multi-modal clustering and service framework for social information network. Extensive experimental results based on social Geolife GPS trajectory and electricity consumption datasets demonstrate that the TuMC and ITuMC methods can cluster multi-source heterogeneous data with both higher accuracy and efficiency under complex social information network by DVI, AR and execution time measurement.

Canonical Polyadic decomposition (CPD) obtains the low-rank approximation for high-order multidimensional tensors through the summation of a sequence of rank-one tensors, greatly reducing storage and computation overhead. It is increasingly being used in the lightweight design of artificial intelligence and big data processing. The existing CPD technology exhibits inherent limitations in simultaneously achieving high accuracy and high efficiency. In this paper, a heterogeneous computing method for CPD is proposed to optimize computing efficiency with guaranteed convergence accuracy. Specifically, a quasi-convex decomposition loss function is constructed and the extreme points of the Kruskal matrix rows have been solved. Further, the massively parallelized operators in the algorithm are extracted, a software-hardware integrated scheduling method is designed, and the deployment of CPD on heterogeneous computing platforms is achieved. Finally, the memory access strategy is optimized to improve memory access efficiency. We tested the algorithm on real-world and synthetic sparse tensor datasets, numerical experimental results show that compared with the state-of-the-art method, the proposed method has a higher convergence accuracy and computing efficiency. Compared to the standard CPD parallel library, the method achieves efficiency improvements of tens to hundreds of times while maintaining the same accuracy.

Multimodal sentiment analysis (MSA) integrates multiple sources of sentiment information for processing and has demonstrated superior performance compared to single-modal sentiment analysis, making it widely applicable in domains such as human–computer interaction and public opinion supervision. However, current MSA models heavily rely on black-box deep learning (DL) methods, which lack interpretability. Additionally, effectively integrating multimodal data, reducing noise and redundancy, as well as bridging the semantic gap between heterogeneous data remain challenging issues in multimodal DL. To address these challenges, we propose an interpretable multimodal Tucker fusion model with information filtering (IMTFMIF). We are the first to utilize the multimodal Tucker fusion model for MSA tasks. This approach maps multimodal data into a unified tensor space for fusion, effectively reducing modal heterogeneity and eliminating redundant information while maintaining interpretability. Furthermore, mutual information is employed to filter out task-irrelevant information and explain the association between input and output from an information flow perspective. We propose a novel approach to enhance the comprehension of multimodal data and optimize model performance in MSA tasks. Finally, extensive experiments conducted on three public multimodal datasets demonstrate that our proposed IMTFMIF achieves competitive performance compared to state-of-the-art methods.

Healthcare social networks (HSNs) are pivotal in spreading healthcare knowledge, providing support to both potential patients and medical professionals, and enhancing healthcare services. However, identifying unseen data in HSN poses a significant challenge due to their intrinsic heterogeneity, dynamic characteristics, and the scarcity of labeled data. Employing semantic knowledge transfer for class-agnostic zero-shot recognition stands out as a promising and innovative solution to this problem, but the visual-semantic gap and domain shift problems considerably hinder advancements in zero-shot recognition capabilities. Previous zero-shot models often impose constraints between vision and semantics in the loss part without explicitly injecting intermodality guidance into the feature refinement process. This article yields a novel zero-shot recognition framework for HSN, named the dual tensor prototype graph network, devoted to improving the performance of recognizing unseen objects in HSN leveraging semantic knowledge. We have developed an iterative and interactive updating strategy for dual tensor prototype graphs, explicitly leveraging the distribution information from one modality to guide the prototype graph updates of another modality. We constrain the update process of the dual prototype graphs by several tailored loss functions and episodic training, alleviating the inconsistency between semantic and visual manifolds. Extensive comparative experiments conducted on two medical imaging datasets and five zero-shot benchmarks affirm the stronger generalization ability of our proposed method compared with other advanced approaches, showing the potential of addressing zero-shot problems in HSN.

As a key infrastructure for social fintech ecosystems, ethereum enables decentralized finance (DeFi) applications where security issues directly compromise ecosystem stability. Among critical security concerns, ethereum phishing scams stand as typical scams. Criminals employ distinctive fund transfer patterns (e.g., money laundering stages: placement, layering, and integration) to obscure illicit funds through long transaction paths. While graph neural networks (GNNs) dominate detection methods, they fail to model these long paths effectively. To address this, we propose the first framework to detect phishing scams through explicitly modeling fund transfer patterns. Our novel method, IMPUTATION, introduces: 1) a heuristic fund transfer path graph construction method utilizing iterative transaction pairing to capture complicated fund transfer patterns; 2) role-topology account embeddings encoding fund transfer patterns; 3) attention fusion leveraging initial transactions to suppress path noise; and 4) heterogeneous correlation graphs with weighted adjacency reconstruction modeling interpath dependencies. Extensive experiments demonstrate that IMPUTATION outperforms on all five metrics and detecting Ethereum phishing scams from fund transfer patterns is effective.

Due to the strong untraceability of mixing services, numerous criminals exploit these services to engage in illicit activities, posing a significant threat to the blockchain ecosystem. This paper addresses the challenge of linking transaction addresses in Tornado Cash, a popular mixing service on Ethereum. While existing state-of-the-art solutions like MixBroker attempt to address this problem, two fundamental limitations persist: insufficient utilization of neighbor information and neglect of address information asymmetry. To address these gaps, a novel framework termed “MixLinker” is proposed, which enhances neighbor information utilization and models information asymmetry. Specifically, a Normalized Adjusted Personal PageRank (NAPPR) module is designed to prioritize significant neighbor nodes while mitigating interference from super and irrelevant addresses. Additionally, tensors are employed to model transactions, capturing rich interaction features related to transaction attributes. Based on historical transaction sequences, Tensor Long Short-Term Memory (TLSTM) is used to obtain high-quality initial input features for the Graph Neural Network (GNN) module, enabling effective learning of nonlinear dynamics. To ensure symmetric output results and model asymmetric information, a temporal-aware symmetry classifier is constructed that leverages asymmetric information through permutation operations and an order-aware classifier. Extensive experiments demonstrate that MixLinker outperforms other methods, validating the effectiveness of the proposed approach and confirming the two underlying motivations.

The breakthroughs of next-generation information technologies have accelerated the advancement of industrial cyber-physical intelligence (ICPI), particularly in system intelligence and applications. However, this progress has also brought challenges in ensuring operational reliability and system intelligence. Anomaly detection, a critical component of fault-tolerant and intelligent ICPI, is usually addressed by treating it as a one-class classification and location problem. While autoencoder frameworks have shown promise in addressing this challenge, most existing methods usual struggle with precise anomaly identification or require resource-intensive region-based training. Furthermore, the dynamic nature of anomalies and the scarcity of labeled training data complicate the development and evaluation of anomaly detection models. In this article, an innovative tensor-based knowledge distillation approach (TKDA) is introduced, which integrates a pretrained teacher network, a tensor-decomposed student network, and a denoising module into a unified framework. Anomalies are identified and localized by analyzing differences in intermediate activation values between teacher and student networks during data processing. Extensive experiments demonstrate that TKDA addresses the limitations of low accuracy in anomaly location and inefficiency in computational processes, achieving significant improvements across diverse datasets, including F-MNIST, MNIST, CIFAR-10, MVTecAD, Retinal-OCT, and two medical datasets.

Artificial intelligence (AI) is now widely adopted across fields, prompting AI companies to deploy models to the cloud for cost, resource, and scalability benefits. However, these cloud-hosted models face security and credibility challenges. Equipment failures or network attacks may compromise data integrity, while commercial interests might cause AI companies or cloud providers to deploy models deviating from their stated specifications, such as version or copyright details. To address these issues, we introduce AI-auditor, a novel data auditing framework that verifies both data integrity and model alignment with declared specifications. Using a challenge-response approach, AI-auditor maintains constant bandwidth usage and O(1) verification efficiency, regardless of file size. It also features a multikey management server mechanism to generate user keys, minimizing risks of single-point failures and trust issues. Analysis and simulations confirm AI-auditor’s correctness, security, and high execution efficiency.

Deep learning provides an intelligent analytical approach for Big Data analysis and feature extraction in Industrial Internet of Things (IIoT). However, due to concerns about data security and privacy disclosure, conventional data-centralized deep learning often faces difficulties about data famine and data islands. Federated learning (FL) as a novel privacy-preserving deep learning paradigm breaks the data islands among different smart factories by sharing their model parameters instead of raw data, which essentially solves the data famine problem for training a high-quality deep learning model. Nevertheless, exchanging numerous model parameters not only generates considerable communication overhead but also poses the risk of privacy information disclosure hidden in model parameters due to inference attacks launched by external attackers orhonest-but-curiousservers. The purpose of this article is to build a high-quality trustworthy FL architecture dubbed TrustFedGRU for IIoT while alleviating the communication overhead. First, a multikey decryption assisted privacy-preserving homomorphic encryption scheme is proposed in FL to meet the distinct privacy-preserving requirements of different data owners without impairing model performance. Furthermore, tensor decomposition is leveraged to convert the weight tensor of the gated recurrent unit (GRU) into a low-rank approximation, so as to reduce the communication bandwidth overhead and decrease the storage requirements. Meanwhile, a novel dynamic update-based FL approach is investigated to improve the model performance. The experimental results show that the proposed TrustFedGRU greatly reduces the communication overhead while guaranteeing the model performance and security.

Nonnegative CANDECOMP/PARAFAC (CP) factorization of incomplete tensors is a powerful technique for finding meaningful and physically interpretable latent factor matrices to achieve nonnegative tensor completion. However, most existing nonnegative CP models rely on manually predefined tensor ranks, which introduces uncertainty and leads the models to overfit or underfit. Although the presence of CP models within the probabilistic framework can estimate rank better, they lack the ability to learn nonnegative factors from incomplete data. In addition, existing approaches tend to focus on point estimation and ignore estimating uncertainty. To address these issues within a unified framework, we propose a fully Bayesian treatment of nonnegative tensor completion with automatic rank determination. Benefitting from the Bayesian framework and the hierarchical sparsity-inducing priors, the model can provide uncertainty estimates of nonnegative latent factors and effectively obtain low-rank structures from incomplete tensors. Additionally, the proposed model can mitigate problems of parameter selection and overfitting. For model learning, we develop two fully Bayesian inference methods for posterior estimation and propose a hybrid computing strategy that reduces the time overhead for large-scale data significantly. Extensive simulations on synthetic data demonstrate that our model can recover missing data with high precision and automatically estimate CP rank from incomplete tensors. Moreover, results from real-world applications demonstrate that our model is superior to state-of-the-art methods in image and video inpainting. The code is available at https://github.com/zecanyang/BNTC.

The large-scale applications of wireless sensor networks (WSNs) place higher demands on their reliability. WSNs deployed in the intelligent tunnel are often affected by environmental interference or malicious intrusions, which lead to untrusted paths and affect the reliability of transmission. A trusted path ensures that the collected information can be successfully and reliably transmitted to the sink node. To solve the transmission reliability problem of wireless sensor networks, a trusted multi-source shortest path-based transmission reliability (TMSPR) algorithm is proposed in this paper. A lightweight trust management model with a node relation matrix (RM) is applied to identify and exclude untrusted nodes, thereby establishing secure transmission links. Meanwhile, the shortest transmission path is selected based on the minimum path to save the energy of the nodes. The information transmitted through trusted multi-source shortest paths (TMSPs) can successfully reach the sink node, which significantly improves the transmission reliability of the network. Furthermore, a transmission reliability indexTRelis defined as a probabilistic measure to assess reliability. Simulation results demonstrate that the proposed algorithm exponentially reduces both computation time and memory usage, while enhancing transmission reliability by approximately 5%.

Accurate and reliable traffic speed data prediction is crucial for Transportation Cyber-Physical Systems (T-CPS), as it directly impacts real-time traffic management, safety control, and overall system efficiency. However, existing deep learning-based traffic speed data prediction methods often require extensive training data and lack interpretability in their predictions. Although matrix and tensor factorization-based approaches enhance interpretability, the performance of these approaches is challenged in scenarios with extremely sparse observed data. These challenges greatly undermine the reliability of predictions and compromise the safety control of T-CPS. To alleviate these shortcomings, this paper proposes a Collaborative Bayesian Tensor Factorization (CBTF) method and applies it to the cloud-edge collaborative traffic speed data prediction scenario. By utilizing a shared factor matrix for collaborative tensor factorization, the proposed method can effectively predict missing data even with extremely limited observed data. For model learning, a posterior estimation method based on Markov Chain Monte Carlo (MCMC) is developed within a Bayesian framework. This approach not only provides point estimates for traffic speed predictions but also offers interval estimates, greatly improving the reliability and interpretability of the results. Extensive simulations demonstrate that the proposed method outperforms several existing approaches. Moreover, collaborative learning experiments reveal the superiority of the proposed approach, particularly in scenarios with a large number of edge nodes in a collaborative learning framework, and each edge node’s data is extremely sparse. Finally, the evaluation of the prediction interval validates the reliability of the proposed method.

Multi-dimensional range queries performed on the mobile user data records become increasingly important and popular in the fields of e-commerce, social media, transportation logistics, etc. Meanwhile, mobile users usually have different privacy requirements for different attributes of the records. A straightforward and effective approach is to first get low-dimensional range query outcomes by using existing LDP mechanisms at different privacy levels, and then derive high-dimensional range query results at each level, and finally aggregate the results from all levels. However, it incurs low utility of the query results, since the non-fixed privacy budgets and the correlation between dimensions (attributes) detrimentally impact the utility of LDP methods, ultimately rendering them ineffective in practice. In this paper, we propose a new Personalized LDP approach for Multi-dimensional Range queries (PLDP-MR) over mobile user data, consisting of the user grouping, data perturbing, data re-perturbing, and range query results aggregating steps. First, PLDP-MR offers flexible dual grouping based on user-selected privacy levels and relevant attributes to obtain the corresponding one-dimensional and two-dimensional grids. PLDP-MR optimizes the grid granularity to minimize errors from perturbing users' attribute data with different LDP noises at non-fixed privacy levels. Furthermore, PLDP-MR carefully re-perturbs the LDP-noisy data from mobile users at lower privacy levels (i.e., having the higher utility) to achieve LDP with higher privacy levels and supplement the data volume of the corresponding groups. Thus, the data utility is effectively improved without additional privacy losses. Finally, PLDP-MR aggregates the frequencies in all the one-dimensional and two-dimensional grids related to the multi-dimensional range query at all query intervals and all privacy levels to derive the final query result with considering the correlation between attributes. The aggregations use maximum entropy optimization and maximum likelihood methods to further enhance its utility. The privacy and utility of PLDP-MR are analyzed, and extensive experiments demonstrate its effectiveness.

Over the past few years, multiview attributed graph clustering has achieved promising performance via various data augmentation strategies. However, we observe that the aggregation of node information in multilayer graph autoencoder (GAE) is prone to deviation, especially when edges or node attributes are randomly perturbed. To this end, we innovatively propose a tensor-representation-based multiview attributed graph clustering framework with smooth structure (MV_AGC) to avoid the bias caused by random view construction. Specifically, we first design a novel tensor-product-based high-order graph attention network (GAT) with structural constraints to realize efficient attribute fusion and semantic consistency encoding. By imposing attribute augmentation mechanisms and smooth constraints (SCs) on the proposed high-order graph attention autoencoder simultaneously, MV_AGC effectively eliminates the instability of reconstructed graph structures and learns a more compact node representation during training. In addition, we also theoretically analyze the stronger generality and expressiveness of the proposed tensor-product-based attention mechanism over the classical GAT and establish an intuitive connection between them. Furthermore, to address the performance degradation caused by clustering distribution updating, we further develop a simple yet effective clustering objective function-guided self-optimizing module for the final clustering performance improvement. Experimental results on the six benchmark datasets have demonstrated that our proposed method can achieve state-of-the-art clustering performance.

Recently, deep learning-based models such as transformer have achieved significant performance for industrial remaining useful life (RUL) prediction due to their strong representation ability. In many industrial practices, RUL prediction algorithms are deployed on edge devices for real-time response. However, the high computational cost of deep learning models makes it difficult to meet the requirements of edge intelligence. In this article, a lightweight group transformer with multihierarchy time-series reduction (GT-MRNet) is proposed to alleviate this problem. Different from most existing RUL methods computing all time series, GT-MRNet can adaptively select necessary time steps to compute the RUL. First, a lightweight group transformer is constructed to extract features by employing group linear transformation with significantly fewer parameters. Then, a time-series reduction strategy is proposed to adaptively filter out unimportant time steps at each layer. Finally, a multihierarchy learning mechanism is developed to further stabilize the performance of time-series reduction. Extensive experimental results on the real-world condition datasets demonstrate that the proposed method can significantly reduce up to 74.7% parameters and 91.8% computation cost without sacrificing accuracy.

Identifying unseen faults is a crux of the digital transformation of process manufacturing. The ever-changing manufacturing process requires preset models to cope with unseen problems. However, most current works focus on recognizing objects seen during the training phase. Conventional zero-shot recognition methods perform poorly when they are applied directly to these tasks due to the different scenarios and limited generalizability. This article yields a tensor-based zero-shot fault diagnosis framework, termed MetaEvolver, which is dedicated to improving fault diagnosis accuracy and unseen domain generalizability for practical process manufacturing scenarios. MetaEvolver learns to evolve the dual prototype distributions for each uncertain meta-domain from seen faults and then adapt to unseen faults. We first propose the concept of the uncertain meta-domain and then construct corresponding sample prototypes with the guidance of class-level attributes, which produce the sample-attribute alignment at the prototype level. MetaEvolver further collaboratively evolves the uncertain meta-domain dual prototypes by injecting the prototype distribution information of another modality, boosting the sample-attribute alignment at the distribution level. Building on the uncertain meta-domain strategy, MetaEvolver is prone to achieving knowledge transferring and unseen domain generalization with the optimization of several devised loss functions. Comprehensive experimental results on five process manufacturing data groups and five zero-shot benchmarks demonstrate that our MetaEvolver has great superiority and potential to tackle zero-shot fault diagnosis for smart process manufacturing.

Empowered by the continuous integration of social multimedia and artificial intelligence, the application scenarios of Information Retrieval (IR) progressively tend to be diversified and personalized. Currently, User-Generated Content (UGC) systems have great potential to handle the interactions between large-scale users and massive media contents. As an emerging multimedia IR, Fashion Compatibility Modeling (FCM) aims to predict the matching degree of each given outfit and provide complementary item recommendation for user queries. Although existing studies attempt to explore the FCM task from a multi-modal perspective with promising progress, they still fail to fully leverage the interactions between multi-modal information or ignore the item–item contextual connectivities of intra-outfit. In this article, a novel FCM scheme is proposed based on Correlation-Aware Cross-Modal Attention Network. To better tackle these issues, our work mainly focuses on enhancing comprehensive multi-modal representations of fashion items by integrating the cross-modal collaborative contents and uncovering the contextual correlations. Since the multi-modal information of fashion items can deliver various semantic clues from multiple aspects, a modality-driven collaborative learning module is presented to explicitly model the interactions of modal consistency and complementarity via a co-attention mechanism. Considering the rich connections among numerous items in each outfit as contextual cues, a correlation-aware information aggregation module is further designed to adaptively capture significant intra-correlations of item–item for characterizing the content-aware outfit representations. Experiments conducted on two real-world fashion datasets demonstrate the superiority of our approach over state-of-the-art methods.

The distributed computing paradigm of edge computing effectively addresses the challenges of data transmission delay and data privacy security. With the increasing popularity of IoT devices and 5 G networks, edge computing has a broader range of applications. The advancement in AI technology enables the realization of edge intelligence, which conducts data processing and analysis on edge devices to avoid excessive data transmission to the cloud, enhance system response speed, and protect user data privacy. In various edge intelligent systems like smart homes and autonomous driving, multimodal data plays a crucial role. However, missing modalities in such systems may lead to model failure in real-world environments. To tackle this issue, we propose a tensor-empowered modality reconstruction network (TMRN) that utilizes an end-to-end variational autoencoder for reconstructing missing modal data. This approach effectively enhances model robustness while reducing model size and training complexity. Furthermore, we introduce a supervised method for feature reconstruction to better align with the true distribution of missing modal data by leveraging tensor feature fusion and label supervision techniques. Additionally, we design a task information disentanglement module to make multimodal representations more relevant to specific tasks by effectively separating task-relevant from task-irrelevant information. Extensive experiments demonstrate that TMRN achieves competitive performance compared to existing state-of-the-art methods.

Avatar is one of the most intuitive central components in Metaverse and faces serious security problems, particularly during the interaction with each other. In this article, we consider the problem of timely detecting the stealthy anomaly in the avatar interaction, which is crucial for security and privacy in Metaverse. With this goal, a new tensor summary statistic is proposed first to well depict the statistical discrepancy between normal and anomalous interaction volume samples, even when anomalies are stealthy. The proposed tensor summary statistic is established from the tensor linear representation residual, which naturally implies the statistical probability that an interaction volume sample lies within or deviates from the tensor lateral space. Moreover, a convex optimization programme is introduced to robustly recover the tensor lateral space in the presence of anomalous samples, thereby enhancing the robustness of our tensor summary statistic. On the basis of the tensor summary statistic, a non-parametric statistic framework is developed for the real-time detection of the stealthy interaction volume anomaly. We also provide theoretical analysis concerning its detection performance and parameter selection. Extensive experiments using synthetic and real-world datasets verify our effectiveness and superiority. Compared with benchmark methods, the proposed detection scheme achieves significantly lower detection delay and higher false alarm period, particularly in the detection of stealthy anomalies with a low change rate.

Voice assistants, as crucial components of the Internet of Things (IoT), are vulnerable to voice spoofing attacks and pose great threats to the security of IoT. Passive liveness detection distinguishes between genuine and spoofing voices by analyzing the collected voice, eliminating the need for deploying additional sensors. This method plays a crucial role in detecting spoofing speeches and ensuring the security of the IoT. However, current passive liveness detection methods typically require users to adopt specific gestures. Meanwhile, these methods are often designed for specific attacks and cannot accommodate multivariate attacks. To address these challenges, this paper proposes an efficient and robust liveness feature called VoiceID, which utilizes the inherent vocal cord vibrations and voiced language to authenticate the collected voice. The VoiceID is defined as the set of maximum magnitude-peak frequency bins in the magnitude spectrum of each frame for voice. VoiceID can be combined with existing acoustic features to compensate for the granularity gap in extracting fine-grained features and distinguishing between genuine and spoofing voices. Furthermore, to leverage VoiceID, this paper proposes a solid fake voice liveness detection system named SFSys and elaborates on a series of acoustic features that can work with VoiceID. Extensive experiments on authoritative ASVspoof 2019 and ASVspoof 2021 datasets reveal that VoiceID reduces the equal error rate and the minimum tandem decision cost function of the existing acoustic features by at most 6.19% and 0.2479. Moreover, SFSys outperforms existing voice liveness detection schemes and exhibits robustness in various advanced spoofing attack environments.

Visual Mobile Crowd-Sensing (VMCS) collects photos by leveraging camera embedded in mobile users’ phones. There are two important issues in VMCS: determining whether photos collected by mobile users meet the requirements or not and designing an appropriate mechanism to attract mobile users to provide photos that meet the requirements. In this article, we address those two issues when VMCS is applied to emergency monitoring applications. We first model an emergency scene as a disk region and define a coverage angle metric that quantifies the coverage ratio provided by each photo, then formulate a Maximize Coverage Angle with Limited Budget problem. The goal of this work is to recruit mobile users to provide panoramic view coverage for a disk while the total reward paid to participants does not exceed the budget. In our solution, we first propose a Coverage Angle Computation algorithm to calculate the coverage angle of each uploaded photo. Then two incentive mechanisms—the Guidance-based Incentive Mechanism and the Coverage Prediction Incentive Mechanism—are designed to encourage mobile users to upload photos with a coverage angle that are not provided by other mobile users. Finally, we design a mobile app called I-share in the Android system to implement the system. Meanwhile, we recruited students to install I-share and simulated the information interaction between mobile users and the server. We conducted experiments by using I-share without and with an embedded Coverage Angle Computation algorithm to validate the efficiency of the two incentive mechanisms. The experiment results demonstrate that our proposed incentive mechanisms effectively attract mobile users to provide panoramic view coverage of emergency scenes when the budget allows. Additionally, the Coverage Prediction Incentive Mechanism outperforms the Guidance-based Incentive Mechanism, offering a higher coverage ratio with lower rewards.

The need for an adaptive congestion control (CC) service is crucial due to the heterogeneity of systems and the diversity of applications. Traditional CC methods often fail to adaptively balance throughput and delay, struggling to meet the varied demands of different network applications. In this work, we introduceAuto, a novel CC service that employs Multi-Objective Reinforcement Learning (MORL) to transcend these limitations. Unlike conventional approaches,Autooptimizes policies within a single model to cater to all potential preferences for balancing throughput and delay, making it ideal for diverse and heterogeneous network environments. To enhance operational transparency, we developed an interpretation algorithm that translates MORL into a human- readable decision tree, essential for service computing where clarity and interpretability are crucial. Furthermore,Autoallows users to explicitly set flow priorities and target sending rates, meeting varied application demands. Our extensive evaluations show thatAutonot only consistently outperforms existing CC methods in diverse network conditions but also exhibits robustness to stochastic packet loss and rapid network changes. These capabilities establishAutoas a pioneering solution for next-generation congestion control in networking services.

With the rapid development and widespread application of information, computer, and communication technologies, Cyber-Physical-Social Systems (CPSS) have gained increasing importance and attention. To enable intelligent applications and provide better services for CPSS users, efficient data analytical models are crucial. This paper presents a novel data analytic framework for CPSS services. First, a Tensor-Based Factorial Hidden Markov Model (T-FHMM) is introduced to comprehensively analyze multi-user activity features, enhancing CPSS activity analytics. A tensor-based Forward-Backward algorithm is then designed for T-FHMM to efficiently perform evaluation tasks using multiple probabilistic computing micro-services. Additionally, a tensor-based Baum-Welch algorithm is developed to accurately learn model parameters via parameter optimization micro-services. Furthermore, a tensor-based Viterbi algorithm is implemented with specific micro-services to improve prediction tasks. Finally, the comprehensive performance of the proposed model and algorithms is validated on three open datasets through self-comparison and other-comparison. Experimental results demonstrate that the proposed method outperforms compared methods in terms of accuracy, precision, recall, and F1-score.

Cyber-Physical-Social Systems (CPSSs) represent a transformative paradigm that integrates human, machine, and environmental interactions to support intelligent services in smart spaces. However, providing accurate and efficient user activity analysis in such environments remains challenging due to the complex, high-dimensional, and noisy nature of sensory data. Although existing tensor-based models have shown promising accuracy in user activity analysis, they often suffer from low efficiency and reduced robustness to data noise, limiting their practicality in real-time applications. To address these challenges, this study proposes a Tensor-based Hidden Semi-Markov Model (T-HSMM) designed to efficiently analyze user activity durations and their dependencies using probabilistic distributions in tensor space. The main objective is to reduce redundant tensor computations while enhancing both the accuracy and robustness of activity analysis. Moreover, to effectively address the three basic micro-services in CPSSs—evaluation, learning, and prediction—we develop tensor-based algorithms, including the Forward-Backward, Baum-Welch, and Viterbi algorithms, for the proposed T-HSMM. These algorithms facilitate three computational subtasks of activity sequence probabilities, model parameter learning, and activity prediction. We evaluated the performance of the proposed model on three widely used open datasets. The results show that T-HSMM surpasses other models in terms of accuracy, precision, recall, and F1-score while maintaining acceptable time consumption. Additionally, we discuss the impact of varying parameters on the model's performance across different daily activities.

Schema information is increasingly crucial to improve service discovery, recommendation, and composition, addressing link sparsity and lack of explainability inherent in methods relying solely on triples. However, existing approaches predominantly utilize schema information as a rigid filtering mechanism, equivalent to fixed conditions that lack the capability to adaptively adjust based on model learning. This paper introduces a novel learnable schema-aware knowledge embedding framework that enhances service link prediction by synergizing entity, relation, and type embeddings through a coupled matrix-tensor factorization model. To our knowledge, this is the first approach that couples entity and relation embeddings to enable adaptive learning ofSchemaEmbeddings (SchemaE). Our framework is both expressive and easy to use, with the capability to generalize to existing bilinear models. Within this framework, we further propose the schema prompt method for embedding isolated nodes, which typically suffer from sparse relations or the absence of neighbors, leading to biased representation often overlooked in existing works. Despite embedding schema information, our model remains lightweight due to the introduction of a parameter-efficient strategy via type assists. We conduct extensive experiments on four public datasets, including comparisons with existing SOTA models, parameter analysis, performance validation on extended models, and visualization. The experimental results confirm the effectiveness and efficiency of the proposed model.

Wireless-powered multi-access edge computing (WP-MEC), as a promising computing paradigm with the great potential for breaking through the power limitations of wireless devices, is facing the challenges of reliable task offloading and charging power allocation. Towards this end, we formulate a joint optimization problem of wireless charging and computation offloading in socially-aware D2D-assisted WP-MEC to maximize the utility, characterized by wireless devices’ residual energy and the strength of social relationship. To address this problem, we propose a deep reinforcement learning (DRL)-based approach with hybrid actor-critic networks including three actor networks and one critic network as well as with Proximal Policy Optimization (PPO) updating policy. Further, to prevent the policy collapse, we adopt the PPO-clip algorithm which limits the update steps to enhance the stability of algorithm. The experimental results show that the proposed algorithm can achieved superior convergence performance and, meanwhile, improves the average utility efficiently compared to other baseline approaches.

Internet of Things (IoT) reliability evaluation contributes to the sustainable computing and enhanced stability of the network. Previous algorithms usually evaluate the reliability of IoT by enumenating the states of nodes and networks, which are difficult to handle IoT with hundreds of nodes because the computational cost. In this paper, a novel algorithm, TMCRA, is proposed to evaluate the reliability of IoT in complex network environment, which consider both coverage and connectivity. For coverage, TMCRA employs the Confident Information Coverage (CIC) model to divide the target area into independent grids and calculates the coverage rate. In terms of connectivity, TMCRA forming the Virtual Backbone Network (VBN) based on two proposed methods: TMA and MGIN, and evaluate connectivity by analyzing the VBN rather than the whole network. The TMA and MGIN are two algorithms for constructing Minimum Connected Dominant Sets (MCDS), which are suitable for different scale networks. Finally, based on the data of coverage and connectivity, TMCRA utilizes tensors for the unified modeling and representation of network structure, and calculates IoT reliability based on the tensors. Simulations are carried out for various sizes of IoT to show the advantages and effectiveness of the proposed approach in reliability evaluation.

The pre-training architectures of large language models encompass various types, including autoencoding models, autoregressive models, and encoder-decoder models. We posit that any modality can potentially benefit from a large language model, as long as it undergoes vector quantization to become discrete tokens. Inspired by the General Language Model, we propose a General Point Model (GPM) that seamlessly integrates autoencoding and autoregressive tasks in a point cloud transformer. This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks. GPM enhances masked prediction in autoencoding through various forms of mask padding tasks, leading to improved performance in point cloud understanding. Additionally, GPM demonstrates highly competitive results in unconditional point cloud generation tasks, even exhibiting the potential for conditional generation tasks by modifying the input's conditional information. Compared to models like Point-BERT, MaskPoint. and PointMAE, our GPM achieves superior performance in point cloud understanding tasks. Furthermore, the integration of autoregressive and autoencoding within the same transformer underscores its versatility across different downstream tasks. Codes are available at https://github.com/gentlefress/GPM

The scarcity of annotated data has sparked signifi-cant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medi-cal visual representation learning. However, existing re-search overlooks the multi-granularity nature of medical visual representation and lacks suitable contrastive learning techniques to improve the models' generalizability across different granularities, leading to the underutilization of image-text information. To address this, we pro-pose MLIP, a novel framework leveraging domain-specific medical knowledge as guiding signals to integrate language information into the visual domain through image-text contrastive learning. Our model includes global contrastive learning with our designed divergence encoder, lo-cal token-knowledge-patch alignment contrastive learning, and knowledge-guided category-level contrastive learning with expert knowledge. Experimental evaluations reveal the efficacy of our model in enhancing transfer performance for tasks such as image classification, object detection, and semantic segmentation. Notably, MLIP surpasses state-of-the-art methods even with limited annotated data, highlighting the potential of multimodal pre-training in advancing medical representation learning.11Codes are available at https://github.com/gentlefress/MLIP

Neural Radiance Fields (NeRF) has recently overhauled novel view synthesis, but it requires extensive computations for training and captures variations in detail with difficulty. In this paper, we propose a novel framework, termed CD-TDRF, to mitigate these dilemmas. CD-TDRF factorizes a density voxel grid into a core tensor and three matrices via Tucker decomposition, reducing memory usage and accelerating training. To better capture variations in complex scenes, CD-TDRF uses a fully convolutional network to extract prior information from the training images. Moreover, three learnable appearance planes are constructed to preserve information about scene details, which enhances the rendering quality significantly. Our experimental results demonstrate that CD-TDRF has achieved competitive rendering quality on three popular datasets and speeds up training compared with traditional NeRF models.

With the bit density improvement and the three-dimensional NAND flash techniques, solid-state drives (SSDs) dramatically increase the storage capacity and performance. However, the incorporation of multiple flash chips within a single flash channel structure in SSDs introduces the access path conflicts when servicing multiple I/O requests accessing flash chips on the same channel. To meet the increasing performance demands of modern applications, network SSDs that employ the interconnection network of flash chips, has a high potential to address the access path conflicts by fundamentally increasing the number of the available access paths. In this paper, we propose SmartNetSSD, a new scheme that utilizes the path diversity in network SSD to dramatically mitigate access path conflicts. SmartNetSSD employs the following key techniques: 1) A multi-path routing algorithm, MProuting, identifies the multiple access paths for read operations. 2) A network-based read-retry technique, NetRR, pipelines the con-secutive read-retry steps for a read operation across the multiple access paths. The experimental results show that SmartNetSSD improves I/O performance by an average of 46.29% over the state-of-the-art approach.

Based on the recent popularity of diffusion models, we have proposed a tensor-based diffusion model for 3D shape generation (TD3D). This generator is capable of tasks such as unconditional shape generation, shape completion and cross-modal shape generation. TD3D utilizes the Vector Quantized Variational Autoencoder (VQ-VAE) for encoding, compressing 3D shapes into compact latent representations, and then learns the discrete diffusion model based on it. To preserve high-dimensional feature information, we propose a tensor-based noise injection process. To capture 3D features in space faster and use them, a ResNet3D module is introduced during the denoising process. To fuse shape features obtained from ResNet3D and Self-Attention mechanisms, we employ a tensor-based Self-Attention mechanism (T-SA) fusion method. Lastly, a ResNet3D-assisted Multi-Frequency Fusion Module (R-MFM) is designed to aggregate high and low frequency features. Based on the aforementioned design, TD3D provides high fidelity, diverse generated samples, and have the ability to generate 3D shapes across modalities. Extensive experiments have demonstrated its superior performance in various 3D shape generation tasks.

With the breakthrough of large models, Segment Anything Model (SAM) and its extensions have been attempted to apply in diverse tasks of computer vision. Underwater salient instance segmentation is a foundational and vital step for various underwater vision tasks, which often suffer from low segmentation accuracy due to the complex underwater circumstances and the adaptive ability of models. Moreover, the lack of large-scale datasets with pixel-level salient instance annotations has impeded the development of machine learning techniques in this field. To address these issues, we construct the first large-scale underwater salient instance segmentation dataset (USIS10K), which contains 10,632 underwater images with pixel-level annotations in 7 categories from various underwater scenes. Then, we propose an Underwater Salient Instance Segmentation architecture based on Segment Anything Model (USIS-SAM) specifically for the underwater domain. We devise an Underwater Adaptive Visual Transformer (UA-ViT) encoder to incorporate underwater domain visual prompts into the segmentation network. We further design an out-of-the-box underwater Salient Feature Prompter Generator (SFPG) to automatically generate salient prompters instead of explicitly providing foreground points or boxes as prompts in SAM. Comprehensive experimental results show that our USIS-SAM method can achieve superior performance on USIS10K datasets compared to the state-of-the-art methods. Datasets and codes are released on https://github.com/LiamLian0727/USIS10K.

Increasing diversity of applications and services are being migrated to modern data center networks (DCNs), and these applications and services are typically generating various combinations of long and short flows with or without deadlines. However, most existing flow scheduling solutions for DCNs either adopt single-queue strategy (e.g., D2TCP) that inevitably results in non-urgent flows blocking urgent flows or multi-queue mechanism (e.g., Aemon) that is at the cost of packet reordering. In this paper, we present DPOT, a Dynamic Priority-based Ordered Transmission mechanism that is aimed at minimizing the flow completion time and deadline missing rate. To avoid the urgent flows being blocked by the non-urgent flows, the DPOT switch adopts different priority queues to buffer packets for different types of flows. What’s more, when the switch detects that a data flow promotes the priority of its packets, it utilizes a disorder-free flow scheduling mechanism based on dynamic prioritization to make sure that packets of the same flow arrive at the receiver without reordering. Through a series of experimental tests, we demonstrate that DPOT can decrease the deadline miss rate by up to 95% while reducing flow completion time by up to 45% in comparison to the state-of-the-art flow scheduling approaches.

In order to resist network attacks on IoT devices, identifying IoT devices is the first step for ensuring device security. The traditional passive method identifies IoT devices by mining the potential relationship between traffic characteristics and devices. However, the form of selected traffic features are too singular without considering device behavioral characteristics and the classifier used is too specific with simple structure in these methods. This paper proposes a stacking ensemble learning approach for IoT device identification, ENSIOT, which fully considering the behavioral characteristics of devices and integrating the advantages of various machine learning methods to achieve efficient identification of IoT devices. Firstly, in the process of traffic processing, our method selects features from activity cycles, port numbers, signalling patterns, and cipher suites. Then, in model integration, many machine learning methods are used as base models to learn features selected, and output preliminary recognition results. Finally, the meta model learns the relationship between label and the recognition results of each base model and outputs the final device identification result. This stacking structure stacks the base models and the meta model to make a classifier with strong identification and generalization ability. Incremental learning is used to improve identification accuracy when traffic pattern changing. Comparative experiments are conducted on two datasets of UNSW and TMA-2021. The experimental results verify the effectiveness of ENSIOT, which achieve the accuracy of over 98% on two dataset and bring a noticeable improvement in terms of both accuracy and macro F1 score.

\beginabstract Social network has obtained extensive attention in recommender system. Existing social recommendation models mostly leverage social relations to capture potential interactions between users and items, thereby enhancing recommendation performance. However, these methods ignore the fine-grained bidirectional trust weight and the constraint on the relative positions of entities in social network and user-item interaction network. To this end, in this paper, we propose a social recommendation framework with Trust mining and multi-semantic reGularization (TrustGo). Specifically, we firstly construct a trust network based on the observed social network and establish a high-quality item implicit network. Then, we integrate the trust network, item implicit network, and user-item interaction network into a heterogeneous network. We introduce a meta-path based aggregation in this heterogeneous network to map the users and items into a latent space. And then, by using an ensemble method, we can obtain the final prediction ratings. Considering the users' different behaviors in social network and user-item interaction network, we define two semantic spaces, i.e., the social semantic space and user-item interactional semantic space. And a multi-semantic regularization module is designed to adjust the relative positions of entities in the two kinds of semantic spaces, respectively. Extensive experiments on three real-world datasets demonstrate that our TrustGo model is superior to other state-of-the-art recommendation models. \endabstract

As the visual interpretations for convolutional neural networks (CNNs), backpropagation attribution methods have been garnering growing attention. Nevertheless, majority of these methods merely concentrate on the ultimate convolutional layer, leading to tiny and concentrated interpretations that fail to adequately clarify the model-central attention. Therefore, we propose a precise attribution method (i.e., Holistic-CAM) for high-definition visual interpretation in the holistic stage of CNNs. Specifically, we first present weighted positive gradients to guarantee the sanity of interpretations in shallow layers and leverage multi-scale fusion to improve the resolution across the holistic stage. Then, we further propose a denoising strategy based on the fundamental scale component to eliminate the faithless attribution derived from fusing larger-scale features. The proposed method is capable of simultaneously rendering fine-grained and faithful interpretations for CNNs from shallow to deep layers. Extensive experimental results demonstrate that Holistic-CAM outperforms state-of-the-art methods on common-used benchmarks, including deletion and insertion, energy-based point game as well as Remove and Debias on ImageNet-1k, it also passes the sanity check easily.

Link prediction aims to infer missing valid triplets to complete knowledge graphs, with recent inclusion of multimodal information to enrich entity representations. Existing methods project multimodal information into a unified embedding space or learn modality-specific features separately for later integration. However, performance was limited in such studies due to neglecting the modalities compatibility and conflict semantic carried by entities in valid and invalid triplets. In this paper, we aim at modeling inter-entity modality interactions and thus propose a novel Modality Circular fusion approach (MoCi), which interweaves multimodal contextual of entities. Firstly, unlike most methods in this task that directly fuse modalities, we design a triplets-prompt modality contrastive pre-training to align modality semantics beforehand. Moreover, we propose a modality circular fusion model using a simple yet efficient multilinear transformation strategy. This allows explicit inter-entity modality interactions, distinguishing it from methods confined to fuse within individual entities. To the best of our knowledge, MoCi presents one of the pioneering frameworks that tailored to grasp inter-entity modality semantics for better link prediction. Extensive experiments on seven datasets demonstrate our model yields SOTA performance, confirming the efficacy of MoCi in modeling inter-entity modality interactions. Our code is released at https://github.com/MoCiGitHub/MoCi.

Unmanned aerial vehicles (UAVs) equipped with high definition (HD) cameras, intelligent sensors, computing, and communication modules can be deployed to execute crowdsensing tasks by leveraging federated learning (FL), e.g., air quality perception and ground target detection. FL can reduce transmission stress and protect data privacy when training models, which is suitable for resource constrained Internet of UAVs. Nevertheless, the incentive issues about information asymmetry and bounded rationality impede the applications of FL-enabled Internet of UAVs. The existing FL incentive approaches focus on the risk-free condition, where task publishers are capable of making decisions with complete rationality by utilizing expected utility theory. In fact, task publishers under risk conditions are often bounded rational, whose risk-awareness makes the utility models more sophisticated. To overcome the above problems, we present a prospect theory (PT)-based incentive mechanism for FL-enabled Internet of UAVs. We first leverage PT to model the task publisher’s risk-awareness behavior and construct the subjective utility model. Thereafter, we utilize the framing effect of PT to design the optimal contract to maximize the subjective utility. Simulation results demonstrate that, compared with the baseline method, the proposed incentive mechanism has better performance.

Mobile crowdsourcing (MC) has emerged as an efficient data collection and processing technique with the growing use of mobile devices. Mobile devices typically have numerous sensors to capture a variety of data types, including location information, speech, picture, and video data. Due to the lack of storage capacity and processing power of mobile devices, conducting in-depth analysis and computation of the data is impossible. Cloud-based MC is a viable solution to the issue of limited resources in data outsourcing. How to effectively represent and process encrypted heterogeneous data is an enormous challenge. To alleviate this matter, a unified encrypted-tensor model is proposed to represent heterogeneous data consisting of unstructured, semistructured, and structured data, which represents data in different formats and from various sources. Due to the heterogeneity of data, we devise the encrypted query index and implement the query scheme for structured, semistructured, and unstructured data by transforming heterogeneous data into a graph. We evaluated the search performance of our proposed scheme on real-world data sets. This article analyzes the aspects of time search efficiency, memory occupation, and approximation accuracy. Theoretical analysis and experimental results show that the searchable encryption method based on heterogeneous data proposed in this article can effectively represent and mine big data.

Internet-of-Things (IoT), is the comprehensive interconnection systems of computational, networking and physical devices with the important goal of providing proactive and personalized services efficiently. The foundation of such services is big data integration and processing among various devices, which brings important challenges including data fusion, transferring and sharing of computational results. On the other hand, decentralized blockchain platforms provide novel technologies for reliable IoT data integration and processing. In addition, to facilitate decentralization and distribution of IoT big data, tensor-train (TT), as a tensor decomposition method, can play a vital role. Therefore, in this paper, a tensor-train-based permissioned-private (P2) blockchain is proposed to realize the organization, integration, sharing and applications of IoT data for intelligent IoT services. To demonstrate the performance of the proposed method, case studies with IoT data are carried out on permissioned-private chain platform to measure its performance.

The Internet of Things (IoT) has recently experienced a significant increase in the frequency of cyberattacks, leading to an urgent need for high security and reliability in intelligent IoT applications. Ensuring that interconnected devices within the system operate as expected and provide accurate data has become an essential concern. Reliable coverage can provide a trusted data source for the system. Comprehensively considering various factors such as node multi-state, potential intrusions, and interferences, a trust-based intrusion-tolerant coverage reliability evaluation algorithm (T-ITCR) is proposed to evaluate the coverage reliability based on the trust-based reliable confident information coverage model (T-RCIC). In T-ITCR, trust management is deeply integrated throughout the evaluation process, facilitating dynamic adjustments in node states, network connectivity, and node coverage weights. Malicious nodes are identified and excluded to guarantee the security of data sensing and transmission. Furthermore, to predict node states more accurately, a precise energy assessment mechanism is conducted based on node interaction processes. A significant number of experiments have demonstrated the performance of the proposed algorithm. Consequently, the T-ITCR algorithm demonstrates its ability to efficiently detect malicious intrusions and adjust network states, which significantly strengthens the security and reliability of the networks.

Artificial Intelligence of Things (AIoT) is an emerging paradigm that integrates artificial intelligence (AI) and Internet of Things (IoT) technologies to provide intelligent IoT solutions. The AIoT system acquires data in real time through IoT sensors, performs intelligent data analysis tasks anywhere in the terminal–edge–cloud continuum, and provides accurate decision-making services based on data predictions. Cloud–edge collaboration can reduce security risks for AIoT data prediction by sharing data features instead of raw data. However, sensitive user data may still be inferred by attackers through model parameter analysis, causing irreparable harm and serious consequences. Therefore, data prediction based on cloud–edge collaboration while maintaining privacy constraints remains a significant challenge. In this article, a differentially private federated tensor completion method is proposed for cloud–edge collaborative AIoT data prediction. This method embeds differential privacy (DP) mechanisms with cloud–edge collaboration. Each edge is capable of processing and analyzing data, and collaborative learning with other edges by sharing privacy-preserving model parameters. For model security, objective perturbation is applied to ensure that the tensor completion method satisfies DP. To achieve higher accuracy, parallel tensor decomposition is introduced to avoid the update conflicts problem of federated tensor completion. Through theoretical analysis, our method can provide data protection for tensor completion with high-security promise. The experiments are performed on both synthetic and real-world data sets to demonstrate the superior performance of our method in preserving data privacy.

Intelligent Internet of Things (IoT), is an emerging paradigm that integrates lightweight intelligence algorithms to various IoT devices to provide convenient and intelligent services for modern life and production. For this purpose, data should be efficiently processed to explore the hidden information to elevate the intelligence of services. However, the IoT data are collected from a complex environment with high speed, and high noise, which inevitably brings problems about missing and imparting challenges to the progression of intelligent IoT services. To recover the missing data with higher precision and provide data cornerstones for intelligent IoT systems, a sparse Bayesian tensor completion (SBTC) method is proposed in this article. With the hierarchical sparse prior, the proposed tensor completion model can obtain the underlying low-rank structure from the incomplete tensor, thereby recovering missing data with high accuracy. For model learning, a variational Bayesian inference method is developed in the frequency domain, which improves the model’s efficiency. The model proposed is within a fully Bayesian framework, thereby endowing the model with commendable robustness. The superiority of our model is fully demonstrated by comparing other state-of-the-art methods on synthetic data, traffic data, logistics data, and visual data. In particular, on traffic data and video data, our method has improved by at least 2% and 10dB.

Removing redundant parameters and computations before the model training has attracted a great interest as it can effectively reduce the storage space of the model, speed up the training and inference of the model, and save energy consumption during the running of the model. In addition, the simplification of deep neural network models can enable high-performance network models to be deployed to resource-constrained edge devices, thus promoting the development of the intelligent world. However, current pruning at initialization methods exhibit poor performance at extreme sparsity. In order to improve the performance of the model under extreme sparsity, this paper proposes a dual-grained lightweight strategy-TEDEPR. This is the first time that TEDEPR has used tensor theory in the pruning at initialization method to optimize the structure of a sparse sub-network model and improve its performance. Specifically, first, at the coarse-grained level, we represent the weight matrix or weight tensor of the model as a low-rank tensor decomposition form and use multi-step chain operations to enhance the feature extraction capability of the base module to construct a low-rank compact network model. Second, unimportant weights are pruned at a fine-grained level based on the trainability of the weights in the low-rank model before the training of the model, resulting in the final compressed model. To evaluate the superiority of TEDEPR, we conducted extensive experiments on MNIST, UCF11, CIFAR-10, CIFAR-100, Tiny-ImageNet and ImageNet datasets with LeNet, LSTM, VGGNet, ResNet and Transformer architectures, and compared with state-of-the-art methods. The experimental results show that TEDEPR has higher accuracy, faster training and inference, and less storage space than other pruning at initialization methods under extreme sparsity.

Recurrent neural network (RNN), a branch of deep learning, is a powerful model for sequential data that has outstanding performance on a wide range of important Internet of Things (IoT) tasks. This unprecedented growth of RNN model has however encountered both heterogeneous IoT data and privacy issues. Existing RNN model can not deal with heterogeneous sequential data; often the larger datasets used in training of RNN model contain sensitive information. To tackle these challenges and for the first time, this research proposes a novel differentially private tensor-based RNN (DPTRNN) that can be applied in many challenging deep learning sequence tasks for IoT systems. Specifically, to process heterogeneous sequential data, we propose a tensor-based RNN model. To guarantee privacy, we develop a tensor-based back-propagation through time algorithm with perturbation to avoid exposing the sensitive information for training the tensor-based RNN model within the framework of differential privacy. Thorough security analysis shows that the differential private tensor-based RNN efficiently protects the confidentiality of sensitive user information for IoT. Our results from extensive experiments on two challenging large video datasets suggest that our proposed scheme is practical with guarantee of data privacy preservation and acceptable accuracy loss.

Secure deletion plays a crucial role in safeguarding privacy and maintaining confidentiality. Historically, secure deletion was achieved on magnetic storage devices by data overwriting. However, with the rapid advancements in magnetic storage technology, existing secure deletion strategies are still oblivious to the unique characteristics of these storage devices. As a result, there is currently a lack of research effectively addressing the implementation of secure deletion for the emerging interlaced magnetic recording (IMR) technology. Regrettably, applying traditional read-modify-write (RMW) processes to enable secure deletion on IMR technology leads to significant challenges such as severe write amplification (WA) and performance degradation. In this paper, we propose move-on-cover (MOC), a novel secure deletion strategy for securely deleting on IMR, to optimize the performance of secure deletion. Specifically, when securely deleting a bottom track, the MOC first moves one of affected top track to a free top track, and then covers the to-be-deleted bottom track with another top track, minimizing redundant data backups and hiding secure deletion latency of bottom tracks. A series of evaluation experiments show that MOC is highly effective in reducing extra I/Os and improving the performance of secure deletion.

Smart healthcare has emerged to provide healthcare services using data analysis techniques. Especially, clustering is playing an indispensable role in analyzing healthcare records. However, large multi-modal healthcare data imposes great challenges on clustering. Specifically, it is hard for traditional approaches to obtain desirable results for healthcare data clustering since they are not able to work for multi-modal data. This paper presents a new high-order multi-modal learning approach using multimodal deep learning and the Tucker decomposition (F- HoFCM). Furthermore, we propose an edge-cloud-aided private scheme to facilitate the clustering efficiency for its embedding in edge resources. Specifically, the computationally intensive tasks, such as parameter updating with high-order back propagation algorithm and clustering through high-order fuzzy c-means, are processed in a centralized location with cloud computing. The other tasks such as multi-modal data fusion and Tucker decomposition are performed at the edge resources. Since the feature fusion and Tucker decomposition are nonlinear operations, the cloud cannot obtain the raw data, thus protecting the privacy. Experimental results state that the presented approach produces significantly more accurate results than the existing high-order fuzzy c-means (HOFCM) on multi-modal healthcare datasets and furthermore the clustering efficiency are significantly improved by the developed edge-cloud-aided private healthcare system.

Global news events graphs (GNEG) are designed for the noisy and ungrammatical world’s news media, aiming at capturing the true insight and providing explanations by incorporating potential dimensions and network structures of global news. This article focuses on the temporal representation learning of GNEG to eliminate misunderstanding or ambiguity caused by missing information. Although some temporal models have been developed, the crossover interactions among entity, relation, and time have not been explicitly discussed. The multidirectional effects between entities, relations, and timestamps matter in predicting the establishment of quadruples. This motivates the proposal of learning temporal interaction embeddings (TIE) to benefit GNEG link prediction performance. Specifically, we propose the following. 1) We propose a crossover convolution layer to learn the two-by-two and common interaction features of entity, relation, and time in GNEG to capture their potential effect patterns in the context of different quadruples. 2) For the learned interaction information, we adopt tensor neural network (TNN) to maintain the multiple order structure and further extract effective features to improve prediction. 3) A tensor temporal consistency constraint (TCC) is proposed to enhance the learning of time-weakly sensitive information and induce the embeddings to have a certain compatibility over time. Finally, we carried out extensive experiments on three benchmark datasets, the results proved that the performance of the proposed TIE model is competitive with the state-of-the-art methods.

Smart manufacturing has been transforming toward industrial digitalization integrated with various advanced technologies. Metaverse has been evolving as a next-generation paradigm of a digital space extended and augmented by reality. In the metaverse, users are interconnected for various virtual activities. In consideration of advanced possibilities that may be brought by the metaverse, it is envisioned that industrial metaverse should be integrated into smart manufacturing to upgrade industry for more visible, intelligent and efficient production in the future. Therefore, a conceptual model, named IMverse Model, and novel characteristics of the industrial metaverse for smart manufacturing are proposed in this article. Besides, an industrial metaverse architecture, named IMverse Architecture, is proposed involving several key enabling technologies. Typical innovative applications of the industrial metaverse throughout the whole product life cycle for smart manufacturing are presented with insights. Nonetheless, in prospect of future, the industrial metaverse still faces limitations and is far from implementation. Thus, challenges and open issues of the industrial metaverse for smart manufacturing are discussed, then outlook is provided for further research and application.

In this work, we focus on the Private Intersection-Sum (PIS) with cardinality problem: two parties hold datasets containing user identifiers, and the second party additionally has an integer value associated with each user identifier. Both parties want to learn the number of users they have in common, and the sum of the integer values associated with a user, without revealing anything more. To this end, Google proposed a PIS protocol and released the open-source library Private-Join-and-Compute. And the security of the protocol has been proven proved in the honest-but-curious model. However, this study found a two potential shortcoming shortcomings in the Private-Join-and-Compute library: the user identifier stealing attack against the PIS protocol based on a special input data structure. An improved PIS protocol is proposed based on differential privacy technology, and the Private-Join-and-Compute open-source library is optimized. Through a security proof and formal analysis based on the Tamarin tool, we show that the improved PIS protocol successfully resists the discovered attack without obvious additional overhead.

Deep learning has displayed superior performance in aerial scene (AS) categorization. However, existing methods for AS classification tend to lack adaptability and efficiency, particularly in optimizing its performance on different embedded devices. They also often fail to dynamically adjust to varying scales of feature representations, which can limit their effectiveness across different datasets and devices. To solve these issues, we provide two algorithms. The first algorithm explores local key features by mining the interactivity between channels. The range of cross-channel interactions is dynamically determined through an adaptive strategy. This ensures that convolution operations are optimized. The resulting features are improved by the second proposed algorithm. The second algorithm introduces convolutions, attention, and functions to calculate the weight of features. It enhances feature discriminative power by assigning adaptive weights. Then, we introduce an inference acceleration method for AS categorization. We create efficient codes for the proposed algorithms through automated optimization to match different devices. The inference time of the proposed method is reduced on various devices. Experiments on three frequently used datasets show we attain higher accuracy. The accuracy of some categories reaches 100%. In contrast to similar methods, our accelerated algorithm has at least 43.16%, 53.37%, 10.07%, 31.16%, and 8.08% less inference time on RTX 2,080Ti, Titan V, Jetson TX2, Jetson NX, and Jetson Nano GPUs, respectively.

Public key Encryption with Keyword Search (PEKS) has emerged as a solution for the receiver to securely search the sender’s encrypted data on the cloud. However, the PEKS scheme is threatened by the Keyword Guessing Attack (KGA), which leaks the receiver’s keyword privacy. To resist KGA, researchers have inherited the authentication mechanism into the PEKS system (PAEKS) but also forbid using one trapdoor to search all sender’s encrypted data. In this paper, we explore the KGA problem from grouping senders and propose the notion of Identity-based Group Encryption with Keyword Search (IBGEKS), which leverages Identity-based cryptography to securely search encrypted data. Compared with the PAEKS scheme, the IBGEKS scheme can search the sender’s ciphertexts within the same group established by the receiver via one receiver’s trapdoor. For security, we analyze the KGA problem and propose ciphertexts, identities, and trapdoors indistinguishability for IBGEKS. The evaluation depicts that the IBGEKS has competitive algorithm performance with other SA-PEKS and PAEKS schemes and has superior search performance on the Enron email dataset.

Remote Patient Monitoring (RPM) using Electronic Healthcare (E-health) is a growing phenomenon enabling doctors predict patient health such as possible cardiac arrests from identified abnormal arrythmia. Remote Patient Monitoring enables healthcare staff to notify patients with preventive measures to avoid a medical emergency reducing patient stress. However weak authentication security protocols in IoT wearables such as pacemakers, enable cyberattacks to transmit corrupt data, preventing patients from receiving medical care. In this paper we focus on the security of wearable devices for reliable healthcare services and propose a Lightweight Key Agreement (LKA) based authentication scheme for securing Device-to-Device (D2D) communication. A Network Key Manager on the edge builds keys for each device for device validation. Device authentication requests are verified using certificates, reducing network communication costs. E-health empowered mobile devices are store authentication certificates for future seamless device validation. The LKA scheme is evaluated and compared with existing studies and exhibits reduced operation time for key generation operation costs and lower communication costs incurred during the execution of the device authentication protocol compared with other studies. The LKA scheme further exhibits reduced latency when compared with the three existing schemes due to reduced communication costs.

This paper explores the joint optimization problem for trajectory planning and radio resource allocation in unmanned aerial vehicle (UAV) communications with the aim of maximizing data collection. Rather than decomposing the problem into subproblems, as most current approaches do, we express the quantity of data gathered by a UAV-assisted network as a function of both the size of the resource block allocated to all ground devices and their average upload rate. Based on this formula, it can be concluded that the problem of maximizing the average data collection can be reduced to minimizing the flight trajectory if each device communicates with the UAV within the maximum allowable coverage of the UAV. To address this issue, we propose an advanced hierarchical clustering algorithm that divides larger network-scale scenarios into many disjoint subregions to determine the initial hovering positions of the UAV. The non-convex minimization trajectory problem is decomposed into a series of convex optimizations to minimize path segments along the trajectory, based on the traveling salesman problem (TSP). Subsequently, the communication optimization process is modified to assign specific upload times for each device. The effectiveness of the optimization algorithm is demonstrated through extensive simulations, which show its superior performance in terms of average rates of data collection and upload failures.

Recurrent neural networks (RNNs) and their variants can efficiently capture the features of time-series characteristic data and are widely used for intelligent transportation tasks. Internet of Vehicles (IoV) edge devices deploying RNN models are an important impetus for the development of intelligent transportation system (ITS) and provide convenient services for users and managers. However, the input data of some transportation tasks have high dimensional characteristics, resulting in the number of training parameters and computational complexity of RNN models being too large, making it difficult to deploy high-performance RNN models on resource-constrained IoV edge devices. To overcome this problem, we compress the training parameters of the RNN model using the proposed multi-tree compact hierarchical tensor representation-Dtensor Block Decomposition (DBD), which reduces the computational complexity of the model and speeds up the training process of the model, thus making the network model lightweight. We evaluate the performance of Dtensor Block-Long Short-Term Memory (DB-LSTM) and Improved Dtensor Block-LSTM (IDB-LSTM) models on multiple real datasets and compare them with the current state-of-the-art LSTM compression models. Experimental results demonstrate that our proposed method can massively compress the number of training parameters of the models on different datasets and shorten the training time of the models without degrading the testing accuracy of the models. In addition, our proposed DB-LSTM and IDB-LSTM models have better comprehensive performance compared with other models and are more suitable for deployment on resource-constrained IoV edge devices.

Transportation big data generated from various Internet of Things devices have the feature of muti-source and heterogeneous. To efficiently represent and analyze these ubiquitous transportation big data, tensor and tensor-based data analysis methods have been widely adopted in recent years. As a tensor-based machine learning method, high-order dominant Z-eigen decomposition (HODZED) in multivariate multi-order Markov model is suitable for multi-modal transportation prediction. However, massive transportation data are usually generated in a streaming way and the transportation system requires frequent updates. To avoid recalculating the history data and provide immediate prediction, we propose a tensor train (TT) based incremental HODZED (TT-IHODZED) method. Concretely, we first present an incremental HODZED (IHODZED) method to update the dominant Z-eigentensor in multivariate multi-order Markov model. Then, TT-based tensor operations are adopted to IHODZED to speed up calculations, especially the repeated Einstein products. Furthermore, to solve the TT-based high-order linear equations in TT-IHODZED method, we also propose a TT-based biconjugate gradient stabilized (TT-HOBiCGS) algorithm. Experimental results based on real-world and synthetic datasets show that, compared to HODZED method, TT-IHODZED significantly improves computation efficiency up to 10 times while keeping the same or even better prediction accuracy.

Traffic and the movement of people are inextricably associated with the potential spread of COVID-19. In Intelligent Transportation System (ITS), Deep Learning (DL) traffic detection approaches driven by transportation big data have significant application values in monitoring, counting and classifying traffic vehicle information during the COVID-19 epidemic blockade, while DL COVID-19 medical diagnostic technology is also very important. However, due to concerns about data privacy and security, traditional data-centralized DL techniques that require uploading training data from multiple cameras or hospitals are no longer suitable. Federated Learning (FL) as a novel collaborative privacy-preserving DL paradigm could address this issue well. Nevertheless, in FL, most existing works train learning models with full-precision weights and communicate them over multiple iterations, which may incur massive additional communication costs and disclose the privacy implied in the trained local models. To tackle these issues, we first propose a novel multi-modal tensor ring decomposition TR-TSVD that not only achieves efficient data reduction but also keeps the correlations among multi-modes. Afterward, applying TR-TSVD to the training process of a convolutional neural network under the FL framework to achieve the goal of reducing communication overhead while ensuring model performance. Additionally, since the weight parameters are transmitted with the TR-TSVD format, attackers cannot infer the data privacy without knowing the specific restoration method. Besides, the additively homomorphic encryption is leveraged to further preserve model security. Extensive experimental results on MNIST, BIT-Vehicle and COVID-CT datasets show that the proposed approach could achieve a better performance.

With the development of recommendation algorithms, researchers are paying increasing attention to fairness issues such as user discrimination in recommendations. To address these issues, existing works often filter users’ sensitive information that may cause discrimination during the process of learning user representations. However, these approaches overlook the latent relationship between items’ content attributes and users’ sensitive information. In this article, we propose DALFRec, a fairness-aware recommendation algorithm based on user-side and item-side adversarial learning to mitigate the effects of sensitive information on both sides of the recommendation process. First, we conduct a statistical analysis to demonstrate the latent relationship between items’ information and users’ sensitive attributes. Then, we design a dual-side adversarial learning network that simultaneously filters out users’ sensitive information on the user and item side. Additionally, we propose a new evaluation strategy that leverages the latent relationship between items’ content attributes and users’ sensitive attributes to better assess the algorithm’s ability to reduce discrimination. Our experiments on three real datasets demonstrate the superiority of our proposed algorithm over state-of-the-art methods.

Desirable information processing in space-terrestrial integrated vehicle networks (STINs) handles data distributed in different satellites while transmitting, where efficient modeling time-varying resources is critical. Existing works are not applicable to STINs, however, because they lack the joint consideration of different movement patterns and fluctuating loads. In this paper, we propose theTime-Varying Resource Graph (TVRG)to model dynamic resources in STINs, by leveraging the advantages of software-defined networking in flexible resource management. Firstly, we propose theSTIN mobility modelto uniformly model different movement patterns in STINs. Then, we propose alayered Resource Modeling and Abstraction (RMA)approach, where evolutions of node resources are modeled as Markov processes, by encoding predictable topologies and influences of fluctuating loads as states. Besides, we propose the low-complexity domain resource abstraction algorithm by defining two mobility-based and load-aware partial orders on resource abilities. Finally, we formulate theTVRG-based Processing on the Way (TPoW)problem for data flows with processing requirements and multiple sources. We propose aMulti-level Processing on the Way (MPoW)approach with a bounded approximation ratio, realizing adaptive matching of resources and demands of processing and transmission. To evaluate the RMA approach, we propose aTVRG-based Routing (TR)algorithm for time-sensitive and bandwidth-intensive data flows, with the multi-level on-demand scheduling ability. Comprehensive simulation results demonstrate that our RMA-TR and MPoW outperform most related schemes by decreasing nearly 40% bandwidth consumption with the shortest end-to-end delay.

The widespread applications of the Hybrid Internet of Things (HIoT) have put forward higher requirements for network reliability. Coverage reliability is one of the important metrics of reliability, and reliable coverage ensures network data perception and transmission to improve the Quality of Service (QoS). In this article, we define Confident Information Coverage Reliability (CICR) based on the Confident Information Coverage Model (CIC), which comprehensively considers sensor multistate, sensor energy, coverage rate, and connectivity robustness to evaluate coverage reliability. Furthermore, a Tensor-based Confident Information Coverage Reliability Algorithm (T-CICR) is proposed based on tensor modeling to evaluateCICR. The algorithm uses a tensor-based Markov model to predict sensor multistate. Three tensors of coverage rate, sensor multistate, and sensor energy are constructed to provide unified representations. Simulation results show that our proposed algorithm can significantly improve coverage reliability in terms of duty cycle, coverage rate requirement, sensing range, Root Mean Square Error (RMSE) threshold, connectivity robustness requirement, and link reliability.

Graph neural networks (GNNs) have shown great ability in modeling graphs; however, their performance would significantly degrade when there are noisy edges connecting nodes from different classes. To alleviate negative effect of noisy edges on neighborhood aggregation, some recent GNNs propose to predict the label agreement between node pairs within a single network. However, predicting the label agreement of edges across different networks has not been investigated yet. Our work makes the pioneering attempt to study a novel problem of cross-network homophilous and heterophilous edge classification (CNHHEC) and proposes a novel domain-adaptive graph attention-supervised network (DGASN) to effectively tackle the CNHHEC problem. First, DGASN adopts multihead graph attention network (GAT) as the GNN encoder, which jointly trains node embeddings and edge embeddings via the node classification and edge classification losses. As a result, label-discriminative embeddings can be obtained to distinguish homophilous edges from heterophilous edges. In addition, DGASN applies direct supervision on graph attention learning based on the observed edge labels from the source network, thus lowering the negative effects of heterophilous edges while enlarging the positive effects of homophilous edges during neighborhood aggregation. To facilitate knowledge transfer across networks, DGASN employs adversarial domain adaptation to mitigate domain divergence. Extensive experiments on real-world benchmark datasets demonstrate that the proposed DGASN achieves the state-of-the-art performance in CNHHEC.

The proliferation of Internet-of-Things (IoT) technologies in modern smart society enables massive data exchange for offering intelligent services. It becomes essential to ensure secure communications while exchanging highly sensitive IoT data efficiently, which leads to high demands for lightweight models or algorithms with limited computation capability provided by individual IoT devices. In this study, a graph representation learning model, which seamlessly incorporates graph neural network (GNN) and knowledge distillation (KD) techniques, named reconstructed graph with global-local distillation (RG-GLD), is designed to realize the lightweight anomaly detection across IoT communication networks. In particular, a new graph network reconstruction strategy, which treats data communications as nodes in a directed graph while edges are then connected according to two specifically defined rules, is devised and applied to facilitate the graph representation learning in secure and efficient IoT communications. Both the structural and traffic features are then extracted from the graph data and flow data respectively, based on the graph attention network (GAT) and multilayer perceptron (MLP) techniques. These can benefit the GNN-based KD process in accordance with the more effective feature fusion and representation, considering both structural and data levels across the dynamic IoT networks. Furthermore, a lightweight local subgraph preservation mechanism improved by the graph attention mechanism and downsampling scheme to better utilize the topological information, and a so-called global information alignment defined based on the self-attention mechanism to effectively preserve the global information, are developed and incorporated in a refined graph attention based KD scheme. Compared with four different baseline methods, experiments and evaluations conducted based on two public datasets demonstrate the usefulness and effectiveness of our proposed model in improving the efficiency of knowledge transfer with higher classification accuracy but lower computational load, which can be deployed for lightweight anomaly detection in sustainable IoT computing environments.

The expansion of data centers, driven by the continuous development of network services, has led to a significant issue of high energy consumption. Due to the real-time interaction between IT and non-IT equipments, it is difficult to consider the holistic energy consumption of heterogeneous data centers. Therefore, this paper proposes a holistic-energy-aware-virtual machine placement (VMP) strategy for data centers that use heterogeneous resources to provide services. Firstly, we propose the energy-aware VMP strategy by using the probabilistically determining mechanism to effectively minimize the number of activated servers and improve server resource utilization. Secondly, within this strategy, we leverage dynamic voltage and frequency scaling (DVFS) technology, enabling nodes to operate at lower frequencies and voltages while meeting performance requirements, thus further reducing computing energy consumption. Thirdly, in addition to the previous two points, the probabilistic determined genetic algorithm (PDGA) is proposed to reasonably distribute the workloads based on the heat-recirculation effect and reduces the cooling energy consumption. The above mechanisms collectively optimize the global energy consumption of heterogeneous data centers. Experimental results demonstrate that the PDGA can significantly reduce the energy consumption of IT and non-IT equipment. The total energy consumption of the data center is significantly reduced (the PDGA is 20.83% lower than the simulated annealing based algorithm and 20.76% lower than the big data task scheduling algorithm based on thermal-aware and DVFS-enabled techniques).

Multimedia cognitive computing as a revolutionary emerging concept of artificial intelligence emulating the reasoning process like human brains can facilitate the evolution of intelligent transportation systems (ITS) to be smarter, safer, and more efficient. Massive multimedia traffic big data is an important prerequisite for the success of cognitive computing in ITS. However, traditional data-centralized artificial intelligence approaches often face the problems of data islands and data famine due to concerns about data privacy and security. To this end, we propose the concept of cognitive federated learning leveraging federated learning as the learning paradigm for cognitive computing, which solves the preceding concerns by sharing updated models rather than raw data. Nevertheless, the exchange of numerous model parameters not only generates significant communication overhead but also suffers from the risk of privacy leakage due to inference attacks. This article aims to design a novel lightweight and privacy-enhanced cognitive federated learning architecture to facilitate the development of ITS. First, a privacy-enhanced model protection scheme with homomorphic encryption as the underlying technology is proposed to simultaneously defend against the inference attacks launched by external malicious attackers, honest-but-curious cognitive platforms, and internal participants. Furthermore, a novel tensor ring-block decomposition and its corresponding deep computation model converting the weight tensor into a set of matrices and third-order core tensors are proposed, which could reduce the communication overhead and storage requirements without compromising model performance. Experimental results on real-world datasets show that the proposed approach performs well.

This work aims at addressing carbon neutrality challenges through resource management with system software control. Reducing energy costs is vital for modern systems, especially those battery-powered devices that need to perform complex tasks. The technique of dynamic voltage or frequency scaling (DVFS) has been commonly adopted for reducing power consumption in cyber-physical systems to support the increasing computation demand under limited battery life. Dynamic slack becomes available when a task finishes earlier than its worst execution time. Dynamic slack management is an important factor for the DVFS mechanism. This paper proposes a dynamic slack-sharing (DSS) DVFS scheduling method that reduces CPU energy consumption by learning the slack-sharing rate. The DSS method automatically changes the slack sharing rate of a task on the fly in different situations through learning from experience to determine how much slack to use for the next task and how much to share. The method used for learning is Q-learning. Extensive experiments have been performed, and the results show that the DSS technique achieves more energy savings than the existing ones.

Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to various graph datasets. In addition, the contrastive losses originally developed in computer vision have been directly applied to graph data, where the neighboring nodes are regarded as negatives and consequently pushed far apart from the anchor. However, this is contradictory with the homophily assumption of net-works that connected nodes often belong to the same class and should be close to each other. In this work, we propose an end-to-end automatic GCL method, named NCLA to apply neighbor contrastive learning on learnable graph augmentation. Several graph augmented views with adaptive topology are automatically learned by the multi-head graph attention mechanism, which can be compatible with various graph datasets without prior domain knowledge. In addition, a neighbor contrastive loss is devised to allow multiple positives per anchor by taking network topology as the supervised signals. Both augmentations and embeddings are learned end-to-end in the proposed NCLA. Extensive experiments on the benchmark datasets demonstrate that NCLA yields the state-of-the-art node classification performance on self-supervised GCL and even exceeds the supervised ones, when the labels are extremely limited. Our code is released at https://github.com/shenxiaocam/NCLA.

High bit-density NAND flash memory, such as quadruple-level cell (QLC) flash, has been widely adopted in emerging storage systems. As voltage-based write-once-memory (WOM-v) codes reduce the erase count of a flash block before storing new data, WOM-v codes are proven feasible to extend the lifetime of high-density flash memory significantly. To ensure data security, secure deletion is widely employed in flash-based storage system.In this paper, we propose FSD, a fast secure deletion strategy for high-density flash memory that cooperates secure deletion with WOM-v codes. FSD classifies request data into secure, and unsecure data by considering data privacy. When secure data deletion command issues to the storage device, FSD cooperates unsecure data program operation to cover secure data. The results show that FSD improves the I/O performance of storage system by 70.37% over the state-of-the-art.

Discrimination against different user groups has received growing attention in the recommendation field. To address this problem, existing works typically remove sensitive attributes that may cause discrimination through adversary learning to achieve fair recommendations. However, these approaches leverage all available interactions for learning user representations and overlook the fact that different interactions have varying relevance to users’ sensitive attributes. Ignoring this issue may weaken the effectiveness of adversary learning in removing sensitive attributes. To tackle this challenge, we propose a novel model called GS-FairRec, which distinguishes between user interactions to achieve better removal of sensitive attributes. The model consists of three modules: graph sampling-based representation learning, pseudo-user representation learning, and adversarial learning. Firstly, the graph sampling-based representation learning module removes some irrelevant neighbors from a user-item bipartite graph and employs a graph convolutional network (GCN) to learn user/item representations. Next, items that are relevant to a user’s sensitive information but do not match their preferences are defined as the user’s pseudo-interest items, which are leveraged to learn the pseudo-user representation. In the adversarial learning module, the user’s two kinds of representations are fused for adversarial learning to remove sensitive information. Additionally, we design a new metric to measure the model’s ability to remove sensitive attributes based on how a generated recommendation list discloses the user’s sensitive attributes. Finally, we conduct experiments on two real-world datasets, and our results demonstrate the superiority of our proposed model in fairness tasks.

Large-scale pre-trained language models have garnered significant attention in recent years due to their effectiveness in extracting sentence representations. However, most pre-trained models currently use transformer-based encoder with a single modality and are primarily designed for specific tasks such as natural language inference and question-answering. Unfortunately, this approach neglects the complementary information provided by multimodal data, which can enhance the effectiveness of sentence representation. To address this issue, we propose a Visually-supervised Pre-trained Multimodal Model (ViP) for sentence representation. Our model leverages diverse label-free multimodal proxy tasks to embed visual information into language, facilitating effective modality alignment and complementarity exploration. Additionally, our model utilizes a novel approach to distinguish highly similar negative and positive samples. We conduct comprehensive downstream experiments on natural language understanding and sentiment classification, demonstrating that ViP outperforms both existing unimodal and multimodal pre-trained models. Our contributions include a novel approach to multimodal pre-training and a state-of-the-art model for sentence representation that incorporates visual information.1 Our code is available at https://github.com/gentlefress/ViP

Recent research about camouflaged object detection (COD) aims to segment highly concealed objects hidden in complex surroundings. The tiny, fuzzy camouflaged objects result in visually indistinguishable properties. However, current single-view COD detectors are sensitive to background distractors. Therefore, blurred boundaries and variable shapes of the camouflaged objects are challenging to be fully captured with a singleview detector. To overcome these obstacles, we propose a behavior-inspired framework, called Multi-view Feature Fusion Network (MFFN), which mimics the human behaviors of finding indistinct objects in images, i.e., observing from multiple angles, distances, perspectives. Specifically, the key idea behind it is to generate multiple ways of observation (multi-view) by data augmentation and apply them as inputs. MFFN captures critical boundary and semantic information by comparing and fusing extracted multi-view features. In addition, our MFFN exploits the dependence and interaction between views and channels. Specifically, our methods leverage the complementary information between different views through a two-stage attention module called Co-attention of Multi-view (CAMV). And we design a local-overall module called Channel Fusion Unit (CFU) to explore the channel-wise contextual clues of diverse feature maps in an iterative manner. The experiment results show that our method performs favorably against existing state-of-the-art methods via training with the same data. The code will be available at https://github.com/dwardzheng/MFFN_COD.

With the advent of the Internet of Things (IoT) era, the multiunmanned aerial vehicle (UAV) networks have attracted great attention in the fields of source detection and localization. However, as the real-time signal processing performance of the UAV is limited by the computing speed and accuracy of the embedded hardware, the effectiveness of source localization is greatly reduced. Aiming at improving the accuracy and computational efficiency of source localization, a Cramer–Rao bound (CRB) weighted multi-UAV network source localization method is proposed based on the deep neural networks (DNNs) and spatial-spectrum fitting (SSF). The proposed source localization system is composed of UAVs equipped with a radar array. The source location can be achieved using the direction of arrival (DOA) of the source signals of UAVs, but the accuracy and real-time performance of the conventional DOA estimation algorithms are not satisfactory, and the data fusion strategy of the conventional cross-location framework needs further improvement. In the proposed method, a DNN-based SSF, denoted as the deep SSF (DeepSSF), is designed to achieve accurate DOA estimation. In the DeepSSF, the DOA estimation performance is guaranteed by the DNN’s strong nonlinear fitting ability and highly parallel structure. In addition, based on the obtained DOA information, the source is located once by every two UAVs. Finally, the source localization is realized based on the weighted CRB according to the principle that the more the DOA distribution deviates from zero, the lower the estimation accuracy. The simulation results verify the efficiency of the proposed method.

Live traffic video is vitally important for vehicles in future intelligent transport systems (ITSs). Due to the limitation of onboard sensors, vehicles may not be able to obtain a full view of the traffic situations which endangers safety for autonomous driving vehicles. In this article, we propose a traffic video multicasting scheme by using video splitting and group splitting techniques for unmanned aerial vehicles (UAVs)-assisted ITS, in which UAVs are considered as the eyes in the sky to capture real-time traffic videos. We aim to maximize the long-term video quality received by vehicles by jointly optimizing vehicle grouping and spectrum allocation. Considering the interactions among UAVs, the above optimization problem is formulated as a multiagent coordination problem in the form of a Markov game (MG). The MG is subsequently solved by leveraging a state-of-the-art multiagent deep reinforcement learning (MADRL) algorithm, namely, multiactor attention critic (MAAC), in which an attention mechanism is utilized to pay attention to other agents to make the learning process more effective and scalable. Extensive simulation results show that the MAAC-based algorithm has better performance in terms of video quality and spectrum efficiency compared with the baseline methods.

Internet of Things (IoT) devices and services have become increasingly ubiquitous in recent years as they greatly facilitate our daily life. To promote IoT data and semantic interoperability, we propose an edge–cloud framework. The edge end is responsible for handling customized data processing tasks and transferring the processed data, while the cloud end deals with semantic information processing. Additionally, we present an entity tree embedding algorithm at the cloud end to convert IoT entities and attributes into embedding vectors in a tree-structured way. Consequently, entity embeddings could reflect the semantic information at both Class and Property levels, which ameliorates our previous entity embedding method, leading to better embedding results and clustering effects. Finally, the entity tree embedding algorithm and the corresponding compression algorithm are evaluated. Results indicate that the Whitening algorithm is the best method to compress embedding vectors. More importantly, the entity tree embedding algorithm captures both the semantic and structural information of entities and attributes. Additionally, the clustering experiments show that the proposed embedding algorithm achieves better clustering results compared with the original entity embeddings and the uncompressed averaging method.

Federated learning (FL) could provide a promising privacy-preserving intelligent learning paradigm for space–air–ground-integrated Internet of Things (SAGI-IoT) by breaking down data islands and solving the dilemma between data privacy and data sharing. Currently, adaptivity, communication efficiency and model security are the three main challenges faced by FL, and they are rarely considered by existing works simultaneously. Concretely, most existing FL works assume that local models share the same architecture with the global model, which is less adaptive and cannot meet the heterogeneous requirements of SAGI-IoT. Exchanging numerous model parameters not only generates massive communication overhead but also poses the risk of privacy leakage. The security of FL based on homomorphic encryption with a single private key is weak as well. Given this, this article proposes a tensor-empowered communication-efficient and trustworthy heterogeneous FL, where various participants could choose suitable heterogeneous local models according to their actual computing and communication environment, so that clients with different capabilities could do what they are good at. Additionally, tensor train decomposition is leveraged to reduce communication parameters while maintaining model performance. The storage requirements and communication overhead for heterogeneous clients are reduced further. Finally, the homomorphic encryption with double trapdoor property is utilized to provide a robust and trustworthy environment, which can defend against the inference attacks from malicious external attackers,honest-but-curiousserver and internal participating clients. Extensive experimental results show that the proposed approach is more adaptive and can improve communication efficiency as well as protect model security compared with the state-of-the-art.

The high-speed mobile networks offer great potentials to many future intelligent applications, such as autonomous vehicles in smart transportation systems. Such networks provide the possibility to interconnect mobile devices to achieve fast knowledge sharing for efficient collaborative learning and operations, especially with the help of distributed machine learning, e.g., Federated Learning (FL), and modern digital technologies, e.g., Digital Twin (DT) systems. Typically, FL requires a fixed group of participants that have Independent and Identically Distributed (IID) data for accurate and stable model training, which is highly unlikely in real-world mobile network scenarios. In this paper, in order to facilitate the lightweight model training and real-time processing in high-speed mobile networks, we design and introduce an end-edge-cloud structured three-layer Federated Reinforcement Learning (FRL) framework, incorporated with an edge-cloud structured DT system. A dual-Reinforcement Learning (dual-RL) scheme is devised to support optimizations of client node selection and global aggregation frequency during FL via a cooperative decision-making strategy, which is assisted by a two-layer DT system deployed in the edge-cloud for real-time monitoring of mobile devices and environment changes. A model pruning and federated bidirectional distillation (Bi-distillation) mechanism is then developed locally for the lightweight model training, while a model splitting scheme with a lightweight data augmentation mechanism is developed globally to separately optimize the aggregation weights based on a splitted neural network structure (i.e., the encoder and classifier) in a more targeted manner, which can work together to effectively reduce the overall communication cost and improve the non-IID problem. Experiment and evaluation results compared with three baseline methods using two different real-world datasets demonstrate the usefulness and outstanding performance of our proposed FRL model in communication-efficient model training and non-IID issue alleviation for high-speed mobile network scenarios.

With the bit density improvement and the 3-D flash techniques, modern NAND flash-memory-based solid-state disks (SSDs) dramatically increase the flash storage capacity. However, in high-density SSDs, the long read latency overheads due to massive read-retry steps have become a serious performance concern to develop flash memory in storage devices. In this article, we proposed a parallel read-retry scheme (PaRR) to utilize the read-retry characteristics among flash memory cells. Specifically, when reading the multiple data pages simultaneously, PaRR reduces the read-response time by parallelizing read-retry operations. PaRR reduces the number of read-retry operations by parallelizing read-retry steps with the different aggressive read reference voltages if simultaneously reading the data pages that exhibit virtually equivalent reliability characteristic. Our evaluation shows that PaRR improves the I/O performance by 33.77% on average compared with the state-of-the-art scheme.

As an important part of cyber–physical–social intelligence, artificial intelligence (AI)-driven smart healthcare is committed to promoting the application of human–machine hybrid augmented intelligence in the medical field, including AI-assisted medical image analysis and lesion recognition. Among them, deep learning models represented by fully convolutional networks (FCNs) have achieved excellent performance in medical image segmentation. However, limited by the complex structure of segmentation networks and the inherently redundant characteristics of convolutional operation, the scale of these models is extremely large. To further promote the application of machine intelligence in the field of medical image analysis, we propose an attention U-Net based on Bi-ConvLSTM (AUBC-Net) for accurate segmentation of medical images in this article. Different from classical U-Net, the proposed model deals with the potential association between decoding features and encoding features by bidirectional convolution LSTM. Furthermore, for the inherent redundancy characteristics of FCNs, we propose a lightweight feature generation strategy and optimize the calculation process of Bi-ConvLSTM based on tensor multilinear algebra, which can greatly reduce the number of network parameters. In addition, we have conducted the image segmentation experiments on two benchmark medical datasets, and the experimental results demonstrate that the proposed model can not only achieve better performance than existing methods, but also effectively compress network parameters while ensuring performance, which greatly facilitates AI-driven smart medical applications.

The development and applications of artificial intelligence (AI) have brought unprecedented opportunities to humans, but also brought many challenges and concerns such as unfairness, immorality, distrust, illegality, and discrimination. Responsible AI provides a new solution to effectively address these AI potential threats by integrating social/physical rules into AI systems. However, these rules are high-level regulations and ethical principles, which are difficult to be formalized. To this end, we attempt to use the data generated in various AI systems such as cyber–physical–social systems (CPSS) to discover and reflect these rules to provide more responsible services for humans. In this article, we first propose a data-driven responsible CPSS framework. Its core idea is to mine valuable rules through perception, fusion, processing, and analysis of CPSS data, and then use these rules to adaptively optimize CPSS. Based on this framework, three tensor-based couple hidden Markov models (T-CHMMs) are constructed to integrate three responsible features (i.e., timing, periodicity, and correlation) for mining potential and valuable rules. Then, the corresponding tensor-based Baum–Welch (TBW) algorithms are designed to solve their learning problems. Finally, the predictive accuracy and computational efficiency of the proposed models and algorithms are verified on three open datasets. The experimental results show that proposed methods have the best performances for various scenarios, which reflects that our methods are more promising and responsible than existing methods.

It has become a trend for clients to outsource their encrypted databases to remote servers and then leverage the Searchable Encryption technique to perform secure data retrieval. However, the method has yet to be considered a crucial need for replication on searchable encrypted data. It calls for challenging works on Dynamic Searchable Symmetric Encryption (DSSE) since clients must share the search capability of the encrypted data replicas and guarantee forward and backward privacy. We define a new notion called “Keyword Search Shareable Encryption” (KS2E) and the corresponding security model capturing forward and backward privacy. In our notion, data owners are allowed to share search indexes of the encrypted data with users. A search index will be updated with a new search key before sharing to guarantee the data privacy of the source database. The target database also inherits data search efficiency along with the shared data. We further construct an instance of KS2E calledBranch, prove its security, and use real-world datasets to evaluate Branch. The evaluation results show that Branch’s performance is comparable to classical DSSE schemes on search efficiency and demonstrate the effectiveness on searching encrypted data replicas from multiple owners.

With the deepening of industry 4.0 paradigm in logistics systems, artificial intelligent has been widely used to improve the quality of logistics services. Considering that data collected in comprehensive logistics service system usually integrate multistage complex information such as traffic flow records and spatiotemporal trajectory, it is inevitable that the data are incomplete and partially missing due to equipment failures, communication interruptions, etc. As an effective spatiotemporal completion tool in logistics systems, low-rank tensor completion has aroused extensive research interest thanks to its excellent performance on data recovery. Although existing tensor completion methods effectively capture the complex associations/dependencies of multidimensional inputs, they fail to exploit the potential characteristics of spatiotemporal data, such as the periodicity. In this article, we propose a jointly low-rank tensor completion method for logistics data completion, which constructs multiple periodic subtensors by setting an appropriate time window, then performs jointly low-rank completion and imputation. In addition, we also provide an optimization algorithm based on Alternating Direction Method of Multiplier framework for the proposed problem. Experimental results on four logistics-related datasets have further demonstrated the promising performance of the proposed method compared with other state-of-the-art competitors. We believe that the proposed approach not only effectively maintains the advantages of classical completion methods, but also fully excavates the multidimensional correlation and hidden patterns behind records, and further provides a novel and effective strategy for data completion and imputation in logistics systems.

Combining data-driven approaches and physical laws for industrial trajectory prediction can improve the performance of industrial applications such as path planning of robots and route selection of vehicles in transportation systems. In the era of industrial Big Data, the application of industrial trajectory prediction based on the physical Markov process and tensor model has attracted much attention. To synchronously improve the prediction accuracy and computational efficiency, this article proposes a tensor-train (TT)-based multiuser multivariate multiorder (3M) physical Markov prediction approach for multimodal industrial trajectory pattern mining. First, we propose a TT-based unified product calculation rule with its scalable computation approach based on decomposed TT cores to speed up the execution efficiency. Then, a TT-based 3M (TT-3M) Markov transition approach is presented. Furthermore, we put forward a TT-based power method to calculate the stationary joint eigentensor (SJE) and an SJE-based multimodal prediction algorithm to mine concealed trajectory patterns. Experimental results based on real GPS trajectory dataset show that compared with the original tensor-based 3M approach, the TT-3M approach can improve the computational efficiency up to three times and reduce the storage space proportion to a minimum of 1‰ while ensuring basically consistent prediction accuracy.

Recent research shows that executable and linkable format (ELF) malware detection models based on deep learning are vulnerable to adversarial attacks. The most commonly used method in previous work is adversarial training to defend adversarial examples. Nevertheless, it is inefficient and only effective for specific adversarial attacks. Given that the perturbation byte insertion positions of existing adversarial malware generation methods are relatively fixed, we propose a new method to detect adversarial ELF malware. Using model interpretation techniques, we analyze the decision-making basis of the malware detection model and extract the features of adversarial examples. We further use anomaly detection techniques to identify adversarial examples. As an add-on module of the malware detection model, the proposed method does not require modifying the original model and does not need to retrain the model. Evaluating results show that the method can effectively defend the adversarial attacks against the malware detection model.

Augmented Intelligence of Things empowered by knowledge graph drives cognitive intelligence for smart enterprise management systems (EMS). Knowledge fusion technology can effectively integrate knowledge from different sources, thereby improving the accuracy and richness of the knowledge graph, which is of great significance to the sustainable development of smart EMS. Traditional machine learning methods on graphs face challenges in the fusion of complex and multirelational enterprise knowledge graphs due to inherent defects in relation semantic and local structure information capturing. In order to break through these limitations and improve EMS knowledge graphs, we propose tensor-based graph attention networks for multirelational graph representation learning (MR-GAT), and apply it to the critical tasks in knowledge fusion: Entity and relation alignment. Specifically, we innovatively adopt tensor operations to adequately model the interactions between entities and relations in EMS knowledge graph to learn more accurate representations. Additionally, we propose a relation attention mechanism, which focuses on assigning weights in the process of aggregating local semantic information for relation learning in an EMS knowledge graph. Furthermore, we develop a joint entity and relation alignment framework by utilizing the proposed multirelational graph attention networks to improve the accuracy of knowledge fusion. Experimental evaluations on three datasets present that the proposed approach outperforms the baseline models by about 1.4% on average in terms of the mean reciprocal rank metric, which demonstrates the superior ability of the proposed MR-GAT in representation learning for knowledge fusion in smart EMS.

Intelligent connected vehicle is rapidly growing with the 5-G technology; the diversity of functional interfaces has significantly expanded the avenues of attack, making automotive controller area network (CAN) more vulnerable to cyberthreats. Automotive CAN network attacks are a direct threat to traffic safety, and in this study, we explore the use of intrusion detection techniques for mitigating cyberattacks. However, most automotive CAN network intrusion detection technologies are not capable of defending against sophisticated attacks, making it extremely challenging for detecting intrusions in practice. In this article, we propose a novel time interval conditional entropy method for detecting intrusions in automotive CAN networks. The time interval conditional entropy intrusion detection method is not susceptible to interference and is capable of detecting a variety of attacks. In our experiments, the conditional entropy values of regular communication messages are collected and utilized to distinguish and detect the attacks. The time interval conditional entropy detection method is implemented and evaluated in our controller area net-work bus (CAN-BUS) network platform. The experiments show that our method has higher detection accuracy and is easier to deploy compared to existing automotive CAN network intrusion detection methods.

There are three key roles in Intelligent Transportation Systems (ITS): driver, vehicle and road. However, existing static interactions among Driver-Vehicle-Road (DVR) are too passive to reflect the change of driver preferences, vehicle conditions, road conditions, etc. Therefore, we provide a data-driven Cloud-Fog-Edge Collaborative Driver-Vehicle-Road (CFEC-DVR) framework. The framework could self-adaptively evolves through continuous iteration to provide better ITS services for humans. The collaboration among DVR creates a lot of relation data that construct our relation graphs. Cloud brings some privacy risks. Relation graphs have great analytic value. As DVR collaboration, privacy quality and analytic accuracy are three key issues in the framework, we propose a Relation Graph Privacy-Preserving scheme with High Accuracy in our framework, which is named as RGPP-HA. Based on machine learning, our method nearly maximizes the difficulty for attackers to know exactly how many other roles are connected to the attacked role, which enhances the privacy quality. Meanwhile, we find as much valuable information as possible from roles’ encrypted relations for more accurately analytic performance. Based on the experiments, we compare the proposed scheme RGPP-HA with existing classic and relevant schemes. The experimental results show that our scheme has the best privacy quality and analytic accuracy. This further verifies the feasibility of CFEC-DVR framework.

With the deep integration of the Internet of Things (IoT) technology and the increase of computational power and memory, vehicles can also serve as the infrastructures for Intelligent Transportation System (ITS), e.g., as fog nodes. However, when connecting vehicles to the internet, alongside with the benefits it brings, it also opens many new challenges such as security attacks. Controller Area Network (CAN) is one of the main in-vehicle communication protocols in modern cars. Its lack of sender verification mechanism makes CAN particularly vulnerable to cyber-attacks including masquerade attack. Fingerprinting Electronic Control Units (ECUs) based on hardware characteristics has been proved feasible and effective on defending CAN buses. However, most state-of-the-art works exploited the supervised learning algorithm to identify the transmitter based on the signal characteristics. This makes the decision process hard to understand, and it also limits the deployment on proprietary CAN bus without prior knowledge. To solve this, we design a novel clock-skew-based approach capable of pinpointing the sender and detecting intrusion on proprietary CAN bus. We take a single CAN frame as the object for measurement, and adjust the measuring process such that our approach can be independent of the transmission time of frames. Based on the statistical analysis of data from real vehicles, we propose a novel box-plot algorithm based on score mechanism to filter the raw data. Finally, the clock skews are estimated and accumulated to build a linear model for representing the transmitter ECU. The evaluation results on one CAN prototype and two production vehicles show that our approach is able to well identify and differentiate ECUs on the bus without prior knowledge. The data processed by the proposed box-plot algorithm can describe the hardware characteristics of ECUs precisely. We also show the ability of our approach to protecting the CAN bus against the masquerade attack.

The controller provisioning, which adjusts the number, locations, and members of satellite controllers adaptive to the dynamic network load and topology, fundamentally impacts the performance of software-defined satellite networks (SDSNs). An ideal provisioning strategy should achieve a low total control overhead throughout the entire satellite operation period, which is extremely challenging since the network loadcan only be predicted in a short time scale. Existing methods can hardly achieve this goal for they greedily configure controllers in each time slot, where switches have to frequently migrate from one controller to another. In this paper, we focus on achievingglobally optimized strategieswith onlycurrent network load information. We first propose a comprehensive control overhead model and formulate theControllerProvisioningProblem (CPP)in SDSNs as a non-convex integer programming problem. To solve the problem, we propose an approximate algorithm named AROA by introducing a regularization framework and based on randomized rounding. We theoretically derive its competitive ratio. To produce strategies in time for future large satellite constellations, we further propose a more efficient heuristic algorithm HROA. Evaluations on our built simulation system show that our proposed methods significantly outperform related schemes in control overhead, latency, and scalability.

Various stream learning methods are emerging in an endless stream to provide a wealth of solutions for artificial intelligence in streaming data scenarios. However, when each data stream is oriented to a different target space, it forces stream learning approaches oriented to the same task to be no longer applicable. Due to inconsistent target spaces for different tasks, the previous approaches fail on the new streaming tasks or it is impracticable to be trained from scratch with few labeled samples at the beginning. To this end, we have proposed an adaptive learning scheme for few-shot streaming tasks with the contributions of tensor and meta-learning. This adaptive scheme is conducive to mitigating the domain shift when a new task has few labeled samples. We elaborate a novel tensor-empowered attention mechanism derived from nonlocal neural networks, which enables to capture long-range dependency and preserve the high-dimensional structure to refine the global features of streaming tasks. Furthermore, we develop a fine-grained similarity computing approach, which is prone to better characterize the difference across few-shot streaming tasks. To show the superiority of our method, we have carried out extensive experiments on three popular few-shot datasets to simulate streaming tasks and evaluate the performance of adaptation. The results show that our proposed method has achieved competitive performance for few-shot streaming tasks compared with the state-of-the-art (SOTA).

Cyber-physical-social systems (CPSS), an emerging cross-disciplinary research area, combines cyber-physical systems (CPS) with social networking for the purpose of providing personalized services for humans. CPSS big data, recording various aspects of human lives, should be processed to mine valuable information for CPSS services. To efficiently deal with CPSS big data, artificial intelligence (AI), an increasingly important technology, is used for CPSS data processing and analysis. Meanwhile, the rapid development of edge devices with fast processors and large memories allows local edge computing to be a powerful real-time complement to global cloud computing. Therefore, to facilitate the processing and analysis of CPSS big data from the perspective of multi-attributes, a cloud-edge-aided quantized tensor-train distributed long short-term memory (QTT-DLSTM) method is presented in this article. First, a tensor is used to represent the multi-attributes CPSS big data, which will be decomposed into the QTT form to facilitate distributed training and computing. Second, a distributed cloud-edge computing model is used to systematically process the CPSS data, including global large-scale data processing in the cloud, and local small-scale data processed at the edge. Third, a distributed computing strategy is used to improve the efficiency of training via partitioning the weight matrix and large amounts of input data in the QTT form. Finally, the performance of the proposed QTT-DLSTM method is evaluated using experiments on a public discrete manufacturing process dataset, the Li-ion battery dataset, and a public social dataset.

Non-volatile memory express (NVMe) solid-state drives (SSDs) have been widely adopted in multi-tenant cloud computing environments or multi-programming systems. The on-board DRAM cache inside NVMe SSDs can efficiently reduce the disk accesses and extend the lifetime of SSDs. Current SSD cache management research either improves cache hit ratio while ignoring fairness, or improves fairness while sacrificing overall performance. In this paper, we present MLCache, a space-efficient shared cache management scheme for NVMe SSDs. By learning the impact of reuse distance on cache allocation, a workload-generic neural network model is built. At runtime, MLCache continuously monitors the reuse distance distribution for the neural network module to obtain space-efficient allocation decisions. MLCache also proposes an efficient parallel writing back strategy based on hit ratio and response time, to improve fairness. Experimental results show MLCache improves the write hit ratio when compared to baseline, and MLCache strongly safeguards the fairness of SSDs with parallel write-back and maintains a low level of degradation.

Deep learning has been proved to be one of the most effective method in feature encoding for different intelligent applications such as video-based human action recognition. However, its nonconvex optimization mechanism leads large memory consumption, which hinders its deployment on the smart embedded systems with limited computational resources. To overcome this challenge, we propose a novel deep model compression technique for smart embedded systems, which realizes both the memory size reduction and inference complexity decrease within a small drop of accuracy. First, we propose an improved naive Bayes inference-based channel parameter pruning to obtain a sparse model with higher accuracy. Then, to improve the inference efficiency, the improved Tucker decomposition method is proposed, where an improved genetic algorithm is used to optimize the Tucker ranks. Finally, to elevate the effectiveness of our proposed method, extensive experiments are conducted. The experimental results show that our method can achieve the state-of-the-art performance compared with existing methods in terms of accuracy, parameter compression, and floating-point operations reduction.

Extensive growth in developing new and efficient methods for tensor factorizations has made their intelligent applications in cyber–physical–social systems (CPSS) a hot research topic. Tensor factorizations facilitate the need for recommendations that are accurate and circumstantial, which pushes the limits of traditional collaborative filtering methods to multifaceted versions based on real intelligent environments. Nevertheless, recommenders in edge–cloud computing require information encapsulated in user models to give useful suggestions on user preferred items, which presents stern privacy trepidations. In this article, a novel edge–cloud-aided differentially private tucker decomposition scheme is proposed to avert data owner’s private data from being learned by other data owners, untrusted edge, and cloud during tucker decomposition for CPSS. Our design dissevers users’ private data computations in tucker decomposition to edges from the cloud, and the cloud is forced to perform perturbed results aggregation while preserving privacy. The scheme employs perturbation to ensure differential privacy, and the perturbation noise components are decomposed into small manageable parts that can be locally and independently resolved by edges. Our extensive experiments on two real data sets show the proposed scheme is efficient and has tolerable side effects on the results’ utility.

Mobile crowdsourcing (MCS) has become an effective data collection method due to its mobility, low cost, and flexibility. However, since centralized MCS confronts severe security and privacy risks in reality, many researchers are devoted to building a decentralized MCS system based on blockchain. Despite the effectiveness of these schemes, they fail to offer anonymous authentication on the trust of MCS nodes, although privacy is a main concern in MCS and trust plays an important role in a series of MCS activities, such as worker selection and truth discovery. Nevertheless, anonymous authentication on trust is not a trivial issue since trust evaluation usually conflicts with anonymity, which is a necessary privacy requirement in an open MCS environment. To tackle this problem, we leverage Intel software guard extension (SGX) and propose a scheme to anonymously authenticate trust with trustworthy trust evaluation in a blockchain-based MCS system. The scheme employs an SGX-enabled cloud server to periodically alter user public/private key pairs and mix newly altered keys among a number of faked keys in order to ensure unlinkability. Besides, we consider the unique features of MCS and work out a novel trust evaluation method by aggregating both subjective feedback and objective behaviors. Finally, we conduct several analyses and experiments to illustrate its security and efficiency.

Given monocular images as inputs, monocular depth estimation (MDE) infers pixel-level depth. MDE is always a critical stage in scene sensing on edge devices. Existing MDE studies frequently employ deep neural networks (DNNs) for MDE, but they still face some problems, such as sacrificing computational complexity and efficiency in return for great precision, or losing more precision in exchange for increased efficiency. To alleviate these issues; 1) we propose an encoder–decoder network (EdgeNet) for precise and fast MDE on different edge devices. When recovering depth in the decoder, we design upsampling modules to aggregate global depth information with low computational complexity, improving the accuracy of the decoder by extracting its different ranges of depth information; 2) we develop a two-stage channel pruning method to, respectively, prune the encoder and decoder based on their characteristics. Our pruning method further reduces latency and model/computational complexity of EdgeNet, while losing little accuracy; and 3) we optimize the pruned EdgeNet to decrease graphics processing unit (GPU) scheduling overhead. The optimization accelerates MDE inference by an order of magnitude on the TX2 GPU device, when the input resolution is 224$\times $224. Extensive experiments show that our strategies are effective on different edge GPU devices, when input resolutions differ in outdoor or indoor scenes. For example, compared with the state of the art, the optimized EdgeNet, respectively, reduces the GPU latency by 76.3% and 89.2% on Nano and TX2 GPU devices with 2.6% lower root mean square error when the input resolution is 128$\times $416.

In the past few decades, the prevalence of Internet of Things (IoT) applications has brought both opportunities and challenges of different categories. One of the main concerns nowadays is semantic interoperability. Although plenty of augmented ontologies and resource description frameworks have been designed to achieve semantic interoperation, there is still no sustainable solution to interconnect the increasing number of heterogeneous devices and corresponding data. Aiming at this problem, this article presents a dataspaces model utilizing distributed approaches to represent semantic information as a sustainable solution for IoT semantic interoperability. In this model, an attention-based entity embedding approach is designed to convert IoT entities into low-dimensional dense vectors, then calculations, including entities, relations, etc., can be further conducted. Consequently, the entity embeddings could reflect the semantic information of Class equivalences among entities. To recognize entity relations, the generated entity vectors and the arithmetic results of two entities are combined as input features. By feeding the input features to a well-trained Tensor-train modified DNN, the relation between two entities could be recognized. Finally, experiments are conducted on two data sets to evaluate the proposed approaches. Results indicate that the generated entity vectors could effectively reflect the semantic similarity between entities. More importantly, while achieving parameter compression and better generalizing ability, the relation recognition approach improves the relation recognition accuracy on new entities compared with the state-of-art models.

Controller area network with flexible data-rate (CAN-FD) has received great attention in automotive cyber–physical systems (ACPSs) due to its high bandwidth and long payload. However, CAN-FD adopts a broadcast message transmission mechanism and lacks security protection, making it extremely vulnerable to cyberattacks. CAN-FD message packing (packing signals into messages) with low bandwidth occupancy (utilization) under security constraints is the prerequisite for running intelligent applications in ACPS. In this work, we implement a two-stage CAN-FD message packing solution to reduce bandwidth utilization and improve signal acceptance rate under security constraints. The first stage solves the message packing problem of minimizing bus bandwidth utilization under security constraints. The second stage aims at improving the signal acceptance rate by repacking signals. Experimental results show that the first stage reduces average bus bandwidth utilization by 135% compared with the unpacking solution, and the second stage improves the average signal acceptance rate by 5% than existing advanced methods.

As an indispensable part of the Internet of Vehicles (IoV), unmanned aerial vehicles (UAVs) can be deployed for target positioning and navigation in the space–air–ground-integrated network (SAGIN) environment. Maritime target positioning is very important for the safe navigation of ships, hydrographic surveys, and marine resource exploration. Traditional methods typically exploit satellites to locate marine targets in the SAGIN environment, and the location accuracy does not satisfy the requirements of modern ocean observation missions. In order to localize the marine target, we develop a system architecture in this article, which contains UAVs integrated with monostatic multiple-input–multiple-output (MIMO) radars. The main thrust is to estimate the direction-of-arrival (DOA) via MIMO radar. Herein, we consider a general scenario that unknown mutual coupling exist and a novel sparse reconstruction algorithm is proposed. The mutual coupling matrix (MCM) is adopted with the help of its special structure, we formulate the data model as a sparse representation form. Then, two novel matrices, a weighted matrix, and a reduced-dimensional matrix are constructed to reduce the computational complexity and enhance the sparsity, respectively. Thereafter, a sparse constraint model is constructed using the concept of optimal weighted subspace fitting (WSF). Finally, the DOA estimation of maritime targets can be achieved by reconstructing the support of a block sparse matrix. Based on the DOA estimation results, multiple UAVs are used to cross-locate marine targets multiple times, and an accurate marine target position is achieved in the SAGIN environment. Numerical results are carried out, which demonstrates the effectiveness of the proposed DOA estimator, and the multi-UAV cooperative localization system can realize accurate target localization.

Knowledge graph builds the bridge from massive data generated by the interaction and communication between various objects to intelligent applications and services in Internet of Things. The graph representation learning technology represented by graph neural networks plays an essential role in the understanding and reasoning of the knowledge graph with complicated internal structure. Although they are capable of assigning different attention weights to neighbors, the graph attention network (GAT) and its variants are inherently flawed and inadequate in modeling high-order knowledge graphs with high heterogeneity. Therefore, we propose a novel multirelational GAT framework in this article for knowledge reasoning over heterogeneous graphs by employing tensor and tensor operations. Specifically, we formulate the general high-order heterogeneous knowledge graph first. Then, the tensor GAT (TGAT), composed of three components: 1) heterogeneous information propagation; 2) multimodal semantic-aware attention; and 3) knowledge aggregation, is developed to simulate rich interactions between mixed triples, entities, and relationships when aggregating local information. What is more, we utilize the Tucker model to compress the parameters of TGAT and further reduce the storage and calculation consumption of the intermediate calculation process on the premise of maintaining the expressive power. We conduct extensive experiments to solve the link prediction task on four real-world heterogeneous graphs, and the results demonstrate that the TGAT model proposed in this article remarkably outperforms state-of-the-art competitors and improves the hits@1 accuracy by up to 7.6%.

As increasingly more textual information becomes available, named entity recognition (NER) systems are thriving, benefiting from powerful models and expressive tagging schemes that promote the full use of diverse features at different levels. To improve performance, traditional approaches have focused mainly on changing the structures of NER models but have always ignored the hard constraints and left the NER tagging schemes unchanged. To solve this problem, this article proposes a dynamic entity-based NER approach under unconstrained tagging schemes. To eliminate the constraints, we reorganize widely used tagging schemes and propose two novel unconstrained schemes: one in which tags are assigned to words and entities separately, and one where words and entities are labeled indiscriminately by uniformly taking them as chunks. Associated with the unconstrained tagging schemes, two entity-based neural architectures are also presented that recognize entities at the same time that the sentence is dynamically segmented. Unlike other static NER models that process all the tags after labeling each word, our models address the inputs dynamically by the interactions between the input text and the output labels. The dynamic mechanism can ensure that the entity-level features are included in the NER system, which is helpful for correctly recognizing entities. Except for word embeddings pretrained from unlabeled corpora, no external language-specific knowledge or other resources such as gazetteers are used. The experiments with English, German, Dutch, and Spanish datasets show that our methods can perform very well with different languages. Particularly, the results of the recall rate against the entity’s length reveal that the proposed entity-based models are suitable for recognizing entities with long lengths.

Nonlinearly constrained nonlinear programming (NLC-NLP) problems arise in various real-world decision-making fields, such as financial engineering, urban planning, supply chain management, and power system control. They are usually large-scale because of having to consider massive variables and constraints. Solving NLC-NLP problems by employing common algorithms (e.g., gradient projection method (GPM)) is usually computationally-expensive, which challenges common organizations in solving large-scale NLC-NLP problems. To address this issue, an option is to adopt cloud computing for help. However, this raises security concerns since real-world NLC-NLP problems may carry sensitive information. Although previous secure outsourcing algorithms try to protect sensitive information, they still let cloud service tenants bear heavy computation burden. In this paper, we develop a practical secure outsourcing algorithm for using the GPM to solve large-scale NLC-NLP problems. To be more prominent, to accelerate computations and avoid possible memory overflowing, we parallelize the developed algorithm. We implement the developed algorithm on the Amazon Elastic Compute Cloud (EC2) and a laptop, and also offer extensive experiment results to show that the developed algorithm can reduce the tenant’s computing time significantly.

As one important technique of fuzzy clustering in data mining and pattern recognition, the possibilistic c-means algorithm (PCM) has been widely used in image analysis and knowledge discovery. However, it is difficult for PCM to produce a good result for clustering big data, especially for heterogenous data, since it is initially designed for only small structured dataset. To tackle this problem, the paper proposes a high-order PCM algorithm (HOPCM) for big data clustering by optimizing the objective function in the tensor space. Further, we design a distributed HOPCM method based on MapReduce for very large amounts of heterogeneous data. Finally, we devise a privacy-preserving HOPCM algorithm (PPHOPCM) to protect the private data on cloud by applying the BGV encryption scheme to HOPCM, In PPHOPCM, the functions for updating the membership matrix and clustering centers are approximated as polynomial functions to support the secure computing of the BGV scheme. Experimental results indicate that PPHOPCM can effectively cluster a large number of heterogeneous data using cloud computing without disclosure of private data.

NAND flash memory has been widely adopted in emerging storage systems. To ensure data security, the support of data sanitization in NAND flash memory-based storage systems is widely employed. Although some existing studies made efforts in employing encryption-based, erasure-based, and scrubbing-based secure deletion approaches to achieve the security requirement, they suffer from the risk of being deciphered, the severe performance, and the scrubbing disturbance problems. Meanwhile, 3-D NAND flash technology, which stacks flash cells in vertical direction, is gaining traction in the modern systems. This made the problems more severe because of the increased number of scrubbing disturbance directions in 3-D NAND flash memory. To address the above issue, this work proposes an approximate-data-aware data sanitization scheme (ADS) with the assistance of the error-resilient data of modern applications, which guarantees the highest degree of security for security-sensitive data sanitization (i.e., storage systems do not keep any old version of secure data once secure data are updated). ADS classifies request data into approx-secure (AS), precise-secure (PS), approx-unsecure (AU), and precise-unsecure (PU) data by considering two factors, including data error resilience and data privacy. Then, a novel data allocation strategy is proposed to selectively interleave secure data and approximate data within the flash blocks, which creates the scrubbing friendly data patterns to minimize the overhead of secure deletion. Our experimental results show that ADS reduces the average secure deletion latency by 58.93% over the state of the art.

With the increased density and the technology scaling, flash memory is more vulnerable to noise effects, overwhelmingly lowering the data retention time. The periodic data refresh technique is commonly used to retain the long-term data integrity. However, the frequent refresh requests introduce the increased access conflict and severe write amplification, leading to suboptimal performance and lifetime improvement of flash memory-based storage systems. In this article, we propose ApproxRefresh, which enables the uncorrectable data reuse with the assistance of approximate-computing applications to reduce the refresh costs. Specifically, we design a lightweight remapping-free refresh technique, called RFR, to periodically correct, compute an enhanced ECC, and only remap new ECC parity bits, which dramatically reduces the refresh costs. Then, with approximate-read and precise-read hotness awareness, ApproxRefresh selectively adopts RFR or the traditional remapping-based refresh technique to reduce the refresh costs and the read disturbance. Besides, ApproxRefresh further improves flash access performance based on data hotness and process variations. In addition, a corresponding ApproxRefresh-aware garbage collection algorithm is proposed to complete the design. Evaluations show that ApproxRefresh reduces the refresh latency by 36.19% over the state of the art.

Private Set Intersection (PSI) is typically used to achieve ID alignment with protection of IDs in the preparation phase of Vertical Federated Learning (VFL). However, existing PSI approaches are limited to protecting IDs that are outside the intersection of participants, and most ignore the sensitivity of intersection for a weak party in an asymmetrical ID alignment. Since the set size of the strong party is much greater than the weak party’s in an asymmetrical federation, and the intersection usually accounts for a substantial part of the weak party set, the weak party’s sensitive sample IDs would be severely compromised through sharing the intersection. To address this issue, we propose Differentially private PSI Cardinality and PSI (DPSI-CA, DPSI) protocols, which protect the intersection cardinality and sensitive IDs inside the intersect ion for the weak party, respectively. First, DPSI-CA encodes IDs in binary notation, and combines them with the GM encryption, to perform the ID-matchmaking by executing bitwise plaintext XOR. Then, the encrypted matching results are independently perturbed using randomized responses to produce differentially private outputs for PSI-CA, and its unbiased estimate is added to remove the deviation brought by the randomization. Furthermore, DPSI fuses Pseudo-Random Function (PRF)-based zero sharing, garbled Bloom filter, and Oblivious PRF (OPRF)-based shares reconstruction, to successfully reconstruct the shares corresponding to sampled IDs in the intersection. Meanwhile, a randomized response is used to sample the inputs and perturb the outputs of the OPRF-based shares reconstruction, producing a randomly sampled intersection for the weak party and differentially private intersection for the strong party. Finally, the privacy analysis shows that our protocols provide differential privacy for the weak party’s sensitive sample IDs, and extensive experiment results illustrate the feasibility of the asymmetrical ID alignment involving millions of IDs.

Industrial cyber–physical–social systems (CPSSs), a prominent data-driven paradigm, tightly couple and coordinate social space into cyber–physical systems (CPSs) within industrial environments. With the proliferation of cloud–fog computing, cloud–fog computing becomes the most prominent computing paradigm used to implement industrial data analysis. However, the open environment of cloud–fog computing and the limited control of industrial CPSSs users make industrial data analysis without compromising users’ privacy one great research challenge in practical cloud–fog-based industrial applications. High-order Bi-Lanczos (HOBI-Lanczos) approach has shown remarkable success in heterogeneous data analysis in industrial applications. In this article, a novel privacy preserving HOBI-Lanczos approach using tensor train in cloud–fog computing is proposed for industrial data applications. Specifically, a privacy preserving industrial data analysis model using cloud–fog computing and tensor train is firstly proposed. The proposed model enables fogs and clouds to securely carry out industrial data analysis for large-scale tensors given in a tensor train format. In addition, by using this model, a privacy preserving HOBI-Lanczos approach is provided. Last but not least, by using a brain-controlled robot system case study, the proposed approach is theoretically and empirically analyzed. Our proposed approach is proven to be secure. A series of experiments corroborate the superiority of the proposed approach in cloud–fog computing for industrial applications.

Human behavior understanding is playing more and more important role in human-centered Industrial Internet of Video Things (IIoVT) system with the deep combination of artificial intelligence and video-based industrial Internet of Things. However, it requires expensively computational resources, including high-performance computing units and large memory, to train a deep computation model with a large number of parameters, which limits its effectiveness and efficiency for IIoVT applications. In this article, a tensor-train mechanism based deep model is presented for video human behavior understanding to meet the requirement of IIoVT applications. It can get competitive performance in accuracy and training efficiency with potentiality for combination of artificial intelligence and prefront IIoVT system. On the one hand, to achieve desirable accuracy, we improved the conventional CNN and adopted the recurrent neural network mechanism to enhance the video representation over time, which takes the correlation between consecutive deep feature into consideration. On the other hand, to enhance the inference capacity between the spatial and temporal features, we carry out the self-critical reinforcement learning mechanism in parameter learning stage. Meanwhile, to further reduce parameter storage size to meet requirement for the deployment of deep neural network and edge device, the tensor-train mechanism is used, which transforms the parameter matrix to a tensor space and carry out tensor decomposition mechanism to decrease the number of parameter generated in parameter training. Finally, we conduct extensive experiments to evaluate our scheme, and the results demonstrate that our method can improve the training efficiency and save the memory space for the deep computation model with better accuracy.

With the bloom of intelligent devices over the world, a large scale of user’s trajectory data are collected. How to mine valuable rules from these data and provide services for the industrial community has become an urgent problem. In this article, we propose a multimodal prediction system to infer users’ mobility pattern embedded in heterogeneous data from cyber–physical–social space. According to users’ mobility pattern, the framework can provide smart services for the industrial community. The highlight is the retrospective multivariate multistep transition tensor (${\text{M}^2}{\text{T}^2}$) chain model, which decomposes a large scale of${\text{M}^2}{\text{T}^2}$into a series of small-scale transition tensors (subtransition tensors) with the tensor maximum likelihood estimation method. Then, that one can solve the stationary probability distribution with the small-scale subtransition tensors so as to highly reduce the computation and storage cost. At the same time, the tensor maximum likelihood estimation method avoids the overfitting of${\text{M}^2}{\text{T}^2}$, so the proposed model improves the performance of prediction systems. In the end, several experiments are constructed to evaluate the proposed model.

Human-oriented and machine-generated data in cyber-physical-social systems are often complicated graph-structured. Graph-powered learning methods are conducive to discovering valuable knowledge from large-scale graph data and improving decision-making processes. However, due to the neglect of diverse relations among things, most existing knowledge reasoning studies are inherently flawed and inefficient in processing the heterogeneous graphs with high-order connectivity. Tensor, as a powerful and effective tool to model high-level semantic interactions between various things, can provide high-order Internet of things graph with new perspectives and possibilities. Therefore, this article innovatively proposes a collaborative artificial intelligence of things data analysis and application framework based on Boolean tensors, which supports the expression and fusion of heterogeneous graph and ultimately promotes the AI processing. In this context, we focus on developing an incremental Boolean tensor factorization (IBTF) approach for efficient knowledge reasoning to meet the requirements of real-time and high-level quality demands for intelligent services. To the best of our knowledge, we are the first to do this work. More concretely, we present factors update and binary features merge algorithms for the integrated graph tensors to avoid numerous repeated calculations of historical data. Experimental results on general synthetic datasets demonstrate that the IBTF approach proposed in this article guarantees nearly equal approximate accuracy while reducing execution time by dozens and even more of times. Furthermore, experimental evaluations and interpretability analysis on real-world datasets verify the practicality of the proposed framework and approach.

Cloud manufacturing has emerged as a service-oriented paradigm, in which knowledge graphs (KGs) play a crucial role in enabling modularization and on-demand servitization by converting unstructured resources into a structured graph representation and factual knowledge for manufacturing tasks. KG embedding converts entities and relations into a low-dimensional space while expressing rich semantics of high-dimensional KGs. Existing works just focus on translating relations surrounding the nodes of graphs, while ignoring the applicability for modeling and inferring multiple relation patterns in the manufacturing context. Furthermore, the relative importance of complex manufacturing relations among different dimensions in embedded procedures has been ignored, leading to unclear representation learning of complex relations and entities in KGs. To overcome this issue, in this article, a novel relation and entropy weight-aware embedding model is proposed, namedTransCE.TransCEperforms coordinated transformations in vector space by normalizing the distance to integrate coordination. An entropy-based weighting method is also proposed to represent complex relations and entities surrounding the edges of graph embedding and assign the weighted value of relations to support the score function. Extended experiments are performed on several datasets, and a manufacturing indicates thatTransCEshows remarkable improvement relative to baseline models.

Recently, along with several technological advancements in cyber-physical systems, the revolution of Industry 4.0 has brought in an emerging concept named digital twin (DT), which shows its potential to break the barrier between the physical and cyber space in smart manufacturing. However, it is still difficult to analyze and estimate the real-time structural and environmental parameters in terms of their dynamic changes in digital twinning, especially when facing detection tasks of multiple small objects from a large-scale scene with complex contexts in modern manufacturing environments. In this article, we focus on a small object detection model for DT, aiming to realize the dynamic synchronization between a physical manufacturing system and its virtual representation. Three significant elements, including equipment, product, and operator, are considered as the basic environmental parameters to represent and estimate the dynamic characteristics and real-time changes in building a generic DT system of smart manufacturing workshop. A hybrid deep neural network model, based on the integration of MobileNetv2, YOLOv4, and Openpose, is constructed to identify the real-time status from physical manufacturing environment to virtual space. A learning algorithm is then developed to realize the efficient multitype small object detection based on the feature integration and fusion from both shallow and deep layers, in order to facilitate the modeling, monitoring, and optimizing of the whole manufacturing process in the DT system. Experiments and evaluations conducted in three different use cases demonstrate the effectiveness and usefulness of our proposed method, which can achieve a higher detection accuracy for DT in smart manufacturing.

Intelligent transportation system (ITS) is a key enabler for future road traffic management systems. The core components of ITS include vehicles, roadside units, and traffic command centers. They generate a large amount of data flow that is made up of both mobility and service-related data. Therefore, some data science methods to handle the transportation data are very necessary for ITS. Although some attempts have been done to explore data science methods for ITS, there exist various scientific and engineering challenges including software and hardware development, computational complexity, data multi-source heterogeneity, and privacy protection. Consequently, to fully explore the benefits of ITS applications like connected and autonomous vehicles, traffic control and prediction, road safety, and accident prediction, advanced data science methodologies and applications are in great need.

In intelligent transportation systems, the key issue of the Ride-Sharing Service (RSS) is to find proper drivers for the passengers by Intelligent Matching (IM) of two or three objects, including the positions of drivers, the travel information of passengers, and the spots where passengers and drivers meet and separate. Unfortunately, the exposure of travel plans of passengers in the IM process due to inference attacks has raised concerns about the privacy violation. To resist the inference attacks, we propose a Differentially Private Tripartite IM (DPTIM) protocol for RSS. DPTIM is based on the tripartite IM process, which intelligently finds the suitable threshold to filter out the matched objects with satisfaction scores below the threshold, so as to provide the high average satisfaction score of matched passengers. Compared to existing relevant mechanisms, DPTIM is distinguished by the feature that it leverages the inference error and differential privacy techniques to prevent the prior-information-based inference attacks and constrain the posterior information leakage, while providing satisfactory matching results. Furthermore, DPTIM meets the personalized demand of location privacy by using the passenger-specific tolerance estimation on inference errors and the personalized privacy budget. Finally, we implement DPTIM on real-world datasets, and demonstrate the satisfactory performance of DPTIM in terms of the average satisfaction score of passengers, the anti-inference-attack capability, and the passenger-specific privacy requirement.

Deep computation models (DCMs) are widely used in intelligent transportation systems (ITS), like driving behavior detection, intelligent parking navigation and real-time road condition detection. Due to the multi-source heterogeneous nature of big data of the ITS, it is difficult for traditional DCMs to learn effective multi-modal data features. Although, the DCMs in tensor space can efficiently represent multi-modal data, it further worsens the problem of model learning parameter explosion. In this paper, we propose a lightweight tensor DCM. The model compresses the redundant learning parameters of the model and reduces the consumption of computational resources while maintaining the learning characterization capability of the DCM in tensor space, thus making the network model more general and lightweight for deploying the DCM to smart cars and edge devices. The proposed lightweight tensor DCM is evaluated on several real datasets. The experimental results show that the number of learning parameters is massively compressed while keeping the performance of the network model almost constant, while also reducing the computational complexity and training time of the model.

Space-Air-Ground Integrated Network (SAGIN) as an efficient newly integration network could provide more comprehensive network services to meet the multifarious quality of service requirements in different Intelligent Transportation Systems (ITS). By taking advantage of SAGIN, Space-Air-Ground Integrated Vehicular Crowdsensing (SAGI-VCS) would have great potential and the services regarding ITS could be facilitated. However, centralized SAGI-VCS is usually vulnerable to malicious attacks and the trust issues are one of the main reasons that hinder its further development. Blockchain as a distributed hyperledger shows a vital potential to solve the trust problem of multiple participants who do not trust each other and tackle the security issues in SAGI-VCS. Additionally, selfishness is another factor that prevents vehicles from participating in SAGI-VCS. The vast majority of existing incentives for vehicular crowdsensing only focus on the terrestrial networks which cannot be directly used in SAGI-VCS. Meanwhile, the redundant winner phenomenon and the multi-attributes of participants are less considered by them. Toward this end, we first illustrate a blockchain-enabled service architecture for SAGI-VCS and then construct a unified representation model. Afterwards, a tensor computing based truthful incentive mechanism TensorBC for blockchain-enabled SAGI-VCS is proposed to motivate vehicles to participate in completing tasks, ensure the security of the whole process and maximize the social welfare. TensorBC not only can eliminate the redundant winner phenomenon, but also can guarantee the economic properties such as truthfulness, individual rationality and profitability. Finally, both the rigorous theoretical analysis and extensive experimental results show that TensorBC could achieve a better performance.

Generative adversarial networks (GANs) have shown great success in deep representations learning, data generation, and security enhancement. With the development of the Internet of Things, 5th generation wireless systems (5G), and other technologies, the large volume of data collected at the edge of networks provides a new way to improve the capabilities of GANs. Due to privacy, bandwidth, and legal constraints, it is not appropriate to upload all the data to the cloud or servers for processing. Therefore, this article focuses on deploying and training GANs at the edge rather than converging edge data to the central node. To address this problem, we designed a novel distributed learning architecture for GANs, called DANCE. DANCE can adaptively perform communication compression based on the available bandwidth, while supporting both data and model parallelism training of GANs. In addition, inspired by the gossip mechanism and Stackelberg game, a compatible algorithm, AC-GAN is proposed. The theoretical analysis guarantees the convergence of the model and the existence of approximate equilibrium in AC-GAN. Both simulation and prototype system experiments show that AC-GAN can achieve better training effectiveness with less communication overhead than the SOTA algorithms, i.e., FL-GAN and MD-GAN.

Smart healthcare systems are generating a large scale of heterogenous high-dimensional data with complex relationships. It is hard for current methods to analyze such high-dimensional healthcare data. Specifically, the traditional data reduction methods can not keep the correlation among different modalities of data objects, while the latest methods based on tensor singular value decomposition are not effective for data reduction, although they can keep the correlation. This article presents a tensor train-tensor singular value decomposition (TT-TSVD) algorithm for data reduction. Particularly, the presented algorithm balances the correlation-preservation ability of modalities and data reduction ability by combining the advantages of the train structure of the tensor train decomposition and the association relationship between the tensor singular value decomposition retention mode. Extensive experiments are conducted on the convolutional neural network and the results clearly show that the presented algorithm performs effectively for data reduction with a low-loss classification accuracy; what is more, classification accuracy on medical image dataset has been improved a little.

The development of 5G has brought new opportunities for the application of Internet of Things (IoT). The integration of 5G and IoT technologies promote high availability, resilience, and reliability of the network infrastructures. IoT deployment optimization is the core issue of 5G IoT. Traditionally, IoT node deployment methods mostly used disk coverage model or probabilistic detection coverage model, which only utilizes the sensing capability of a single IoT node, which results in higher deployment costs. In this article, we study the network resilience of coverage estimation error and solve the coverage problem of resilient deployment of smart nodes in 5G IoT. The coverage formulation in the deployment optimization method is defined based on the confident information coverage (CIC). In order to obtain the optimal deployment with a given coverage quality and with a given budget, the mixed-integer linear programming models (CICILP-COST) and (CICILP-ERROR) are proposed based on the CIC model. After analyzing the model complexity, the proposed models are solved by the variable relaxation algorithm (CICVR-COST) and dichotomous search algorithm (CICDS-ERROR), respectively. Simulations on air pollution datasets in Lyon, France, show that the proposed model yields a lower cost optimal deployment than existing peer schemes.

Knowledge graph describes entities by numerous RDF data (subject-predicate-object triples), which has been widely applied in various fields, such as artificial intelligence, Semantic Web, entity summarization. With time elapses, the continuously increasing RDF descriptions of entity lead to information overload and further cause people confused. With this backdrop, automatic entity summarization has received much attention in recent years, aiming to select the most concise and most typical facts that depict an entity in brief from lengthy RDF data. As new descriptions of entity are continually coming, creating a compact summary of entity quickly from a lengthy knowledge graph is challenging. To address this problem, this article first formulates the problem and proposes a novel approach of Incremental Entity Summarization by leveraging Formal Concept Analysis (FCA), called IES-FCA. Additionally, we not only prove the rationality of our suggested method mathematically, but also carry out extensive experiments using two real-world datasets. The experimental results demonstrate that the proposed method IES-FCA can save about 8.7 percent of time consumption for all entities than the non-incremental entity summarization approach KAFCA at best. As for the effectiveness, IES-FCA outperforms the state-of-the-art algorithms in terms of$F1-measure$,$MAP$, and$NDCG$.

It is critical but difficult to efficiently model re-sources in space-terrestrial integrated networks (STINs). Existing work is not applicable to STINs because they lack the joint consideration of different movement patterns and fluctuating loads. In this paper, we propose the time-varying resource graph (TVRG) to model STINs from the resource perspective. Firstly, we propose the STIN mobility model to uniformly model different movement patterns in STINs. Then, we propose a layered Resource Modeling and Abstraction (RMA) approach, where evolutions of node resources are modeled as Markov processes, by encoding predictable topologies and influences of fluctuating loads as states. Besides, we propose the low-complexity domain resource abstraction algorithm by defining two mobility-based and load-aware partial orders on resource abilities. Finally, we propose an efficient TVRG-based Resource Scheduling (TRS) algorithm for time-sensitive and bandwidth-intensive data flows, with the multi-level on-demand scheduling ability. Comprehensive simulation results demonstrate that the RMA-TRS outperforms related schemes in terms of throughput, end-to-end delay and flow completion time.

With more devices being inter- or intra-connected, Internet of Things (IoT) has gradually been adopted in many disciplines, such as healthcare industry, coined as Internet of Medical Things (IoMT). The purpose of IoMT is to facilitate the efficiency and effectiveness of medical operations, i.e., remotely monitoring the status of patients. In such healthcare environments, smartphones have become an important device to communicate with others and update the information of patients, resulting in a special type of IoMT called Medical Smartphone Networks (MSNs). To reinforce the distributed architecture, trust management schemes are often implemented to defend against insider attacks. However, how to maintain the robustness of trust management in heavy traffic networks still remains a challenge, i.e., COVID-19 incident would cause excessive traffic for healthcare organizations and increase the difficulty of validating trustworthiness among MSN nodes. In this work, we focus on this issue and propose a blockchain-enabled adaptive traffic sampling method to help enhance the robustness of trust management under high traffic environments. The use of blockchain technology aims to build a verified database of malicious traffic among all nodes. The evaluation in a real healthcare environment demonstrates the viability and effectiveness of our approach.

Video surveillance techniques like scene segmentation are playing an increasingly important role in multimedia Internet-of-Things (IoT) systems. However, existing deep learning-based methods face challenges in both accuracy and memory when deployed on edge computing devices with limited computing resources. To address these challenges, a tensor-train video scene segmentation scheme that compares the local background information in regional scene boundary boxes in adjacent frames is proposed. Compared to the existing methods, the proposed scheme can achieve competitive performance in both segmentation accuracy and parameter compression rate. In detail, first, an improved faster region convolutional neural network (faster-RCNN) model is proposed to recognize and generate a large number of region boxes with foreground and background to achieve boundary boxes. Then, the foreground boxes with sparse objects are removed and the rest are considered as optional background boxes used to measure the similarity between two adjacent frames. Second, to accelerate the training efficiency and reduce memory size, a general and efficient training way using tensor-train decomposition to factor the input-to-hidden weight matrix is proposed. Finally, experiments are conducted to evaluate the performance of the proposed scheme in terms of accuracy and model compression. Our results demonstrate that the proposed model can improve the training efficiency and save the memory space for the deep computation model with good accuracy. This work opens the potential for the use of artificial intelligence methods in edge computing devices for multimedia IoT systems.

In the Internet of Things (IoT) for smart healthcare applications, sensors collect a vast amount of healthcare data, while coverage significantly affects the Quality of Service (QoS). In wireless sensor networks (WSNs), the QoS as well as the network lifetime are dramatically degraded with the increment of coverage holes, especially in large-scale hybrid WSNs (LS-HWSNs) where big data are collected by thousands of sensors distributed in a wide monitored area. In a LS-HWSN, two crucial problems, i.e., covering the wide area without coverage holes and designing an energy-efficient manner for dispatching mobile sensors to repair coverage holes, need to be solved. We study the problems from the cutting point of confident information coverage hole repairing (CICHR). To this end, based on the confident information coverage (CIC) model, a CIC hole predicting (CICHP) algorithm, centralized energy-efficient repairing (CEER) algorithm, and distributed energy-efficient repairing (DEER) algorithm are developed. The CICHP algorithm can predict the prior information of CIC holes (CICHs) by using the period-by-period energy consumption information of sensor nodes. Based on the prior information of CICHs, two repairing algorithms: 1) CEER and 2) DEER can schedule mobile sensors to repair CICHs beforehand. Simulation results show that the proposed algorithms can significantly improve the QoS and extend the network lifetime of LS-HWSNs.

Driven by an increasing number of connected medical devices, Internet of Medical Things (IoMT), as an application of Internet of Things (IoT) in healthcare, is developed to help collect, analyze, and transmit medical data. During the outbreak of a pandemic like COVID-19, IoMT can be useful to monitor the status of patients and detect main symptoms remotely, by using various smart sensors. However, due to the lack of emotional care in the current IoMT, it is still a challenge to reach an efficient medical process. Especially under COVID-19, there is a need to monitor emotional status among particular people like the elderly. In this work, we propose an emotion-aware healthcare monitoring system in IoMT, based on brainwaves. With the fast development of electroencephalography (EEG) sensors in current headsets and some devices, brainwave-based emotion detection becomes feasible. The IoMT devices are used to capture the brainwaves of a patient in a scenario of smart home. Also, our system involves the analysis of touch behavior as the second layer to enhance the brainwave-based emotion recognition. In the user study with 60 participants, the results indicate the viability and effectiveness of our approach in detecting emotions like comfortable and uncomfortable, which can complement existing emotion-aware healthcare applications and mechanisms.

In this article, we present an efficient criticality-aware decision-making system, named Devote, for fog-based Internet of Things (IoT) environment. Devote introduces an intelligent algorithm for the service of data based on the criticality, while considering the current availability of the resources at the fog node (FN). To cope with the dynamic IoT environment, we adopt a reinforcement-learning-based algorithm for the processing of the IoT data based on time-varying conditions. Additionally, we propose an efficient online secretary-based algorithm for choosing the best suitable candidate FN for offloading the data. To show the effectiveness of Devote, we obtained the numerical results for assessing its performance, while collating it with the benchmark schemes. We analyze different performance metrics, such as service delay, economy, and user satisfaction, which show that Devote incurs less service delay, as compared to other systems, while achieving user satisfaction of 88.4%.

Internet-of-Things (IoT)-based bridge structural health monitoring (BSHM) has recently attracted considerable attention from both academic and industrial communities of civil engineering and computer science. In conjunction with researchers from civil engineering and computer science, this article studied a fundamental problem motivated from practical IoT-based BSHM: how to effectively prolong network lifetime while guaranteeing desired coverage. Integrating a promising reinforcement learning model named learning automata (LA) with confident information coverage (CIC) model, this article presented an energy-efficient sensor scheduling strategy for partial CIC coverage in IoT-based BSHM system to guarantee network coverage and prolong network lifetime. The proposed scheme fully exploits cooperation among deployed nodes and alternatively schedules the wake/sleep status of nodes while satisfying network connectivity and partial coverage ratio. Especially, the proposed scheme takes full advantage of the LA model to adaptively learn the optimal sensor scheduling strategy and significantly extend network lifetime. A series of comparison simulations using real data sets collected by a practical BSHM system strongly verify the effectiveness and energy efficiency of the proposed algorithm. To the best of our knowledge, this is the first study on how to combine the reinforcement learning mechanism with partial coverage for maximizing the network lifetime of the IoT-based BSHM.

Social Internet of Things (SIoT), integrating the social networks and Internet of Things (IoT), leads to heterogeneous interactions of thing to thing, human to human, and human to thing, which in turn generates exploded information. Hence, as the soul of SIoT, information with its interaction and diffusion, records the track of humans and things and contains the hidden value for social administration and people's lives. Therefore, how to characterize the interplay between behavior spreading and information diffusion in SIoT is essential to predict and manage the information. Motivated by this, a more comprehensive understanding of the coupled modeling of social interaction and information diffusion processes in SIoT is conceived first. With the widespread adoption of cloud-edge computing, different nodes have different consciousness on information. Hence, a cloud-edge-aided information diffusion model is proposed for efficient interactions, which incorporates the role of edge in timely processing and feedback. On this basis, a blockchain-based cloud-edge SIoT architecture is proposed for traceability and security of information diffusion. Furthermore, the dynamical analysis of the coupled model in SIoT is provided, which illustrates the outbreak threshold, stability, and scale of information propagation. An interesting finding is that interactive behavior spreading only influences the final size of information propagation, not the spreading threshold. Extensive simulation results and detailed performance analysis verify the theoretical results, which are beneficial to provide traceable dissemination so as to find the most influential node and control the scale of information diffusion.

It is well known that deep learning is one of the most important methods for data mining. With the development of the fifth-generation mobile networks (5G) and the Internet of Things (IoT), the large volume of data collected in IoTs provides a new way to improve the capability of deep learning. Due to privacy, bandwidth, and legal concerns, it is impractical to send the data to a server or the cloud. The computing power of mobile devices makes it possible to process the data. Therefore, this article focuses on training these models in mobile devices. To solve the challenges, including unreliable networks, constrained resources, and slow convergence, we let multiple mobile devices learn a shared model collaboratively. We propose a novel architecture, GREAT, where each node chooses partners to share local model parameters according to link reliability. To balance the constrained resources and learning effectiveness, an optimization problem is developed by taking the reliability threshold as the variable of controlling the resources’ overhead. To implement this architecture, a dynamic control algorithm called Alpha-GossipSGD has been proposed. Its performance is evaluated by extensive experiments, which show that Alpha-GossipSGD can realize stable learning effectiveness over unreliable networks with constrained resources.

Cyber-physical-social big data concern heterogeneous, multiaspect, large-volume data generated in cyber-physical-social systems (CPSS). Orthogonal tensor SVD (OTSVD) has emerged as a powerful tool to reduce cyber-physical-social big data. In this work, we propose an improved secure high-order-Lanczos based OTSVD for cyber-physical-social big data reduction in clouds. Specifically, to take advantage of the parallel processing capability of cloud computing, the improved secure high-order Lanczos algorithm is derived by restructuring the original high-order Lanczos algorithm such that only one synchronization point per iteration is required. To protect data privacy, the improved secure high-order-Lanczos based OTSVD employs homomorphic encryption integrated with batching technique, and garbled circuits, and makes all computations of the OTSVD algorithm in clouds come true. To our knowledge, this is the first study to efficiently tackle big data reduction in clouds in a privacy-preserving manner. Finally, we prove that our improved approach is secure in semi-trusted model. And we evaluate the proposed improved secure OTSVD on real datasets. The results show that our proposed improved secure approach is efficient and scalable for cyber-physical-social big data reduction.

Cyber-physical-social big data generated from ubiquitous devices and diverse spaces generally are multi-source, heterogeneous, and deeply intertwined. To efficiently analyze and handle the ubiquitous cyber-physical-social big data, tensor is considered as an effective tool, but the curse of dimensionality is still the main bottleneck of tensor-based big data analysis. Tensor networks can considerably alleviate or overcome it through the tensor approximate theory. Therefore, this paper focuses on developing an efficient big data processing framework based on tensor networks and providing an incremental tensor train decomposition approach for the streaming big data. Concretely, this paper first presents a hierarchical cyber-physical-social big data processing framework composed of three planes, namely, data representation and decomposition, data storage and processing, and data analysis and service, in which tensor train (TT) and quantized TT decompositions are particularly introduced to remarkably overcome the curse of dimensionality. Besides, to efficiently handle the continuous streaming big data and avoid the repeated decomposition for the history data, an incremental tensor train decomposition (ITTD) approach is proposed and the complexities are further analyzed in detail. Experimental results demonstrate that ITTD demonstrably outperforms the nonincremental TT decomposition in execution time on the precise of guaranteeing the nearly equal approximation error.

In NAND flash memory-based solid-state drives (SSDs), during the idle time between the consecutive program/erase cycles (dwell time), the dielectric damage of flash cell can be partially repaired, also known as the self-recovery effect. As the effectiveness of the self-recovery effect can be improved under high temperature, self-healing SSDs are proven feasible to extend the flash endurance significantly. However, current self-healing SSDs perform the heating operations on all the worn-out blocks without considering the data retention requirement, and measures the lifetime of flash memory based on the worst-case self-recovery effect, leading to some unnecessary heating operations and the degraded performance. We propose SmartHeating, a smart heating scheme that exploits the dwell time variation and the write hotness variation to improve the I/O performance and the lifetime of self-healing SSDs. SmartHeating tracks the dwell time of all worn-out flash blocks, predicts their self-recovery effect and reliability, and avoids performing heating operations on the worn-out flash blocks that still have strong flash reliability. In addition, by exploiting the data hotness variation, SmartHeating only heats the worn-out flash blocks that store write-cold data, while allocating write-hot data to a small portion of worn-out flash blocks with negligible refresh overhead. The experimental results show that SmartHeating reduces the number of heating operations by 12.5% on average, boosts I/O performance of flash storage systems by 21.0%, and improves the lifetime of flash memory by $1.20\times $ compared with conventional heating scheme.

Smart Chinese medicine has emerged to contribute to the evolution of healthcare and medical services by applying machine learning together with advanced computing techniques like cloud computing to computer-aided diagnosis and treatment in the health engineering and informatics. Specifically, smart Chinese medicine is considered to have the potential to treat difficult and complicated diseases such as diabetes and cancers. Unfortunately, smart Chinese medicine has made very limited progress in the past few years. In this paper, we present a unified smart Chinese medicine framework based on the edge-cloud computing system. The objective of the framework is to achieve computer-aided syndrome differentiation and prescription recommendation, and thus to provide pervasive, personalized, and patient-centralized services in healthcare and medicine. To accomplish this objective, we integrate deep learning and deep reinforcement learning into the traditional Chinese medicine. Furthermore, we propose a multi-modal deep computation model for syndrome recognition that is a crucial part of syndrome differentiation. Finally, we conduct experiments to validate the proposed model by comparing with the staked auto-encoder and multi-modal deep learning model for syndrome recognition of hypertension and cold.

Control-Flow Integrity(CFI) is one of the most promising techniques against control-flow hijacking attacks. ForCommercial Off-the-Shelf(COTS) binaries, a number of solutions provide coarse-grained CFI and thus are context-insensitive, while having the benefit of introducing a low runtime overhead. However, they can hardly defend against elaborately designed attacks due to the inaccuracy of theControl-Flow Graphs(CFGs). This paper presentsCloudCFI, a context-sensitive and incremental CFI, which specifically makes full use of the characteristic of the cloud environment, where multiple instances of a software run on multiple virtual machines, and the control flow checking result from one software instance could be utilized to handle the control-hijacking occurred on other sibling instances. InCloudCFI, the accuracy of the control flow checking can be continuously increased to offer the incremental CFI, and a context-sensitive CFI policy is enforced to determine the validity of the control flow of the execution path through checking the entire execution path instead of the single edge or partial edges in the execution path.CloudCFIincludes the static phase and the runtime phase respectively. Control-flow information and basic-block information is collected through emulation execution in the static phase, and the execution paths are tracked in runtime phase to collect process-tracking information. Next, it recovers the execution path by using basic-block information and process-tracking information, and checks the validity of the control flow by using the control-flow information. A prototype system is implemented and evaluated from several aspects using RIPE and SPEC benchmarks, as well as real-world cloud applications, Memcached and Redis. The evaluation results show thatCloudCFIcan defend against most common control-flow hijacking attacks. Meanwhile, it only introduces a low runtime performance overhead.

SDN (Software defined networking) provides effective technical methods for optimal resource management. However, there are resource conflicts frequent and serious in current related schemes because they mix elephant and mice flows on shared transmission paths. So, controllers in SDN have to be smart enough to detect elephant flows with low cost and then reroute elephant and mice flows in a feature-aware way. However, existing elephant flow detection schemes suffer from high bandwidth consumption and long detection time; and little literature considers mice-flow scheduling. In this paper, we propose an Efficient Sampling and Classification Approach (ESCA). Our ESCA significantly reduces sampling overhead through estimating the arrival interval of elephant flows and filtering out redundant samples, and efficiently classifies samples with a new supervised classification algorithm based on correlations among data flows. Then, based on our low-cost ESCA, we propose a novel load-balanced routing approach LBRouting that sets up paths for elephant and mice flows with different mechanisms. The theoretical analysis proofs our ESCA outperforms related schemes. Extensive experiment results further demonstrate that our ESCA can provide accurate detection with less sampled packets and shorter detection time; and our routing approach LBRouting significantly outperforms related proposals.

In the recent past, deep learning has received remarkable acceptance in real-world applications. Social computing expands the existing notion of cyber space and physical space to a more advance cyber-physical-social system (CPSS). Therefore, deep learning provides a propitious technique for accurate mining of information from CPSS, thus facilitates CPSS to offer services of exceptional quality efficiently. However, most of the current deep learning methods are struggling to keep up with the ever-increasing heterogeneous and highly nonlinear dissemination of data. Furthermore, the advancement of deep learning presents privacy concerns. This article proposes a deep private tensor autoencoder (dPTAE), where tensors are used for data representation, and differential privacy guarantees strong privacy. The core idea of our work is to enforce differential privacy through noise injection into the objective functions instead of the results they produce. In addition, the proposed method preserves the privacy of information shared amongst CPSS in smart environments. We applied dPTAE on three representative data sets. Rigorous experimental evaluations and theoretical analysis demonstrate that dPTAE is significantly effective and efficient.

The advancement of several significant technologies, such as artificial intelligence, cyber intelligence, and machine learning, has made big data penetrate not only into the industry and academic field but also our daily life along with a variety of cyber-enabled applications. In this article, we focus on a deep correlation mining method in heterogeneous big data environments. A hierarchical hybrid network (HHN) model is constructed to describe multitype relationships among different entities, and a series of measures are defined to quantify the internal correlations within one specific layer or external correlations between different layers. An intelligent router based on deep reinforcement learning framework is designed to generate optimal actions to route across the HHN. An improved random walk with the restart-based algorithm is then developed with the intelligent router, based on the hierarchical influence across network associated with multiple correlations. An intelligent recommendation mechanism is finally designed and applied to support users' collaboration works in scholarly big data environments. Experiments based on DBLP and ResearchGate data show the practicability and usefulness of our model and method.

Nowadays, in machine learning based intrusion detection systems, ensemble learning is a commonly adopted method to improve the detection accuracy. Unfortunately, the existing works have not considered the accumulation and reuse of historical knowledge, as well as the sensitivity of the detection model to different types of attacks, which leads to a low detection accuracy. To address the issue, this article proposes a model based on sustainable ensemble learning. In the model training stage, by taking the individual classifiers probability output and classification confidence as the training data, we build multi-class regression models such that ensemble learning adapts to different attacks. Besides, in the updating stage, an iterative updating method is presented, where the parameters and decision results of the historical model are added to the training process of the new ensemble model to realize the incremental learning. Experiment results show that the proposed model significantly outperforms the existing solutions in terms of detection accuracy, false alarm, stability and robustness.

Medical Internet of Things are generating a big volume of data to enable smart medicine that tries to offer computer-aided medical and healthcare services with artificial intelligence techniques like deep learning and clustering. However, it is a challenging issue for deep learning, and clustering algorithms to analyze large medical data because of their high computational complexity, thus hindering the progress of smart medicine. In this article, we present an incremental high-order possibilistic c-means algorithm (IHoPCM) on a cloud-edge computing system to achieve medical data coclustering of multiple hospitals in different locations. Specifically, each hospital employs the deep computation model to learn a feature tensor of each medical data object on the local edge computing system, and then uploads the feature tensors to the cloud computing platform. The high-order possibilistic c-means algorithm is performed on the cloud system for medical data clustering on uploaded feature tensors. Once the new medical data feature tensors are arriving at the cloud computing platform, the incremental high-order possibilistic c-means algorithm (IHoPCM) is performed on the combination of the new feature tensors and the previous clustering centers to obtain clustering results for the feature tensors received to date. In this way, repeated clustering on the previous feature tensors is avoided to improve the clustering efficiency. In the experiments, we compare different algorithms on two medical datasets regarding clustering accuracy and clustering efficiency. Results show that the presented IHoPCM method achieves great improvements over the compared algorithms in clustering accuracy and efficiency.

Tucker decomposition has been widely used to extract meaningful and underlying data from heterogeneous data generated by different kinds of devices in a wide range of industrial Internet of Things (IIoT) applications. IIoT data uploaded to the cloud contain personal and sensitive information; thus, there is a growing concern about data privacy. Current existing data analysis solutions, however, assume that the data are reliably and securely collected from different IIoT data providers, an assumption that is not always true in the real world. To address the issues, in this article we propose a privacy-preserving tucker train decomposition based on gradient descent over blockchain-based encrypted IIoT data. Specifically, we use blockchain techniques to enable IIoT data providers to reliably and securely share their data by encrypting them locally before recording them in the blockchain. We use tensor train (TT) theory to build an efficient TT-based tucker decomposition based on gradient descent that tremendously reduces the number of elements to be updated during the tucker decomposition. We utilize the massive resources of fogs and clouds to implement an efficient privacy-preserving tucker train decomposition scheme. We use homomorphic encryption to build our scheme that does complete tucker train decomposition without the involvement of users. Results from a series of extensive experiments on synthetic datasets and real-world datasets demonstrate that our proposed scheme is efficient.

Data in modern industrial applications and data science present multidimensional progressively, the dimension and the structural complexity of these data are becoming extremely high, which renders existing data analysis methods and machine learning algorithms inadequate to the extent. In addition, high-dimensional data in actual scenarios often share some common latent components and patterns, it is necessary and significant to analyze such data in an associative manner, rather than treating them independently. Considering the problem of data islands and data privacy that is prevalent in the industry. In this article, we propose the first joint high-order orthogonal iterative (J-HOOI) algorithm for simultaneous tensor decomposition and federated tensor decomposition (FTD) model for feature extraction and dimension reduction of high-dimensional industrial data under the federated learning framework. Moreover, we also develop a secure federated computation process based on the J-HOOI method. Using this method, multiple participants iteratively calculate the local factor matrices and transfer the local information to the parameter server, which aggregates the local information to generate the globally updated factor matrices. Finally, each client generates globally compressed features by projecting local data onto these common potential spaces. We have demonstrated with real-world industrial datasets that our approach is similar to a centralized training model in decomposition accuracy and classification accuracy while respecting privacy.

For industrial applications of the artificial intelligence of things, mechanical control usually affects the overall product output and production schedule. Recently, more and more engineers have applied the deep reinforcement learning method to mechanical control to improve the company's profit. However, the problem of deep reinforcement learning training stage is that overfitting often occurs, which results in accidental control and increases the risk of overcontrol. In order to address this problem, in this article, an expected advantage learning method is proposed for moderating the maximum value of expectation-based deep reinforcement learning for industrial applications. With the tanh softmax policy of the softmax function, we replace the sigmod function with the tanh function as the softmax function activation value. It makes it so that the proposed expectation-based method can successfully decrease the value overfitting in cognitive computing. In the experimental results, the performance of the Deep Q Network algorithm, advantage learning algorithm, and propose expected advantage learning method were evaluated in every episodes with the four criteria: the total score, total step, average score, and highest score. Comparing with the AL algorithm, the total score of the proposed expected advantage learning method is increased by 6% in the same number of trainings. This shows that the action probability distribution of the proposed expected advantage learning method has better performance than the traditional soft-max strategy for the optimal setting control of industrial applications.

Supervised machine learning algorithms, especially classification algorithms, have been widely used in data analysis of industrial big data. Among them, the support vector machine (SVM) has achieved great success in the binary classification of some areas like image processing, computer vision, and pattern recognition. However, an SVM cannot achieve the desirable classification results for heterogeneous and high-dimensional data generated from thousands of industrial sensors in physical environments, because the traditional vector-based and feature-aligned SVM algorithm may result in loss of structural information and rich context information. Although the support tensor machine (STM) has extended the traditional vector-based SVM to tensor space, it fails to deal with multiple classification problems. Therefore, designing a general multiple classification algorithm for heterogeneous and high-dimensional data is a challenging but promising topic. To achieve this goal, this article presents a support multimode tensor machine (SMTM) algorithm by applying the multimode product to generalize the formulation of the STM. Furthermore, this article presents an efficient algorithm to train the parameters. Experiments conducted on various data sets validate the better performance of the SMTM over other algorithms in the multiple classification and imply the potential of the proposed model for multiple classification on industrial big data.

In the modern industry, the information has been sufficiently shared among the production equipment, intelligent subsystems, and mobile devices via advanced network technology. For this purpose, many challenges on plant-wide performance evaluation such as product quality prediction have been received considerable attention in complex industrial Internet of Things systems. In this article, an efficient and effective soft sensor based on the semisupervised parallel deepFM model is proposed for the product quality prediction. First, a label broadcasting method is presented to augment labeled samples from unlabeled samples. Then, a data binning method is introduced to discretize process variables for an unbiased estimation. Based on the modified deepFM model, quality information can be separately extracted from different components of the model while high- and low-dimensional features can be obtained. Manifold regularization is embedded into the back propagation algorithm, in which unlabeled samples issue can be further resolved. Experiments on a real-world dataset demonstrate the effectiveness and performance of the proposed methods.

As an essential part of Internet of Things, monocular depth estimation (MDE) predicts dense depth maps from a single red-green-blue (RGB) image captured by monocular cameras. Past MDE methods almost focus on improving accuracy at the cost of increased latency, power consumption, and computational complexity, failing to balance accuracy and efficiency. Additionally, when speeding up depth estimation algorithms, researchers commonly ignore their adaptation to different hardware architectures on edge devices. This article aims to solve these challenges. First, we design an efficient MDE model for precise depth sensing on edge devices. Second, We employ a reinforcement learning algorithm and automatically prune redundant channels of MDE by finding a relatively optimal pruning policy. The pruning approach lowers model runtime and power consumption with little loss of accuracy through achieving a target pruning ratio. Finally, we accelerate the pruned MDE while adapting it to different hardware architectures with a compilation optimization method. The compilation optimization further reduces model runtime by an order of magnitude on hardware architectures. Extensive experiments confirm that our methods are effective for images of different sizes on two public datasets. The pruned and optimized MDE achieves promising depth sensing with a better tradeoff among model runtime, accuracy, computational complexity, and power consumption than the state of the arts on different hardware architectures.

In a 5G industrial IoT, using fog devices (FD) to release the burden of transmission data between a base station (BS) and a register user, is currently a promising method for device-to-device (D2D) communications. In this article, we propose a collaborative communication ecosystem to deploy RF-powered FDs as intermediaries to improve the utility as well as the fairness. We examine three contributing works that activate a relay-labor exchanging market. First, we build Stackelberg games to attract D2D collaborations; second, we employ an energy harvest technology and a time-switching power scheme to make exchange benefits to support the games; third, to reduce the relay redundancy and guarantee effective transmission rates, we employ network-coded flows. To solve the double-objects optimization model of our collaborative games, a genetic algorithm NSGA-II is applied to find an optimal solution to the market. We also mathematically prove the existence of an equilibrium state in the proposed games, and afterwards simulate the whole scenario using Mininet for a performance analysis. The simulation results in Mininet show that the BS and FDs in the market games all achieve desirable utilities as well as fairness among FDs.

Industrial Internet-of-Things (IIoT) has revolutionized almost every aspect of industrial manufacturing through industrial intelligence by incorporating production equipment, mobile terminals, and smart devices with wireless or wired networks. However, industrial visual information, such as images, videos, graphs, and texts, generated and collected from the industrial processes, contains various kinds of hidden value for industrial intelligence. Therefore, for the trend of providing ubiquitous industrial intelligence, new paradigms of perception and processing technologies of visual information such as recognition methods are required. However, industrial visual information is heterogeneous and complex with multiattributes, which presents significant challenges on visual information perception and processing technologies such as multiattributes recognition method. In this article, to provide industrial intelligence, a tensor-based visual feature recognition method is used to recognize the object from the perspective of multiattributes with the combination of attributes. To demonstrate its practical implementation, a case study about the industrial intelligence on the faulty location and diameter of bearings in the IIoT is described. Also, experiments on object recognition are carried out on the public image set COIL-100 to demonstrate the performance of the proposed method.

The industrial Internet of Things (IIoT) is growing quickly due to increasing deployment and integration of smart sensors, instruments, and devices, and software using wired or wireless networks. Through this integrated hardware-software approach, industrial practices will improve significantly, resulting in industrial intelligence for more efficient manufacturing. To realize such industrial intelligence, significant developments in IIoT big data processing and analysis are required to uncover and use hidden essential and valuable information of the production process. But large-scale, streaming, multiattribute IIoT data from production processes are noisy and have redundancies. Therefore, a suitable data processing technique such as tensor-train that can handle these IIoT data is needed. However, existing tensor-train decomposition methods are inefficient and cannot meet the processing demands of the large-scale IIoT big data. In this article, we propose an advanced (improved and highly efficient) distributed tensor-train (ADTT) decomposition method with its incremental computational method for processing IIoT big data. Finally, experiments are carried out on a typical and publicly available IIoT dataset - the bearing test data to verify and measure the performances of the proposed ADTT method.

Controller Area Network with Flexible Data-rate (CAN FD) is beneficial for the in-vehicle communication of Internet of Connected Vehicles (IoCVs) because of its high bandwidth and data field length. However, CAN FD lacks a security authentication mechanism, making it extremely vulnerable to masquerade attacks. This study proposes the security enhancement for a real-time parallel in-vehicle application adopting a two-stage method. The first stage obtains the lower bound of an in-vehicle application by quickly abandoning most of sequences, while the second stage enhances security by adding Message Authentication Codes (MACs) to messages taking advantage of the laxity interval from the lower bound to the deadline. Experiments with an example and the adaptive cruise control in-vehicle application show the advantage of the proposed two-stage method in increasing the total byte size of MACs.

With the rapid development of Internet of vehicles, connected vehicles, autonomous vehicles, and autonomous driving technologies, automotive Controller Area Networks (CAN) have suffered from numerous security threats. Deep learning models are the current mainstream intrusion detection techniques for threat analysis, and the state-of-the-art intrusion detection technique introduces the Generative Adversarial Networks (GAN) model to generate usable attacked samples to supplement the training samples, but it exists the limitations of rough CAN message block construction and fails to detect the data tampering threat. Based on the CAN communication matrix defined by the automotive Original Equipment Manufacturer (OEM) for a vehicle model, we propose an enhanced deep learning GAN model with elaborate CAN message blocks and the enhanced GAN discriminator. The elaborate CAN message blocks in the training samples can precisely reflect the real generated CAN message blocks in the detection phase. The GAN discriminator can detect whether each message has suffered from the data tampering threat. Experimental results illustrate that the enhanced deep learning GAN model has higher detection accuracy, recall, and F1 scores than the state-of-the-art deep learning GAN model under various attacks and threats.

Predicting the future traffic flows by applying deep learning methods has become an alternative way for transportation network management. Combining recurrent neural networks (RNNs) with tensor to implement accurate predictions has drawn intensive attention. However, traditional RNNs cannot deal with the high-order traffic flow data and capture their inherent structural relationship to provide accurate multi-modal prediction services. Therefore, this article focuses on proposing a series of tensor-based RNNs (T-RNNs) and a T-RNNs based multi-modal prediction approach (TMMP) to provide accurate prediction services. First, we propose three types of T-RNNs including tensor-based vanilla RNN, tensor-based long short-term memory (T-LSTM) and tensor-based gated recurrent unit (T-GRU), in which the input, output and weights are arbitrary high-order tensors. Then, to compress the weight parameters, we further propose two compact TT-based GRU (TT-GRU) and Tucker-based GRU (Tucker-GRU) models by applying tensor train (TT) and Tucker decompositions to T-GRU model. Afterwards, based on the high-order output tensor generated by T-RNNs, a TMMP approach is proposed to achieve the accurate predictions under various scenarios. Extensive experimental results on the metro traffic flow dataset demonstrate that the proposed TMMP approach can improve the traffic flow prediction accuracy by at most 25.29 percentage compared with the traditional MSE-based approaches. Meanwhile, compared with the T-GRU model, the TT-GRU model can compress the number of parameters by 200~780 times. The proposed T-RNNs and TMMP approach can adapt to different application scenarios and can be used to improve the efficiency of transportation management.

Deep learning techniques have shown significant success in cyber-physical-social systems (CPSS). As an instance of deep learning models, generative adversarial nets (GAN) model enables powerful and flexible image augmentation, image generation, and classification, thus can be applied to real-world CPSS settings. GAN model training needs a large collection of cyber-physical-social data originating from various CPSS devices. Numerous prevailing GAN models depend on a tacit assumption that several cyber-physical-social data providers present a reliable source to collect training data, which is seldom the case in real CPSS. The existing GAN models also fail to consider multi-dimensional latent structure. In our work, we put forward a novel blockchain-enabled tensor-based conditional deep convolutional GAN (TCDC-GAN) model for cyber-physical-social systems. The blockchain is employed to develop a decentralized and reliable cyber-physical-social data-sharing platform between numerous cyber-physical-social data providers, such that the training data and the model are documented on a ledger that is distributed. Furthermore, a tensor-based generator and a tensor-based discriminator are well designed by employing the tensor model. The results of extensive simulation experiments show the efficacy of the proposed TCDC-GAN model. Compared with the state-of-the-art models, our model gains superior estimation performance.

Pervasive Social Networking (PSN) supports online and instant social activities with the support of heterogeneous networks. Since reciprocal activities among both familiar/unfamiliar strangers and acquaintances are quite common in PSN, it is essential to offer trust information to PSN users. Past work normally evaluates trust based on a centralized party, which is not feasible due to the dynamic changes of PSN topology and its specific characteristics. The literature still lacks a decentralized trust evaluation scheme in PSN. In this article, we propose a novel blockchain-based decentralized system for trust evaluation in PSN, called Social-Chain. Considering mobile devices normally lack computing resources to process cryptographic puzzle calculation, we design a lightweight consensus mechanism based on Proof-of-Trust (PoT), which remarkably improves system effectivity compared with other blockchain systems. Serious security analysis and experimental results further illustrate the security and efficiency of Social-Chain for being feasibly applied into PSN.

The rapid development of the Internet of Things has led to demand for high-speed data transformation. Serving this purpose is the Tactile Internet, which facilitates data transfer in extra-low latency. In particular, a Tactile Internet based on software-defined networking (SDN) has been broadly deployed because of the proven benefits of SDN in flexible and programmable network management. However, the vulnerabilities of SDN also threaten the security of the Tactile Internet. Specifically, an SDN controller relies on the network status (provided by the underlying switches) to make network decisions, e.g., calculating a routing path to deliver data in the Tactile Internet. Hence, the attackers can compromise the switches to jeopardize the SDN and further attack Tactile Internet systems. For example, an attacker can compromise switches to launch distributed denial-of-service attacks to overwhelm the SDN controller, which will disrupt all the applications in the Tactile Internet. In pursuit of a more secure Tactile Internet, the problem of abnormal SDN switches in the Tactile Internet is analyzed in this article, including the cause of abnormal switches and their influences on different network layers. Then we propose an approach that leverages the messages sent by all switches to identify abnormal switches, which adopts a linear structure to store historical messages at a relatively low cost. By mapping each flow message to the flow establishment model, our method can effectively identify malicious SDN switches in the Tactile Internet and thus enhance its security.

Up-to-date results in data stream analytics are difficult to obtain because the data are in rapid sequence and can be accessed only once. Due to the exactly-once delivery nature of streaming data, online processing is quite unstable. To guarantee comprehensive and accurate results, aggregating historical data is essential when processing streaming data. In this paper, we propose a hash-based hybrid cache model, namely,HCache, for fast data analytics covering real-time streaming data and historical data. TheHCachemodel integrates the online cache and batch cache for hybrid online and batch processing and uses a hash structure to accelerate storage. When executing analytic tasks, the batch cache and online cache are accessed in parallel. Computed streaming data are stored in the online cache, which returns qualified results based on one-time visiting. The most recently visited historical data are stored in the batch cache, and they are also used to correct errors in the online cache. Efficient replacement strategies are used to keep the caches within a relatively stable size. To coordinate the online cache with the batch cache, an LRU-based selection strategy is designed to achieve comprehensive results. Experimental results show that theHCachemodel can quickly and efficiently execute analytic tasks with little additional overhead; moreoverHCacheis more stable and effective at data storage, access and query with less memory utilization than other models.

In this paper, we consider the nonlinear least squares (NLLSs) problems in adaptive networks, where a collection of nodes with adaptation ability by learning are required to estimate a global vector parameter by minimizing the specified convex cost function. Although the global Gauss-Newton (GN) method is an excellent candidate for solving such problems, many challenges need to be addressed for practical realization due to its natures of centralization and noncooperation. Without specialized design for routing, we motivate and propose new diffusion GN methods with cooperative strategy among local neighborhoods. The good performances of diffusion cooperation schemes have been proved in different literatures, such as distribution, robustness, and easy implementation. The proposed cooperative diffusion strategies are named as aggregation-then-update (ATU) and update-then-aggregation (UTA), which reach fully information diffusion across network and consist of two steps in a reversible way including aggregation of local estimates and local GN update. Although all implementations are local, the cooperation between nodes is network wide. Based on the steady-state equilibria theory in the nonlinear discrete dynamical system, the convergence analysis of proposed algorithms is provided. The results show that the global convergence can be achieved when the sufficient conditions are satisfied. We also provide performance comparisons and analysis together with simulation to confirm the applicability and effectiveness of proposed diffusion GN algorithms.

Cyber-physical-social systems (CPSS) are revolutionizing the relationships between humans, computers, and things. Outsourcing computation to the cloud can offer resources-constrained enterprises and consumers sustainable computing in CPSS. However, ensuring the security of data in such an outsourced environment remains a research challenge. Principal eigentensor computation has emerged as a powerful tool dealing with multidimensional cyber-physical-social systems data. In this paper, we present two novel secure principal eigentensor computation (SPEC) schemes for sustainable CPSS. To the best of our knowledge, this is the first effort to address SPEC over encrypted data in the cloud without the interaction need between multiple users and cloud. More specifically, we leverage cloud server and trusted hardware component to design a collaborative cloud model. Using the model, we propose (1) a basic SPEC scheme based on homomorphic computing and (2) an efficient SPEC scheme that combines the advantages of homomorphic computing and garbled circuits, and exploits packing technology to reduce computational cost. Finally, we theoretically and empirically analyze the security and efficiency of our SPEC schemes. Findings demonstrate that the proposed schemes provide a secure and efficient way of outsourcing computation for CPSS. In addition, from the cloud user's perspective, our proposal is lightweight.

Large-scale clusters are often built with over-provisioned service resources, so as to satisfy the huge demand raised by enormous users in cloud environments. By estimating the resource demand of workloads, an on-demand resource provisioning method can be realized in these clusters, thus improving the energy efficiency. However, to guarantee Quality of Service (QoS), the resource demand of workload should be accurately estimated so as to provide suitable resources. Many statistical approaches estimate actual resource demand based on some workload features. But the relations between actual resource demand and workload features are generally obscure, and it's a big challenge to gain an accurate estimation under an obscure relation. In this paper, by considering a cluster as a queueing system, we construct a linearly dependent relation between resource demand and multiple feature combinations. The linearly dependent relation is inconstant due to its variable coefficients. Then, to ascertain specific relations which match actual situations, we design a Basic Linear regression (BL) algorithm. BL can obtain the optimal values for these coefficients, thus determining the inconstant relation to specific ones. Finally, we propose a Constructed Linear regression (CL) approach to estimate actual resource demands. CL forms a two-layer neural network by using several processes of BL as the neurons. To evaluate CL, we realize an On-Demand Resource Provisioning (ODRP) method in a typical power-aware cluster. Several evaluation metrics are proposed for conducting extensive experiments. The experimental results show that CL is effective to make accurate estimations.

Smart city, a focus of many researchers from academia and industry, is a successful example of Cyber-Physical-Social Systems (CPSS). Based on the rapid and efficient processing of large-scale data, Smart city, an example of CPSS, has revolutionized the service provision model by providing proactive services for humans. However, to operationalize the services provided in smart cities, a comprehensive analysis of heterogeneous and large-scale big data is required. Further, to speed up data processing and improve the adaptability and extensibility of big data, CPSS big data processing should be realized in the form of blocks and avoid redundant computing on historical data. In this paper, as an extension of multi-order distributed and incremental High-Order Singular Value Decomposition (HOSVD) computing, Ring-based Tree algorithm and Tree-based Tree algorithm are proposed for the problems of increasing scale of processable data and computational efficiency. The experimental and simulation results demonstrate that the proposed algorithms have high performance in terms of error, improvement factor, and improvement factor ratio. At last, to demonstrate the performance of our improved algorithms, a case study about CPSS big data processing is provided.

Cyber-Physical-Social Systems (CPSS) are the extension of Cyber-Physical Systems (CPS) which integrate social characteristics into Cyber-Physical Systems. The emergence of CPSS provides a promising solution for energy and sustainability challenges, at the same time, CPSS make sustainability computing space change from single space to multi-spaces. To cope with the problem, we propose Cyber-Physical-Social Transition Tensor service framework to provide sustainable services for multi-spaces. To the best of our knowledge, this is the first framework that can support multi-space services at one time. The framework solves various stationary probability distributions arising from the multi-relational data from CPSS, then provides services for multi-spaces based on the probability distributions. In order to solve the stationary probability distributions, we develop a novel iterative algorithm, named Intersect Tensor Power Method (ITPM). Furthermore, we prove the convergence of the iterative algorithm, the existence and uniqueness of the stationary probability distribution. This paper's highlight is the Cyber-Physical-Social Transition Tensor (CPST2) model which leverages multivariate transition tensor to seamlessly integrate massive data from CPSS. A case study of multi-space prediction service illustrates our framework, the accuracy reaches 95 percent with three kinds of humans, two hundred and fifty traffic flow slices, and nineteen time slices.

Three-dimensional (3D) NAND flash memory has been widely adopted in emerging storage systems, ranging from mobile devices to cloud systems, due to its performance benefits and scalability. While 3D flash improves capacity through stacking more cells in the vertical direction, the read disturbance has become a serious reliability concern to develop 3D flash memory in storage devices, especially for read-intensive applications. To address the above challenge, we propose a novel disturbance-aware read redirection scheme (DRR). By exploiting parity-based redundancy and data duplication to regenerate data content, DRR redirects reads from strong disturbed flash blocks to weak ones without any data replication. DRR makes the redirection decision based on the accumulative read disturbance, data redundancy, data duplication, and the current I/O traffic. Results show that DRR provides as much as 24.6% performance improvement in the average read/write response time, and extends the endurance of 3D flash devices by 4.7%.

Non-volatile memory express (NVMe) solid-state drives (SSDs) have been widely adopted in emerging storage systems, which can provide multiple I/O queues and high-speed bus to maximize high data transfer rate. NVMe SSD use streams (also called "Multi-Queue") to store related data in associated locations or for other performance enhancements. The on-board DRAM cache inside NVMe SSDs can efficiently reduce the disk accesses and extend the lifetime of SSDs, thus improving the overall efficiency of the storage systems. However, in previous studies, such SSD cache has been only used as a shared cache for all streams or a statically partitioned cache for each stream, which may seriously degrade the performance-per-stream and underutilize the valuable cache resources.

With the increased density and the technology scaling, flash memory is more vulnerable to noise effects, overwhelmingly lowering the data retention time. The periodic data refresh technique is commonly used to retain the long-term data integrity. However, the frequent refresh requests also introduce the increased access conflict and severe write amplification, leading to sub-optimal performance and lifetime improvement.

As an emerging network paradigm, the Internet of Things (IoT) which consists of a significant number of multifunctional and heterogeneous IoT nodes has attracted dramatic attentions from both academia and industry. With the merits of intelligent capacity, desirable scalability, and high reliability, the IoT recently has been applied for smart ocean applications to provide protection for ocean environment monitoring and surveillance. Aiming to provide coverage service for ocean border environmental surveillance, this article studies the barrier coverage problem which investigates how to select a collection of IoT nodes to obtain an IoT node chain and build barrier paths to detect intruders and trespassers crossing the border region of interest. To overcome the disadvantages in the existing works on barrier coverage, we adopt a novel and widely adopted confident information coverage (CIC) model as the fundamental coverage model and formulate the CIC barrier path construction (CICBC) problem with the goals of maximizing the number of barrier paths and minimizing the amount of IoT nodes in each barrier path. We propose a distributed CIC barrier path (CICBP) construction approach based on learning automata (CBLA). The CBLA includes four crucial phases which are initialization phase, learning phase, monitoring phase, and repairing phase. Each IoT node equips a learning automaton. CBLA selects an optimal IoT node to construct the barrier path by learning. The simulation results show that the performance of the CBLA algorithm outperforms two peer algorithms in terms of the number of barrier paths and the average number of nodes in each barrier path.

Excavating human's temporal and spatial regularities hidden in trajectory data and predicting users' mobility patterns are conducive to providing proactive smart services for people. Combining Markov transition and tensor theories to improve the prediction performance has proved to be effective. However, the existing state-of-the-art multivariate multiorder Markov model neglects the mutual influence among different users. In a practical trajectory system, people's mobility patterns are influenced by their social relationships. Therefore, this article focuses on proposing a novel multiuser multivariate multiorder Markov model and a multimodal user mobility pattern prediction approach. First, we construct two concrete Markov trajectory transition models based on the single-user multivariate multiorder Markov model. Then, we propose a multiuser multivariate multiorder Markov model, including the influence model of multiple users and the multiuser Markov trajectory transition model. Afterward, two unified product-based power methods are developed to calculate the stationary joint eigentensor (SJE) for single-user and multiuser multivariate multiorder Markov models. Furthermore, an SJE-based multimodal prediction approach is proposed to realize precise mobility pattern prediction. Finally, we conduct a series of experiments based on real-world GPS trajectory data set to verify the performance of the proposed approaches. Experimental results demonstrate that the proposed multiuser multivariate multiorder Markov-based multimodal prediction approach can improve the trajectory prediction accuracy by highest up to 31.10% points compared with the Z-eigen-based approach.

With the advent of the 5G era, the Internet of Things (IoT) will flourish in the future. Millions of IoT devices will be connected by 5G networks, which will bring great challenges to network management. Software-defined network (SDN) is a novel solution for managing a large number of IoT devices over the network. In order to solve the problems of secure data analysis in SDN-based IoT, a differentially private tensor computing model (DPTCM) is proposed in this article. Our approach utilizes tensor to model and analyze the SDN-based IoT big data, and an algorithm named differentially private tensor train decomposition (DPTTD) is proposed to achieve secure computing in SDN-based IoT. The algorithm can make full use of the flexible computing power of edge-cloud computing so as to realize collaborative computing between edges, cloud, and the third party. By separating the calculation process of the private data and nonprivate data, the algorithm implements the localized calculation and preservation of the original data which can protect the data security from the source. Meanwhile, we use the differential privacy technology to protect the privacy of data transmitted to the cloud. Finally, we prove that the algorithm satisfies $\varepsilon $ -differential privacy. In the experiments, we verify our model on two real-world data sets. The experimental results show that differential privacy has a little side effect on prediction results, and our model has good performance in data prediction.

Internet of Things (IoT) has become a critical infrastructure in smart city services. Unlike traditional network nodes, most of the current IoT devices are constrained with limited capabilities. Moreover, frequent changes in the network status (e.g., nodes turns into the sleep mode to save battery) make it even more difficult to set up a stable, secure transmission among smart city IoT devices. On the one hand, these weaknesses make the IoT more vulnerable to attacks, such as data eavesdropping, which can monitor, tamper, and obtain the transporting data. On the other hand, the high-confidence smart city service strongly relies on the security of data transporting among the IoT devices, e.g., data being tempered would reduce the reliability of smart city services and data being monitored or stolen would infringe the privacy of smart city services. Toward high-confidence smart city IoT services, we proposed an approach to secure the data transportation among the smart city IoT devices, which combines a k-n secret-sharing mechanism and software-defined networking (SDN) technique to securely transport IoT data. Specifically, the data are transported by multiple routes calculated by the SDN controller adaptively. Data safety is guaranteed by the all-or-nothing feature of the k-n secret-sharing mechanism. Two SDN-based transmission strategies, which leverage the SDN's advantages on network management, and scheduling, are applied to overcome the challenges of the unstable network state in IoT. Extensive experiments conducted from many aspects show that the proposed approach can remarkably reduce the attack success rate with reasonable and acceptable overhead.

Along with the advancement of several emerging computing paradigms and technologies, such as cloud computing, mobile computing, artificial intelligence, and big data, Internet of Things (IoT) technologies have been applied in a variety of fields. In particular, the Internet of Healthcare Things (IoHT) is becoming increasingly important in human activity recognition (HAR) due to the rapid development of wearable and mobile devices. In this article, we focus on the deep-learning-enhanced HAR in IoHT environments. A semisupervised deep learning framework is designed and built for more accurate HAR, which efficiently uses and analyzes the weakly labeled sensor data to train the classifier learning model. To better solve the problem of the inadequately labeled sample, an intelligent autolabeling scheme based on deep Q-network (DQN) is developed with a newly designed distance-based reward rule which can improve the learning efficiency in IoT environments. A multisensor based data fusion mechanism is then developed to seamlessly integrate the on-body sensor data, context sensor data, and personal profile data together, and a long short-term memory (LSTM)-based classification method is proposed to identify fine-grained patterns according to the high-level features contextually extracted from the sequential motion data. Finally, experiments and evaluations are conducted to demonstrate the usefulness and effectiveness of the proposed method using real-world data.

Big service is an extremely important application of service computing to provide predictive and needed services to humans. To operationalize big services, the heterogeneous data collected from Cyber-Physical-Social Systems (CPSS) must be processed efficiently. However, because of the rapid rise in the volume of data, faster and more efficient computational techniques are required. Therefore, in this paper, we propose a multi-order distributed high-order singular value decomposition method (MDHOSVD) with its incremental computational algorithm. To realize the MDHOSVD, a tensor blocks unfolding integration regulation is proposed. This method allows for the efficient analysis of large-scale heterogeneous data in blocks in an incremental fashion. Using simulation and experimental results from real-life, the high-efficiency of the proposed data processing and computational method, is demonstrated. Further, a case study about cyber-physical-social system data processing is illustrated. The proposed MDHOSVD method speeds up data processing, scales with data volume, improves the adaptability and extensibility over data diversity and converts low-level data into actionable knowledge.

Big data feature learning is a crucial issue for the service management for Internet of Things. However, big data collected from Internet of Things is of dynamic nature at a high speed, which poses an important challenge on wireless big data learning models, especially the deep computation model. In this paper, an incremental deep computation model is proposed for wireless big data feature learning in Internet of Things. First, two incremental tensor auto-encoders (ITAE) are developed by devising two incremental learning algorithms, namely parameter-based incremental learning algorithm (PI-TAE) and structure-based incremental learning algorithm (SI-TAE), when new wireless samples are available. PI-TAE only updates the network parameters while SI-TAE simultaneously adjusts the structure and updates the parameters to adapt to the new arriving wireless big data. Furthermore, an incremental deep computation model is constructed by stacking several ITAEs. Experiments are conducted to evaluate the performance of the proposed model by comparing with the conventional deep computation model and other two representative incremental learning algorithms, i.e., OANN and PIE. Results demonstrate that the presented model can modify the network in an incremental manner for new arriving data learning efficiently with preserving the prior knowledge for the previous data learning, proving its potential for dynamic wireless big data learning in Internet of Things.

With the rapid development of the Internet, cloud storage has penetrated into every aspect of human society. However, cloud data disclosure happens more and more frequently, which makes cloud data security and privacy protection impact wide adoption of cloud storage. Control cloud data access based on reputation by introducing a Reputation Center (RC) was proposed and demonstrated to secure cloud data effectively in [9] . But the acceptance of such a system by cloud users and Cloud Service Providers (CSPs) is crucial for its practical deployment and final success. In this paper, we investigate the acceptance of a cloud data access control system based on reputation using Game Theory. Due to the existence of dishonest CSPs, there exists a social reputation dilemma among CSPs, which seriously impedes the popularity of cloud storage. To encourage users to use cloud storage and suppress collusion between CSPs and data requesters, a repeated public-goods game is built up by applying a compensation mechanism to improve the utilities of cloud users and a punishment mechanism based on reputation to incent honest behaviors. Theoretical analysis and simulation results show the effectiveness of the compensation and punishment mechanisms to increase cloud storage rate and restrain dishonest system entities.

A tremendous challenge in the development of Cyber-Physical-Social Systems (CPSS) is to integrate the growing volume and wide variety of data generated from multiple sources. To address the challenge, this paper presents an integration framework on cloud consisting of five functionally complementary processes, namely data representation, dimensionality reduction, relation establishment, data rank and data retrieval. The unstructured, semi-structured and structured data in the cyber, physical and social space are first represented as low-order data tensors, and then transformed to a three-order feature tensor for relation establishment. A similarity-based multi-linear data rank approach is proposed to measure the importance of the CPSS big data, and an incremental method is explored to rapidly and accurately update the rank vector. This paper, through a smart home case study, illustrates a practical application of the proposed integration framework, and evaluates the performance of the multi-linear data rank approach as well as the incremental rank update method. The results reveal that the proposed framework is feasible and competitive to integrate the CPSS big data on cloud.

Motivated by complementing the ubiquitous wireless sensor networks (WSNs) and powerful cloud computing (CC), a lot of attention from both industry and academia has been drawn to Sensor-Cloud (SC). However, SC pricing is barely investigated. Towards pricing for SC, this paper 1) introduces five SC Pricing Models (SCPMs) first. Specifically, to charge a SC user, each SCPM considers one of the following factors respectively: i) the lease period of the SC user; ii) the required working time of SC; iii) the SC resources utilized by the SC user; iv) the volume of sensory data obtained by the SC user; v) the SC path that transmits sensory data from the WSN to the SC user. Further, this paper 2) performs analysis to discuss and exhibit the characteristics of the proposed SCPMs. With that, this paper 3) presents the case studies regarding the application of SCPMs. Eventually, this paper 4) conducts a review about the user behavior study. This paper aims to serve as a very favorable guidance for future research about pricing in SC.

The Internet of Things (IoT) is becoming a backbone of sensing infrastructure to several mission-critical applications such as smart health, disaster management, and smart cities. Due to resource-constrained sensing devices, IoT infrastructures use Edge datacenters (EDCs) for real-time data processing. EDCs can be either static or mobile in nature, and this article considers both of these scenarios. Generally, EDCs communicate with IoT devices in emergency scenarios to evaluate data in real-time. Protecting data communications from malicious activity becomes a key factor, as all the communication flows through insecure channels. In such infrastructures, it is a challenging task for EDCs to ensure the trustworthiness of the data for emergency evaluations. The current communication security pattern of “communication before authentication” leaves a “black hole” for intruders to become part of communication processes without authentication. To overcome this issue and to develop security infrastructures for IoT and distributed Edge datacenters, this article proposes a user-centric security solution. The proposed security solution shifts from a network-centric approach to a user-centric security approach by authenticating users and devices before communication is established. A trusted controller is initialized to authenticate and establishes the secure channel between the devices before they start communication between themselves. The centralized controller draws a perimeter for secure communications within the boundary. Theoretical analysis and experimental evaluation of the proposed security model show that it not only secures the communication infrastructure but also improves the overall network performance.

With the rapid development and proliferation of multimedia systems and applications, there is a growing need to handle multimedia heterogeneous data safely and efficiently on the cloud. Tensor models are effective in representing multimedia multidimensional data, and the tensor decomposition is one of the basic building blocks of data analysis and learning models. In this article, we propose a secure tensor singular value decomposition (${S}$-tSVD), in which the time-domain operation is converted into a scheme featuring frequency-domain multilinear circular unfolding–folding. First, we represent various multimedia data as cipher subtensors, using fully homomorphic encryption. We then take the fast Fourier transform (FFT) approach to launch a new multiplication operation along the tubal fibers of a unified high-order tensor. Second, relying on the homomorphism of addition and multiplication theory, we prove the fully homomorphic consistency of the proposed${S}$-tSVD algorithm. Third, we provide an elegant solution to tackle the typical dimensionality inconsistency problem while working with multiple subtensors. Finally, we carry out theoretical analyses with respect to dimensionality reduction, reconstruction error of${S}$-tSVD, running time, and data security. We use real unstructured video data and semistructured XML documents, integrating them within a unified tensor model for decomposition. We demonstrate that the error ratio of the${S}$-tSVD is lower than the same compression ratio compared to the SVD decomposition and tSVD-slice approaches. Moreover, the specific${S}$-tSVD decomposition not only enables effective data mining and dimensionality reduction but also ensures the accuracy of the decomposition result and data privacy protection.

Tensor-based big data analysis approaches are effectively exploited to handle multisource and heterogeneous cyber-physical-social big data generated from diverse spaces. However, the curse of dimensionality seriously restricts their widespread exploitation, especially under edge/fog computing environments. To alleviate the dilemma, we attempt to present a set of tensor-train (TT)-based tensor operations with their scalable computations and then propose a novel TT-based big data processing framework under edge/fog computing environments. Specifically, in this article, we first summarize and present a set of TT-based tensor operations by converting the original high-order tensor operation to a series of low-order (second- or third-order) TTcore-based operations. Then, we propose a two-layer scalable TT-based computation architecture, including inter-TTcore and intra-TTcore scalable models. Afterward, according to various scalable models, a series of scalable TT-based tensor computations (STT-TCs) with their complexity analysis are proposed in detail. Finally, we propose a novel TT-based big data processing framework to adapt to edge/fog computing environments. We conduct extensive experiments based on both random data sets and real-world ubiquitous bus traffic data sets. Experimental results demonstrate that the proposed STT-TCs can significantly improve computation efficiency and are suitable for edge/fog computing environments.

Tensors are popular and versatile tools which model multidimensional data. Tensor decomposition has emerged as a powerful technique dealing with multidimensional data. With the booming development of cloud computing, a large number of users are inclined to outsource big data storage and computations to the cloud. However, because of the rise of various privacy concerns, sensitive data usually need to be encrypted prior to being outsourced to a cloud. Computations over encrypted data in the cloud without compromising the privacy of data is still a challenge. This paper presents a novel privacy-preserving tensor decomposition approach over semantically secure encrypted big data. The proposed approach leverages properties of homomorphic encryption and employs a federated cloud to securely decompose an encrypted tensor for multiple users, without the clouds learning any knowledge about users' data. This is, to our knowledge, the first attempt to solve privacy-preserving tensor decomposition without requiring interaction between users and cloud service providers. In addition, in our approach, we present the first secure integer division and integer square root schemes over encrypted data (the dividend, divisor and radicand are in encrypted format). Finally, we prove the security of our approach under semi-trusted model and empirically analyze its effectiveness, which demonstrates the utility of our proposed approach in cloud deployments.

Heterogeneous multicore processors have recently become de facto computing engines for state-of-the-art embedded applications. Nonetheless, very little research focuses on the scheduling of periodic (implicit-deadline) real-time tasks upon heterogeneous multicores under the requirements of task synchronization, which is stemmed from resource access conflicts and can greatly affect the schedulability of tasks. In view of partitioned Earliest Deadline First and Multiprocessor Stack Resource Policy, we first discuss the blocking-aware utilization bound for uniform heterogeneous multicores and then illustrate its non-monotonicity, where the bound may decrease with more deployed cores. Following the insights obtained from the bound analysis, taking the system heterogeneity into consideration, we propose a Synchronization-Aware Task Partitioning Algorithm for Heterogeneous Multicores (SA-TPA-HM)). Several resource-guided and heterogeneity-oriented mapping heuristics are incorporated to reduce the negative impacts of blocking interferences for better schedulability performance of tasks and balanced workload distribution across cores. The extensive simulation results show that SA-TPA-HM can obtain the schedulability ratios approximate to an Integer Non-Linear Programming--based solution, and much higher (e.g., 60% more) in contrast to the existing partitioning algorithms targeted at homogeneous multicores. The measurement results in Linux kernel further reveal the practical viability of SA-TPA-HM that can experience lower runtime overhead (e.g., 15% less) when compared to other mapping schemes.

In this article, a high-order possibilistic c-means algorithm (HOPCM) based on the double-layer deep computation model (DCM) is proposed for big data clustering. Specifically, an asymmetric tensor autoencoder is presented to efficiently train the double-layer DCM for big data feature learning. Furthermore, an edge-cloud computing system is developed to improve the clustering efficiency. In the edge-cloud system, the computation-intensive tasks including the parameters' training and clustering are offloaded to the cloud while the task of feature learning is performed at the edge of network. Finally, we conduct extensive experiments to evaluate the performance of the presented algorithm by comparing it with other two representative big data clustering algorithms, i.e., the standard HOPCM and the HOPCM based on deep learning. Results demonstrate that the presented algorithm achieves higher accuracy than the two compared algorithms and furthermore the clustering efficiency are significantly improved by the developed edge-cloud computing system.

Energy efficiency and autonomous power management are extremely important for mobile-edge computing. Reducing energy consumption of a number of applications running concurrently in mobile devices while maintaining performance poses a challenge to energy optimization due to the limited capacity of the embedded battery. To extend battery life and offer a long-lasting working energy, dynamic voltage and frequency scaling (DVFS) has been widely used in mobile devices for energy consumption minimization. However, most conventional DVFS techniques scale operating frequency based on static policies, and thus, they are difficult to be adapted to systems of varied conditions. In order to improve adaptivity, in this article, we proposed a Double-Q power management approach to scale operating frequency based on learning. The Double-Q method stores two Q tables and two corresponding update functions. In each decision point, either of Q tables is randomly chosen and updated, while the other is used for the measurement. This mechanism reduces the overestimation in Q values, consequently enhancing the accurateness of frequency predictions. To evaluate the effectiveness of our proposed approach, a Double-Q governor is implemented in the Linux kernel. Our approach is computationally light, and experimental results indicate that it achieves at least 5-18% total energy saving compared to on-demand and conservative governors, as well as Q learning-based method.

Software-defined networking (SDN) provides an efficient way of managing traffic load by shifting complex and rigid computing tasks to the centralized controller. It reduces the burden on the switches, task of which is to perform the routing based upon the rule-action pair. However, the flow table storage capacity of switches is limited. It may have to face performance bottlenecks, which, in turn, can cause serious security breaches and performance degradation. Hence, in this article, BloomStore, which is a dynamic bloom-filter-based secure rule-space management scheme in SDN, is proposed. BloomStore handles the data traffic dynamically by managing network resources. A twofold security check is used for secure data transfer using double hashing, i.e., two independent hash functions are used to generate k hash functions. Moreover, partitioned hashing is proposed to have insertion and query in a bucket of bloom array. The result analysis demonstrates that BloomStore outperforms its competing variants with respect to various performance parameters.

For the industrial Internet of Things (IIoT), public-key encryption with keyword search (PEKS) is a type of applicable and promising encryption technique to maintain the data stored in clouds secure and searchable. To further improve the efficiency of searching, it is popular to introduce edge computing near the IIoT as the substitute for a cloud. However, the straightforward collaboration of the two techniques performs negatively in latency-sensitive applications since the sluggish encryption of PEKS by IIoT devices negates the instant reaction of edges. To meet this challenge, in this article, we exploit the capability of the edge-cloud architecture and propose a lightweight-designed scheme called edge-aided searchable public-key encryption (ESPE). It allows IIoT devices to delegate their costly cryptographic operations to the nearby edge for fast computing and guarantees that all outsourced ciphertexts are semantically secure. Consequently, ESPE accelerates the corresponding ciphertext procedures on edges and saves over 70% encryption cost of an IIoT device.

The integration of the fifth generation (5G) networks and artificial intelligence (AI) benefits to create a more holistic and better connected ecosystem for industries. User profiling has become an important issue for industries to improve company profit. In the 5G era, smartphone applications have become an indispensable part in our everyday lives. Users determine what apps to install based on their personal needs, interests, and tastes, which is likely shaped by their genders-the behavioral, cultural, or psychological traits typically associated with their sex. It is possible to profile users' gender based simply on a single snapshot of apps installed on their smartphones. With this inference based on easy to access data, we can make smartphone systems more user-friendly, and provide better personalized products and services. In this article, we explore such possibilities through an empirical study on a large-scale dataset of installed app lists from 15 000 Android users. More specifically, we investigate the following research questions: 1) What differences between females and males can be explored from installed app lists? 2) Can user gender be reliably inferred from a snapshot of apps installed? Which snapshot feature(s) are the most predictive? What is the best combination of features for building the gender prediction model? 3) What are the limitations of a gender prediction model based solely on a snapshot of apps installed on a smartphone? We find significant gender differences in app type, function, and icon design. We then extract the corresponding features from a snapshot of apps installed to infer the gender of each user. We assess the gender predictive ability of individual features and combinations of different features. We achieve an accuracy of 76.62% and area under the curve of 84.23% with the best set of features, outperforming the existing work by around 5% and 10%, respectively. Finally, we perform an error analysis on misclassified users and discussed the implications and limitations of this article.

Product quality prediction, as an important issue of industrial intelligence, is a typical task of industrial process analysis, in which product quality will be evaluated and improved as feedback for industrial process adjustment. Data-driven methods, with predictive model to analyze various industrial data, have been received considerable attention in recent years. However, to get an accurate prediction, it is an essential issue to extract quality features from industrial data, including several variables generated from supply chain and time-variant machining process. In this article, a data-driven method based on wide-deep-sequence (WDS) model is proposed to provide a reliable quality prediction for industrial process with different types of industrial data. To process industrial data of high redundancy, in this article, data reduction is first conducted on different variables by different techniques. Also, an improved wide-deep (WD) model is proposed to extract quality features from key time-invariant variables. Meanwhile, an long short-term memory (LSTM)-based sequence model is presented for exploring quality information from time-domain features. Under the joint training strategy, these models will be combined and optimized by a designed penalty mechanism for unreliable predictions, especially on reduction of defective products. Finally, experiments on a real-world manufacturing process data set are carried out to present the effectiveness of the proposed method in product quality prediction.

Cloud computing offers various services based on outsourced data by utilizing its huge volume of resources and great computation capability. However, it also makes users lose full control over their data. To avoid the leakage of user data privacy, encrypted data are preferred to be uploaded and stored in the cloud, which unfortunately complicates data analysis and access control. In particular, few existing works consider the fine-grained access control over the computational results from ciphertexts. Though our previous work proposed a framework to support several basic computations (such as addition, multiplication and comparison) with flexible access control, privacy-preserving division calculations over encrypted data, as a crucial operation in many statistical processes and machine learning algorithms, is neglected. In this paper, we propose four privacy-preserving division computation schemes with flexible access control to fill this gap, which can adapt to various application scenarios. Furthermore, we extend a division scheme over encrypted integers to support privacy-preserving division over multiple data types including fixed-point numbers and fractional numbers. Finally, we give their security proof and show their efficiency and superiority through comprehensive simulations and comparisons with existing work.

The improvement of coverage quality in the construction of multiple-barrier coverage is a critical problem in a wireless sensor network. In this article, we investigate the K -barrier coverage construction problem in passive bistatic radar sensor networks. In contrast to traditional bistatic radar networks, the transmitters in a passive bistatic radar network are predeployed and noncooperative. To construct K barriers, we need to deploy receivers that couple with predeployed transmitters to build continuous barriers. In this work, we focus on the minimum number of receivers problem of constructing K -barrier coverage, where the minimum number of receivers is based on the predeployed transmitters. To handle this problem, we first investigate the optimal placement of receivers between adjacent transmitters for a sub-barrier formation and then determine the optimal placement of receivers for the one-barrier construction. For multiple-barrier coverage construction, we introduce a weighted transmitter graph (WTG) to describe the relation among different transmitters, where the weight in the graph is the minimum number of receivers needed for these two transmitters for a sub-barrier formation. Based on WTG, the minimum receivers problem changes to a problem of how to find K -disjoint paths with the minimum total weight in the graph. For large-scale networks, we also propose two efficient heuristic algorithms to solve the corresponding problem. Finally, we conduct extensive experiments to validate the correctness and the efficiency of the proposed algorithms.

The significant growth of the Internet of Things (IoT) takes a key and active role in healthcare, smart homes, smart manufacturing, and wearable gadgets. Due to complexness and difficulty in processing multimedia data, the IoT based scheme, namely Internet of Multimedia Things (IoMT) exists that is specialized for services and applications based on multimedia data. However, IoMT generated data are facing major processing and privacy issues. Therefore, tensor-based deep computation models proved a better platform to process IoMT generated data. A differentially private deep computation method working in the tensor space can attest to its efficacy for IoMT. Nevertheless, the deep computation model comprises a multitude of parameters; thus, it requires large units of memory and expensive computing units with higher performance levels, which hinders its performance for IoMT. Motivated by this, therefore, the paper proposes a deep private tensor train autoencoder (dPTTAE) technique to deal with IoMT generated data. Notably, the compression of weight tensors to manageable tensor train format is achieved through Tensor Train (TT) network. Moreover, TT format parameters are trained through higher-order back-propagation and gradient descent. We applied dPTTAE on three representative datasets. Comprehensive experimental evaluations and theoretical analysis show that dPTTAE enhances training time efficiency, and greatly improve memory utilization efficiency, attesting its potential for IoMT.

Modern cloud computing platforms based on virtual machine monitors (VMMs) host a variety of complex businesses which present many network security vulnerabilities. In order to protect network security for these businesses in cloud computing, nowadays, a number of middleboxes are deployed at front-end of cloud computing or parts of middleboxes are deployed in cloud computing. However, the former is leading to high cost and management complexity, and also lacking of network security protection between virtual machines while the latter does not effectively prevent network attacks from external traffic. To address the above-mentioned challenges, we introduce a novel customized network security for cloud service (CNS), which not only prevents attacks from external and internal traffic to ensure network security of services in cloud computing, but also affords customized network security service for cloud users. CNS is implemented by modifying the Xen hypervisor and proved by various experiments which showing the proposed solution can be directly applied to the extensive practical promotion in cloud computing.

With the development of GPS technology, a new Mobile Internet of Things (M-IoT) is emerging, which perceives the city's rhythm and pulse day and night to collect a large scale of city data. It is urgent to innovate M-IoT service system for these large-scale and heterogeneous data. To cope with the problem, this article proposes a Mobile-IoT based multi-modal reinforcement learning service framework from data perspective, which has three highlights, i) Developing Action-aware High-order Transition Tensor (AHTT) to fuse the heterogeneous data from M-IoTs in a unified form. ii) Developing Multi-modal Markov Decision Process (MMDP) to model the multi-modal reinforcement learning for M-IoT service framework. iii) Developing Tensor Policy Iteration algorithm (TPIA) to solve the optimal tensor policy. Due to using tensor keeps the multi-modal relations of the context information in the process of solving the optimal policy. The proposed M-IoT service system provides more personalized service for taxi drivers. The experiment results shows that most taxi drivers earn more revenue according to the tensor policy.

Blockchain, as an emerging decentralized architecture and distributed computing paradigm underlying Bitcoin and other cryptocurrencies, has attracted intensive attention in both research and applications recently. Blockchain, especially powered by chain-coded smart contracts, has the full potential of revolutionizing increasingly centralized cyber-physical-social systems (CPSSs) for constructions and applications, and reshaping traditional knowledge automation workflows. The key advantage of blockchain technology lies in the fact that it can enable the establishment of secured, trusted, and decentralized autonomous ecosystems for various scenarios, especially for better usage of the legacy devices, infrastructure, and resources.

Secure cyber-physical-social big data computations are being increasingly used to protect the users' data security in cyber-physical-social systems (CPSS). Despite the increasing popularity, how to process the tasks of the secure cyber-physical-social big data computations, while taking care of the energy consumption and meeting the users' requirements, remains challenging. To address the problem, in this work, we propose a novel tensor-based optimization model for the secure sustainable cyber-physical-social big data computations. The proposed model is a general and fine-grained model, which can jointly optimize the execution time, energy consumption, reliability, and quality of experience, and can comprehensively take into account step, task, time slot, type, node, core, cryptosystem, and security level. To our knowledge, this is the first study to holistically optimize the tasks in the secure cyber-physical-social big data computations. To illustrate the proposed model, the case study of the secure high-order Lanczos in cloud-assisted CPSS is presented. Finally, the proposed model is empirically evaluated by using multi-objective optimization, and the extensive results demonstrate that from the users' perspective our proposed tensor-based optimization model is preferable for the secure sustainable cyber-physical-social big data computations.

Online education and e-learning have vigorously sprung up and produced massive educational data in a streaming way. It is very challenging to acquire the appropriate learning resources and the suitable learning partners from the streaming-updated educational big data. This article aims to provide sustainable smart educational services including precise personalized recommendation and adaptive clustering under different contexts by correlatively analyzing the global educational data from multiple dimensions via incremental tensor decomposition. First, a tensor-based recommendation and service framework for the streaming educational big data is developed. Then three local tensors concerning learners, resources, and learning records are constructed and further fused to an integrated global learner-resource tensor. Afterward, we present an incremental tensor-based correlative analysis and personalized recommendation (ITCA-PR) algorithm to recommend appropriate resources under various contexts. Besides, we also propose an incremental tensor-based adaptive clustering and community recommendation (ITAC-CR) algorithm to recommend suitable learning partners under various contexts and accordingly construct adaptive learning communities. Extensive experimental results demonstrate that the ITCA-PR algorithm outperforms state-of-the-art improved collaborative filtering algorithms by F-score measurement and the ITAC-CR algorithm has a better clustering performance by DVI measurement. These precise educational services will promote the development of sustainable smart education.

Abstract Internet of Things (IoT), as a typical representation of cyberization, enables the interconnection of physical things and the Internet, which provides intelligent and advanced services for industrial production and human lives. However, it also brings new challenges to IoT applications due to heterogeneity, complexity and dynamic nature of IoT. Especially, it is difficult to determine the sources of specified data, which is vulnerable to inserted attacks raised by different parties during data transmission and processing. In order to solve these issues, data provenance is introduced, which records data origins and the history of data generation and processing, thus possible to track the sources and reasons of any problems. Though some related researches have been proposed, the literature still lacks a comprehensive survey on data provenance in IoT. In this paper, we first propose a number of design requirements of data provenance in IoT by analyzing the features of IoT data and applications. Then, we provide a deep-insight review on existing schemes of IoT data provenance and employ the requirements to discuss their pros and cons. Finally, we summarize a number of open issues to direct future research.

On heterogeneous cluster systems, the convergence performances of neural network models are greatly troubled by the different performances of machines. In this paper, we propose a novel distributed Stochastic Gradient Descent (SGD) algorithm named Grouping-SGD for distributed deep learning, which converges faster than Sync-SGD, Async-SGD, and Stale-SGD. In Grouping-SGD, machines are partitioned into multiple groups, ensuring that machines in the same group have similar performances. Machines in the same group update the models synchronously, while different groups update the models asynchronously. To improve the performance of Grouping-SGD further, the parameter servers are arranged from fast to slow, and they are responsible for updating the model parameters from the lower layer to the higher layer respectively. The experimental results indicate that Grouping-SGD can achieve 1.2~3.7 times speedups using popular image classification benchmarks: MNIST, Cifar10, Cifar100, and ImageNet, compared to Sync-SGD, Async-SGD, and Stale-SGD.

The ever-growing Industrial Internet of Things (IoT) provides a powerful method to sense a series of critical industrial environments. This paper studies how to deploy the fixed number of IoT nodes so that the network lifetime is maximized in a sensing field with obstacles while guaranteeing the requirements of confident information coverage, network connectivity, energy efficiency, fault tolerance, and reliability. An IoT node deployment scheme based on an improved nature-inspired genetic algorithm is proposed to solve the defined constrained optimization problem. In the proposed IoT node deployment scheme, we utilize a population initialization based on the Delaunay triangulation to generate the better initial population, a chromosome modification operation to achieve both connectivity and coverage for each chromosome and a chromosome mirror-crossover operation to produce the better offsprings. Experimental results show that our deployment schema equips better performance in terms of longer network lifetime and comparable coverage ratio compared with the other four peer algorithms.

The promising Internet of Things (IoT) provides a powerful platform for practical smart applications. The limited resources of the IoT nodes as well as the emerged coverage holes pose a great challenge on the quality of service of the IoT. Mobile edge computing (MEC), which can improve the IoT nodes energy consumption efficiency and optimize the utilization effectiveness of the limited resources, provides a novel view for coping with the challenge. Based on the MEC, this paper focuses on how to solve the problem of dispatch of mobile edge nodes for confident information coverage holes repairing (DMEN-CICHR) with the goal of maximizing the network lifetime and guaranteeing the network connectivity. To deal with the DMEN-CICHR problem, we develop an energy-balanced and obstacle-adaptive mobile edge node dispatch algorithm called EBOADMEN-CICHR, which restricts the mobile edge nodes from moving too long distance by setting a bound for each CIC hole and repeatedly updating the bound by a competition mechanism. To guarantee the network connectivity, the EBOADMEN-CICHR recursively performs breadth first search on a constructed undirected graph to find all disconnected subgraphs and then dispatches some mobile edge nodes to connect those disconnected subgraphs until the whole network is connected. A number of experiments emulating the realistic scenarios in radiological pollution monitoring in uranium tailings are executed to verify the effectiveness of the proposed EBOADMEN-CICHR solution. Experimental results show the EBOADMEN-CICHR can perform better than other peer methods in term of higher energy efficiency and longer network lifetime.

The sybil attack in Internet of Things (IoT) commonly aims the sensing domain that may impose serious threat to the devices both in perception and communication layer. The singularity of the sybil attack is a sybil node that publish multiple identities of legitimate devices. It is highly essential to learn the behavior and predict possible actions of a sybil attacker while devising a defense mechanism for it. This paper provides a comprehensive characteristic analysis of sybil attack in IoT. Based on the nature of the task performed during this attack, it is classified into three phases as compromise, deployment, and launching phase. The compromise phase is modeled as an automaton with attacker state transition as a Markov chain model. A heuristic is also proposed for selection criteria of an attacker to compromise a node. In the deployment phase of the attack, an algorithm based on K -mean clustering is proposed to group compromised identities and deploy the sybil node for corresponding identities without violating the set of adjacent nodes. In the launching phase, the process of replacing sybil identities either over time or on detection is modeled using age replacement policy. The results depict that the proposed model effectively visualize the behavior of a sybil attacker in challenging environments of IoT.

The promising Industrial Internet of Things (IIoT) consisting of heterogeneous resource-restricted IoT nodes recently has attracted great attention from both academia and industry communities. However, the battery-powered, computing and communication resource-constrained, and randomly uneven distributed features of the IoT nodes pose several great tough hurdles, including the quality of services of real-time processing, energy efficiency, network lifetime, and coverage holes to the IIoT-based industrial applications. To deal with these challenges, based on the emerging edge computing paradigm and the novel confident information coverage (CIC) model, this paper investigates how to relocate redundant IoT edge nodes to provide timely CIC service in an offloading-assisted energy-balanced manner while extending the network lifetime, which is called as the CIC-based IoT edge node relocation (CICENR) problem. To effectively handle the CICENR problem, we propose an offloading-assisted energy-balanced IoT edge node relocation approach CIC-based offloading-assisted energy-balanced approach (CIC-OAEBA) and the other CIC-based direct replacement approach. Specially, the CIC-OAEBA adopts the Grid-Quorum strategy to quickly detect the redundant IoT edge nodes by offloading the communication-intensive and computing-intensive tasks from grid header nodes to peer IoT edge nodes, and make full use of the cascaded movement strategy to move the nearest redundant IoT edge nodes to the requesting CIC hole locations. Experimental results indicate the proposed approaches remarkably outperform other peer methods in terms of response time, energy efficiency, and especially the network lifetime and coverage performance.

Singular value decomposition (SVD) has been applied to cyber security and cyber forensics since it can reduce data. However, SVD is hard to reduce high-order big data because it is designed for only matrix data initially. Reducing high-order big data is desired for cyber security applications, and is a very challenging issue. In this paper, we propose a novel orthogonal tensor SVD method using big data techniques for high-order big data (naturally represented as tensors) reduction, which can be extensively used in big data applications of cyber security and cyber forensics. More specifically, we first present a high-order lanczos-based orthogonal tensor SVD algorithm to reduce high-order data. Then, for utilizing the incomparable benefits of cloud, we develop a secure orthogonal tensor SVD method to outsource the computation task of the orthogonal tensor SVD algorithm to cloud. The secure orthogonal tensor SVD method can protect data security from untrusted cloud by applying garbled circuits to the orthogonal tensor SVD algorithm. This is, to our best knowledge, the first work to address high-order big data reduction by employing cloud computing. Finally, we analyze the security and efficiency of our proposed orthogonal tensor SVD on synthetic dataset and real network intrusion detection dataset, and the results demonstrate that our proposed method is very promising for big data reduction.

The exponential growth of big data places a great burden on current computing environment. However, there exists a vast gap in the approaches that can securely and efficiently process the large scale heterogeneous data. This paper, on the basis of transparent computing paradigm, presents a unified approach that coordinates the transparent servers and transparent clients to decompose tensor, a mathematical model widely used in data intensive applications, to a core tensor multiplied with a number of truncated orthogonal bases. The structured, semi-structured as well as structured data are transformed to low-order sub-tensors, which are then encrypted using the Paillier homomorphic encryption scheme on the transparent clients. The cipher sub-tensors are transported to the transparent servers for carrying out the integration and decomposition operations. Three secure decomposition algorithms, namely secure bidiagonalization algorithm, secure singular value decomposition algorithm, and secure mode product algorithm, are presented to generate the bidiagonal matrices, truncated orthogonal bases, and core tensor respectively. The homomorphic operations of the three algorithms are carried out on the transparent servers, while the non-homomorphic operations, namely division and square root, are performed on the transparent clients. Experimental results indicate that the proposed method is promising for secure tensor decomposition for big data.

Quality of cloud service (QoS) is one of the crucial factors for the success of cloud providers in mobile cloud computing. Context-awareness is a popular method for automatic awareness of the mobile environment and choosing the most suitable cloud provider. Lack of context information may harm the users' confidence in the application rendering it useless. Thus, mobile devices need to be constantly aware of the environment and to test the performance of each cloud provider, which is inefficient and wastes energy. Crowdsourcing is a considerable technology to discover and select cloud services in order to provide intelligent, efficient, and stable discovering of services for mobile users based on group choice. This article introduces a crowdsourcing-based QoS supported mobile cloud service framework that fulfills mobile users' satisfaction by sensing their context information and providing appropriate services to each of the users. Based on user's activity context, social context, service context, and device context, our framework dynamically adapts cloud service for the requests in different kinds of scenarios. The context-awareness based management approach efficiency achieves a reliable cloud service supported platform to supply the Quality of Service on mobile device.

Pervasive Social Networking (PSN) intends to support instant social activities in a pervasive way at any time and anywhere. In order to protect crucial social activities, ensure communication dependability, and enhance user privacy, securing pervasive social communications becomes especially important. However, neither centralized nor distributed solutions can protect PSN communications as expected. How to automatically control data access in a trustworthy and efficient way is an important security issue. In this article, we propose a scheme to guarantee communication data security in PSN based on two dimensions of trust in a flexible manner on the basis of Key-Policy Attribute-Based Encryption (KP-ABE). Its advantages and performance are justified and evaluated through extensive analysis on security, computation complexity, communication cost, scalability, and flexibility, as well as scheme implementation. In addition, we develop a demo system based on Android mobile devices to test our scheme in practice. The results demonstrate its efficiency and effectiveness. Comparison with our previous work based on CP-ABE (Yan and Wang 2017) further shows its feasibility to be applied to PSN.

C yber- P hysical- S ocial S ystems (CPSS) integrating the cyber, physical, and social worlds is a key technology to provide proactive and personalized services for humans. In this paper, we studied CPSS by taking h uman- i nteraction-aware b ig d ata (HIBD) as the starting point. However, the HIBD collected from all aspects of our daily lives are of high-order and large-scale, which bring ever-increasing challenges for their cleaning, integration, processing, and interpretation. Therefore, new strategies for representing and processing of HIBD become increasingly important in the provision of CPSS services. As an emerging technique, tensor is proving to be a suitable and promising representation and processing tool of HIBD. In particular, tensor networks, as a significant tensor decomposition technique, bring advantages of computing, storage, and applications of HIBD. Furthermore, T ensor- T rain (TT), a type of tensor network, is particularly well suited for representing and processing high-order data by decomposing a high-order tensor into a series of low-order tensors. However, at present, there is still need for an efficient Tensor-Train decomposition method for massive data. Therefore, for larger-scale HIBD, a highly-efficient computational method of Tensor-Train is required. In this paper, a d istributed T ensor- T rain (DTT) decomposition method is proposed to process the high-order and large-scale HIBD. The high performance of the proposed DTT such as the execution time is demonstrated with a case study on a typical form of CPSS data, C omputed T omography (CT) image data.

With the ongoing development of sensor devices and network techniques, big data are being generated from the cyber-physical systems. Because of sensor equipment occasional failure and network transmission unreliability, a large number of low-quality data, such as noisy data and incomplete data, is collected from the cyber-physical systems. Low-quality data pose a remarkable challenge on deep learning models for big data feature learning. As a novel deep learning model, the deep computation model achieves superior performance for big data feature learning. However, it is difficult for the deep computation model to learn dependable features for low-quality data, since it uses the nonlinear function as the encoder. In this article, a dependable deep computation model is proposed for feature learning on low-quality big data in cyber-physical systems. Specially, a regularity is added into the objective function of the deep computation model to obtain reliable features in the intermediate-level representation space. Furthermore, a learning algorithm based on the back-propagation strategy is devised to train the parameters of the proposed model. Finally, experiments are conducted on three representative datasets and a real dataset to evaluate the effectiveness of the dependable deep computation model for low-quality big data feature learning. Results show that the proposed model achieves a remarkable result for the tasks of classification, restoration, and prediction, proving the potential of this work for practical applications in cyber-physical systems.

High efficiency video coding (HEVC), which is the newest video coding standard currently, achieves the best coding efficiency compared with all the other existing video coding standards. However, the computational complexity of the typical HEVC encoder dramatically increases because of the recursive searching scheme for finding the best coding unit (CU) partitions. In this paper, an adaptive fast CU size decision algorithm for HEVC Intra prediction is proposed based on CU complexity classification (CC) by using machine learning (ML) technology. Firstly, certain image features are extracted to characterize the CU complexity, which has a strong relationship with CU partitions, and then, the support vector machine is employed to analyze and construct the classification model according to the CU complexity. Finally, the proposed adaptive fast CU size decision algorithm, named as CCML, is released based on the complexity classification. The experimental results show that the proposed algorithm could achieve around 60% encoding time reduction for various test video sequences on average with only 1.26% Bjontegaard delta bit rate increase compared with the reference test model HM15.0 of HEVC.

Today search engines are tightly coupled with social networks, and present users with a double-edged sword: they are able to acquire information interesting to users but are also capable of spreading viruses introduced by hackers. It is challenging to characterize how a search engine spreads viruses, since the search engine serves as a virtual virus pool and creates propagation paths over the underlying network structure. In this paper, we quantitatively analyze virus propagation effects and the stability of the virus propagation process in the presence of a search engine. First, although social networks have a community structure that impedes virus propagation, we find that a search engine generates a propagation wormhole. Second, we propose an epidemic feedback model and quantitatively analyze propagation effects based on a model employing four metrics: infection density, the propagation wormhole effect, the epidemic threshold, and the basic reproduction number. Third, we verify our analyses on four real-world data sets and two simulated data sets. Moreover, we prove that the proposed model has the property of partial stability. Evaluation results show that, compared the cases without a search engine, virus propagation with the search engine has a higher infection density, shorter network diameter, greater propagation velocity, lower epidemic threshold, and larger basic reproduction number.

Radio frequency identification (RFID) systems, as one of the key components in the Internet of Things (IoT), have attracted much attention in the domains of industry and academia. In practice, the performance of RFID systems rather relies on the effectiveness and efficiency of anti-collision algorithms. A large body of studies have recently focused on the anti-collision algorithms, such as the Q-algorithm ( QA ), which has been successfully utilized in EPCglobal Class-1 Generation-2 protocol. However, the performance of those anti-collision algorithms needs to be further improved. Observe that fully exploiting the pre-processing time can improve the efficiency of the QA algorithm. With an objective of improving the performance for anti-collision, we propose a Nested Q-algorithm ( NQA ), which makes full use of such pre-processing time and incorporates the advantages of both Binary Tree ( BT ) algorithm and QA algorithm. Specifically, based on the expected number of collision tags, the NQA algorithm can adaptively select either BT or QA to identify collision tags. Extensive simulation results validate the efficiency and effectiveness of our proposed NQA (i.e., less running time for processing the same number of active tags) when compared to the existing algorithms.

With the rapid development of Industrial Internet of Things, the category and quantity of industrial equipment will increase gradually. For centralized monitoring and management of numerous and multivariate equipment in the intelligent manufacturing process, the equipment categories shall be identified first. However, manual labeling of electrical equipment needs high costs. For the purpose of recognizing industrial equipment accurately in manufacturing systems, this study adopts the long short-term memory to analyze big data features and build a nonintrusive load monitoring system. Edge computing is used to implement parallel computing to improve the efficiency of equipment identification. Considering the practical popularity, the fairly priced low-frequency Smart Meter is used to collect the appliance data. According to the proposed optimal adjustment strategy of parameter model, the average random recognition rate can achieve 88% and the average recognition rate of the continuous data of a single electrical equipment can achieve 83.6%.

The deep convolutional computation model (DCCM) enabled remarkable progress in feature learning of industrial big data in Internet of Things. However, as a typical static deep learning model, it is difficult to learn features for incremental industrial big data. To solve this problem, we propose an incremental DCCM by developing two incremental algorithms, i.e., parameter-incremental algorithm and structure-incremental algorithm. The parameter-incremental algorithm aims to incrementally train the fully connected layers together with fine tuning for incorporating the new knowledge into the prior one. Then, the structure-incremental algorithm is used to transfer the previous knowledge by introducing an updating rule of the tensor convolutional, pooling, and fully connected layers. Furthermore, the dropout strategy is extended into the tensor fully connected layer to improve the robustness of the proposed model. Finally, extensive experiments are carried out on the representative datasets including CIFRA and CUAVE to justify the proposed model in terms of adaption, preservation, and convergence efficiency.

Duplicated data storage wastes memory resources and brings extra data-management load and cost to cloud service providers (CSPs). Various feasible schemes to deduplicate encrypted cloud data have been reported. However, their successful deployment in practice depends on whether all system players or stakeholders are willing to accept and execute them in a cooperative way, which was scarcely investigated in the previous literature. In this paper, we employ a noncooperative game to model the interactions in a client-side server-controlled deduplication scheme (S-DEDU) and construct an incentive mechanism based on payment discount to motivate its final acceptance. The experimental results based on a real-world dataset demonstrate the individual rationality, incentive compatibility, profitability, and robustness of our incentive mechanism.

Deep computation, as an advanced machine learning model, has achieved the state-of-the-art performance for feature learning on big data in industrial Internet of Things (IoT). However, the current deep computation model usually suffers from overfitting due to the lack of public available labeled training samples, limiting its performance for big data feature learning. Motivated by the idea of active learning, an adaptive dropout deep computation model (ADDCM) with crowdsourcing to cloud is proposed for industrial IoT big data feature learning in this paper. First, a distribution function is designed to set the dropout rate for each hidden layer to prevent overfitting for the deep computation model. Furthermore, the outsourcing selection algorithm based on the maximum entropy is employed to choose appropriate samples from the training set to crowdsource on the cloud platform. Finally, an improved supervised learning from multiple experts scheme is presented to aggregate answers given by human workers and to update the parameters of the ADDCM simultaneously. Extensive experiments are conducted to evaluate the performance of the presented model by comparing with the dropout deep computation model and other state-of-the-art crowdsourcing algorithms. The results demonstrate that the proposed model can prevent overfitting effectively and aggregate the labeled samples to train the parameters of the deep computation model with crowdsouring for industrial IoT big data feature learning.

Aiming at discovering hidden different data structures in big data from different perspectives, a tensor-based multiple clustering method has been developed recently, which can be widely used in Industrial Internet of Things (IoT) to improve production and service quality. However, due to the high computational cost and huge volume of data, outsourcing computing to relatively inexpensive cloud servers can greatly save local costs, but there is a high risk of revealing user privacy. To address the above problem, a privacy-preserving tensor-based multiple clustering method on the secure hybrid cloud is proposed. The proposed scheme utilizes a homomorphic cryptosystem to encrypt object tensors and, then, employs cloud servers to completely implement multiple clustering calculation over encrypted object tensors. Furthermore, a series of related security subprotocols are proposed to support privacy-preserving tensor-based multiple clusterings. In the proposed scheme, only encryption and removing perturbation are performed on the client, which is very lightweight for users. Experimental results show that the proposed scheme is accurate and efficient when clustering objects to different groups, while no private or additional information is leaked. Moreover, when employing more cloud nodes, the scheme has high scalability; thus, it is very suitable for clustering Industrial IoT big data.

Multipath routing can significantly improve the network throughput and end-to-end (e2e) delay. Network coding based multipath routing removes the complicated coordination among multiple paths so that it further enhances data transmission efficiency. Traditional network coding based multipath routing protocols, however, are inefficient for Low Earth Orbit (LEO) satellite networks with the long link delay and regular network topology. Considering these characteristics, in this paper, we first formulate the multipath cooperative routing problem, then propose a Network Coding based Multipath Cooperative Routing (NCMCR) protocol for LEO satellite networks to improve the throughput. We propose source-based and destination-based multipath cooperative routing algorithms, which deliver different parts of a data flow along multiple link-disjoint paths dynamically and cooperatively. Furthermore, we design an efficient No-Stop-Wait ACK mechanism for our NCMCR protocol to accelerate the data transmission, where a source node continuously sends subsequent batches before it receives ACK messages for the batches sent previously. Under the proposed acknowledgement mechanism, we theoretically analyze the number of coded packets that should be sent and the transmission times of each batch for successfully decoding a batch. NS2-based simulation results demonstrate that our NCMCR outperforms the most related protocols.

Predicting the future network traffic through big data analysis technologies has been one of the important preoccupations of network design and management. Combining Markov chains with tensors to implement predictions has received considerable attention in the era of big data. However, when dealing with multi-order Markov models, the existing approaches including the combination of states and Z-eigen decomposition still face some shortcomings. Therefore, this paper focuses on proposing a novel multivariate multi-order Markov transition to realize multi-modal accurate predictions. First, we put forward two new tensor operations including tensor join and unified product (UP). Then a general multivariate multi-order (2M) Markov model with its UP-based state transition is proposed. Afterwards, we develop a multi-step transition tensor for 2M Markov models to implement the multi-step state transition. Furthermore, an UP-based power method is proposed to calculate the stationary joint probability distribution tensor (i.e., stationary joint eigentensor, SJE) and realize SJE based multi-modal accurate predictions. Finally, a series of experiments under various Markov models on real-world network traffic datasets are conducted. Experimental results demonstrate that the proposed SJE based approach can improve the prediction accuracy for network traffic by highest up to 38.47 percentage points compared with the Z-eigen based approach.

Smart environments, also referred to as cyber-physical-social systems (CPSSs), are expected to significantly benefit from the integration of edge, fog, and cloud for intelligence service flexibility, efficiency, and cost saving. High-order Bi-Lanczos method has emerged as a powerful tool serving as multi-dimensional data processing, such as prevailing feature extraction, classification, and clustering of high-order data, in CPSSs. However, integrated edge-fog-cloud architecture is open and users have very limited control; how to carry out big data processing without compromising the security and privacy is a challenging issue in edge-fog-cloud-assisted smart applications. In this work, we propose a novel and practical privacy-preserving high-order Bi-Lanczos scheme in integrated edge-fog-cloud architectural paradigm for smart environments. More precisely, we first propose a privacy-preserving big data processing model using the synergy of edge, fog, and cloud. The proposed model enables edge, fog, and cloud to cooperatively complete big data processing without compromising users’ privacy for large-scale tensor data in CPSSs. Subsequently, making use of the model, we present a privacy-preserving high-order Bi-Lanczos scheme. Finally, we theoretically and empirically analyze the security and efficiency of the proposed privacy-preserving high-order Bi-Lanczos scheme based on an intelligent surveillance system case study. And the results demonstrate that the proposed scheme provides a privacy-preserving and efficient way of computations in integrated edge-fog-cloud paradigm for smart environments.

Transfer learning, which focuses on finding a favorable representation for instances of different domains based on auxiliary data, can mitigate the divergence between domains through knowledge transfer. Recently, increasing efforts on transfer learning have employeddeepneuralnetworks (DNN) to learn more robust and higher level feature representations to better tackle cross-media disparities. However, only a few articles consider the correction and semantic matching between multi-layer heterogeneous domain networks. In this article, we propose adeep semantic mapping model forheterogeneous multimediatransferlearning (DHTL) using co-occurrence data. More specifically, we integrate the DNN withcanonicalcorrelationanalysis (CCA) to derive a deep correlation subspace as the joint semantic representation for associating data across different domains. In the proposed DHTL, a multi-layer correlation matching network across domains is constructed, in which the CCA is combined to bridge each pair of domain-specific hidden layers. To train the network, a joint objective function is defined and the optimization processes are presented. When the deep semantic representation is achieved, the shared features of the source domain are transferred for task learning in the target domain. Extensive experiments for three multimedia recognition applications demonstrate that the proposed DHTL can effectively find deep semantic representations for heterogeneous domains, and it is superior to the several existing state-of-the-art methods for deep transfer learning.

As the computing devices and software executions are susceptible to manifold faults, fault tolerance has been an important research topic in safety-critical real-time systems. Moreover, multicore processors have recently emerged as prevailing computing engines for modern embedded systems. However, there exists rather rare work on the fault-tolerant scheduling of real-time tasks executing on multicores with shared resources, where the task synchronization originated from resource access contention may significantly degrade the schedulability of task system. With the focus on the partitioned-EDF scheduler with the MSRP (Multiprocessor Stack Resource Policy) protocol and primary/backup recovery mechanism, we first investigate a utilization bound and then identify its anomaly where the bound may decrease when more cores are deployed. Next, following the insights gained by the analysis of the bound, we propose a reliability and synchronization aware task partitioning algorithm (RSA-TPA) together with an efficient version to implement the joint management of task synchronization and system reliability, where several resource-oriented heuristics are developed to improve both the schedulability performance and workload balancing. The extensive simulation results show that the RSA-TPA schemes can obtain higher acceptance ratio (e.g., 60 percent more) and generate more balanced partitions, when compared to the existing schemes that consider either reliability management or task synchronization. Finally, with the different fault arrival rates being considered, the actual implementation in Linux kernel further demonstrates the applicability of RSA-TPA that has lower run-time overhead (e.g., 20 percent less) in comparison with other mapping algorithms.

As the volume of data keeps growing rapidly, more and more storage devices, servers and network devices are continuously added into data centers to store, manage and analyze the data. The industry experience indicates that, instead of a huge number of servers added at a time, the data center network also expands gradually by adding a small number of servers from time to time. As a result, how to achieve an incremental scalability is becoming a very important challenge in designing modern data center network architectures in order to maintain the topological properties unchanged when the size of data centers grows. In this paper, we propose a new type of data center network architecture named HSDC (High Scalability Data Center Network Architecture) based on the hypercube network. The HSDC is constructed by using $m$m-port switches and 2-port servers. The fault-tolerant routing algorithm designed in this paper for HSDC can be executed on any vertex and is able to construct a path between any pair of vertices. In order to achieve an incremental scalability, we further propose three types of incomplete HSDC structures that allow gradually adding servers into the structures, while maintaining all the topological properties. The simulation experiments and performance results demonstrate that the throughput of HSDC is comparable to that of Fat-Tree, BCube and DCell. Furthermore, the analysis results indicate that HSDC strikes a good balance among diameter, bisection width, incremental scalability, cost and energy consumption in contrast to the state-of-the-art data center network architectures.

Reducing energy consumption is a vital and challenging problem for the edge computing devices since they are always energy-limited. To tackle this problem, a deep Q-learning model with multiple DVFS (dynamic voltage and frequency scaling) algorithms was proposed for energy-efficient scheduling (DQL-EES). However, DQL-EES is highly unstable when using a single stacked auto-encoder to approximate the Q-function. Additionally, it cannot distinguish the continuous system states well since it depends on a Q-table to generate the target values for training parameters. In this paper, a double deep Q-learning model is proposed for energy-efficient edge scheduling (DDQ-EES). Specially, the proposed double deep Q-learning model includes a generated network for producing the Q-value for each DVFS algorithm and a target network for producing the target Q-values to train the parameters. Furthermore, the rectified linear units (ReLU) function is used as the activation function in the double deep Q-learning model, instead of the Sigmoid function in QDL-EES, to avoid gradient vanishing. Finally, a learning algorithm based on experience replay is developed to train the parameters of the proposed model. The proposed model is compared with DQL-EES on EdgeCloudSim in terms of energy saving and training time. Results indicate that our proposed model can save average 2%-2.4% energy and achieve a higher training efficiency than QQL-EES, proving its potential for energy-efficient edge scheduling.

Mobile cloud computing (MCC) is extensively ubiquitous in the mobile Internet era and embraces complex environments because of the heterogeneity of devices and complexity of communications. Balancing the costs of different influencing objectives (e.g., energy consumption, system reliability, and quality of experience (QoE)) in MCC faces great challenges. This paper focuses on reasonably allocating computational tasks to suitable cores of mobile devices or cloud in MCC to minimize the total energy consumption, and maximize the system reliability and QoE. Concretely, this paper 1 proposes a holistic mobile cloud optimization model including energy consumption, system reliability, and QoE; 2 presents a DVFS-enabled and thermal-aware global energy consumption model which simultaneously considers the synergy of multiple factors concerning mobile devices, cloud, and networks; 3 constructs a tensor-based representation model to comprehensively reflect the complex relationship of multiple influencing factors and cope with their heterogeneity; and 4 proposes a customized optimization framework and two heuristic single-objective optimization (SOO) and triple-objective optimization (TOO) algorithms based on simulated annealing. Experimental results demonstrate that the proposed scheme outperforms the state-of-the-art scheduling schemes in SOO and the Pareto front in TOO can provide appropriate solutions to satisfy different application requirements.

With an objective to provide the proactive and personalized services for human beings, Cyber-Physical-Social Systems (CPSS), which combine the cyber space, physical space, and social space together, need to process the large scale heterogenous data first. Tensor, as an appropriate data representation tool, has been widely used for representation of heterogeneous Cyber-Physical-Social big data. When computationally processing such tensor, many necessary constraints have to be taken into account, e.g., the execution time, energy consumption, economic cost, security as well as reliability. However, the systematic integration of these constraints and then the modelling of general optimization for tensor processing become more challenging. In this paper, with such constraints being considered together, a general model for tensor computation that optimizes the execution time, energy consumption, and economic cost with acceptable security and reliability is proposed. From diverse perspectives of user requirements, a case study for the tree-based distributed High-Order Singular Value Decomposition (HOSVD) is measured. With the focus on multi-objective combination, the experimental results validate the applicability and generality of the proposed model.

Energy saving is a critical and challenging issue for real-time systems in embedded devices because of their limited energy supply. To reduce the energy consumption, a hybrid dynamic voltage and frequency scaling (DVFS) scheduling based on Q-learning (QL-HDS) was proposed by combining energy-efficient DVFS techniques. However, QL-HDS discretizes the system state parameters with a certain step size, resulting in a poor distinction of the system states. More importantly, it is difficult for QL-HDS to learn a system for various task sets with a Q-table and limited training sets. In this paper, an energy-efficient scheduling scheme based on deep Q-learning model is proposed for periodic tasks in real-time systems (DQL-EES). Specially, a deep Q-learning model is designed by combining a stacked auto-encoder and a Q-learning model. In the deep Q-learning model, the stacked auto-encoder is used to replace the Q-function for learning the Q-value of each DVFS technology for any system state. Furthermore, a training strategy is devised to learn the parameters of the deep Q-learning model based on the experience replay scheme. Finally, the performance of the proposed scheme is evaluated by comparison with QL-HDS on different simulation task sets. Results demonstrated that the proposed algorithm can save average$4.2\%$energy than QL-HDS.

Existing random access protocols designed for satellite networks have poor performance in short burst communications because of the difficulty on global time synchronization and frequent collisions. In this paper, we propose a Lightweight Retransmission (LwR) mechanism for random access in satellite networks to reduce collisions and get rid of synchronization requirement. In our LwR, only partial bits in a packet are retransmitted. Firstly, we formulate the lightweight retransmission problem and prove that it is NP-hard. Next, we focus on the construction of partial replicas, which is the core of our LwR, and propose regular and random construction methods. Especially, we prove the sufficient conditions for successfully decoding two conflicted packets by ZigZag. Finally, we propose an algebraic model and derive the upper and lower bounds of successfully decoding probability under different construction methods. Both theoretical analysis and experimental results reveal that the random construction method achieves higher decoding probability than the regular construction method. Simulation results also demonstrate that our LwR significantly outperforms related schemes designed for satellite networks.

Abstract This special issue contains 28 full papers selected from the Computer Animation

In the paradigm of infrastructure-as-a-service cloud computing involving an Internet of Things network, customers outsource their infrastructure to the cloud. An outsourced infrastructure is a virtual infrastructure that mimics the physical infrastructure of the precloud era; it is therefore referred to as a tenant network (TN) in this paper. This practice draws upon the notion of TN abstraction, which specifies how TNs should be managed. However, current virtual software-defined network (SDN) technology uses an SDN hypervisor to attain TNs, where the cloud administrator is given much-more-than-necessary privileges; thus, not only could violation of the security principle of least privilege occur, but the threat of a malicious or innocent-but-compromised administrator may be present. Motivated by this need, we propose the specification of TN abstraction, including its functions and security requirements. Then, we present a platform-independent concretization of this abstraction called TNGuard, which is an SDN-based architecture that protects the TNs while removing unnecessary privileges from the cloud administrator. In order to show that TNGuard concretizes the TN abstraction, we present an instantiation of TNGuard on the Xen virtualization platform with the Ryu controller. Experimental results show that the resulting system is practical, incurring a small performance overhead.

The Internet of Things (IoT) evolving from the conventional wireless sensor networks (WSNs) with more smart sensors has attracted significant attention. As one of the most crucial metrics for evaluating the quality of service (QoS) of both IoT and WSNs, sensing coverage characterizes the monitoring status of a sensing field of interest. However, the existence of coverage holes will remarkably degrade the QoS of the IoT. Based on the novel confident information coverage (CIC) model, this paper provides an in-depth study on how to energy-efficiently heal the multimodal CIC holes (MCICH) in a narrowband IoT (NB-IoT)-enabled hybrid IoT deployed for radiological pollution monitoring, where both mobile and stationary sensors equip multimodal sensing units for sensing dissimilar multimodal physical attributes and the NB-IoT provides satisfied network connectivity. We pinpoint the MCICH healing (MCICHH) problem with the objective of energy-efficiently dispatching a series of multimodal mobile IoT sensors to the CIC holes such that the MCIC holes can be headed and the CIC performance can be satisfied. After proving the NP-completeness of MCICHH by reducing it to the set partition problem, we develop a family of effective heuristic schemes including the centralized-MCICHH, the distributed-MCICHH and random CIC hole healing, all of which target for efficiently healing the MCIC holes while minimizing the total moving energy consumption of the dispatched multimodal mobile sensors or maximizing the average remaining energy of the multimodal mobile sensors. Extensive experiments verify the effectiveness and practicality of the proposed schemes.

Because of the co-existing of H.264/AVC and high efficiency video coding standard (HEVC) in the coming long period, video transcoding technology has become an essential part of multimedia communication in the field of the Internet of Vehicles (IoV). However, due to the huge computational complexity of re-encoding processes, traditionally cascaded transcoders greatly increase the computing burden of the embedded devices and impact the real-time capability of transportation communication systems. In order to address this problem, a fast transcoding solution is proposed in this paper. First, we exploit the mapping relationship among H.264/AVC decoding information and HEVC coding unit (CU) depth decision and prediction unit (PU) mode decision. Then, a three-output classification model is built for CU depth decision processes, and a two-output classification model is built for PU mode selection processes by using support vector machine method. Finally, the models are applied into the cascaded transcoder to accelerate the re-encoding process. The experimental results show that our proposal averagely achieves up to 53.7% and 52.3% complexity reductions under Lowdelay_P_main and Randomaccess_main configurations, respectively, with the negligible rate-distortion degradation, which show a great potential in improving the transcoding efficiency in the real-time video communication system of IoV.

In the recent years, vehicular adhoc networks (VANETs) can be an attractive choice for collecting and transferring the healthcare data of the passengers to the remote healthcare centers. In VANETs, some of the intermediate nodes may act as relay nodes in which case, these networks are called as vehicular relay networks (VRNs). However, the transmitted information in VRNs can be captured by intruders during transmission. Moreover, an attacker can launch selective forwarding, blackhole, and sinkhole attacks in the network, which may in turn degrade the network performance parameters like high end-to-end delay, low packet delivery ratio (PDR) and network throughput. Hence, to address these issues, a secure data dissemination scheme using VRNs is proposed. In the proposed scheme, first, a secure vehicular medical relay network system is designed for the users belonging to disconnected rural areas. The collected information is filtered at zonal levels before transmission to a nearby road side units, which further pass it to the incoming vehicles. Second, a secure passenger health monitoring network is designed which continuously monitors health services of the passengers traveling in different vehicles. The information collected through small body sensors installed in the vehicles act as data sets that is forwarded to the on-board monitoring unit within the vehicle. This collected data is then transmitted to centralized healthcare centers for processing by using VRNs. Lastly, a strong elliptic curve cryptography-based cryptographic solution is designed for secure communication among different vehicles. The performance of the proposed scheme is evaluated in various network scenarios with respect to different selected parameters, such as throughput, network delay, PDR, jitter, transmission and computation overheads, and key distribution overhead. The obtained results indicate that the proposed scheme provides improvement of 52% in average delay and 5% in PDR. This further indicates effective message delivery even with high mobility of the vehicles.

The explosive growth of Internet of Things is generating massive data which are normally stored in data centers. The power consumption has become a very important challenge of designing modern data centers due to the explosive growth of data. The power consumed by cooling system accounts for about half of the total power consumption. Reducing the peak inlet temperature of racks residing in data centers can effectively decrease the temperature requirement of supplied cold air, thus cutting down the cooling cost. Task distribution in data centers has a significant impact on this inlet temperature. Many investigations have been conducted on achieving an optimal task distribution in terms of the air organization [e.g., genetic algorithm (GA)]. However, the existing methods can be easily trapped into a local optimum. This paper constructs a power model to correlate the task assignment, heat recirculation, inlet temperature, and cooling cost in the homogeneous and heterogeneous data centers with under-floor air supply. Furthermore, genetic simulated annealing algorithm is proposed and designed to enhance the traditional GA and assign tasks in the data centers according to the corresponding air organization by integrating the advantages of simulated annealing, thus minimizing the inlet temperature and reducing the cooling cost. Experimental results indicate that the proposed approach can effectively decrease the temperature requirement of supplied cold air and reduce the power consumption of the cooling system in contrast to the traditional GA and ant colony algorithm, especially when the data centers are with medium utilization.

Recent years have witness a considerable advance of Internet of Things with the tremendous progress of communication theories and sensing technologies. A large number of data, usually referring to big data, have been generated from Internet of Things. In this paper, we present a double-projection deep computation model (DPDCM) for big data feature learning, which projects the raw input into two separate subspaces in the hidden layers to learn interacted features of big data by replacing the hidden layers of the conventional deep computation model (DCM) with double-projection layers. Furthermore, we devise a learning algorithm to train the DPDCM. Cloud computing is used to improve the training efficiency of the learning algorithm by crowdsourcing the data on cloud. To protect the private data, a privacy-preserving DPDCM (PPDPDCM) is proposed based on the BGV encryption scheme. Finally, experiments are carried on Animal-20 and NUS-WIDE-14 to estimate the performance of DPDCM and PPDPDCM by comparing with DCM. Results demonstrate that DPDCM achieves a higher classification accuracy than DCM. More importantly, PPDPDCM can effectively improve the efficiency for training parameters, proving its potential for big data feature learning.

Big data has received considerable attentions in recent years because of massive data volumes in multifarious fields. Considering various “V” features, big data tasks are usually highly complex and computational intensive. These tasks are generally performed in parallel in data centers resulting in massive energy consumption and Green House Gases emissions. Therefore, efficient resource allocation considering the synergy of the performance and energy efficiency is one of the crucial challenges today. In this paper, we aim to achieve maximum energy efficiency by combining thermal-aware and dynamic voltage and frequency scaling (DVFS) techniques. This paper proposes: (a) a thermal-aware and power-aware hybrid energy consumption model synchronously considering the computing, cooling, and migration energy consumption; (b) a tensor-based task allocation and frequency assignment model for representing the relationship among different tasks, nodes, time slots, and frequencies; and (c) a big data Task Scheduling algorithm based on Thermal-aware and DVFS-enabled techniques (TSTD) to minimize the total energy consumption of data centers. The experimental results demonstrate that the proposed TSTD algorithm significantly outperforms the state-of-the-art energy efficient algorithms from total, computing, and cooling energy consumption perspectives, as well as cooling energy consumption proportion and total energy consumption savings.

Due to the rapid advances of information technologies, Big Data, recognized with 4Vs characteristics (volume, variety, veracity, and velocity), bring significant benefits as well as many challenges. A major benefit of Big Data is to provide timely information and proactive services for humans. The primary purpose of this paper is to review the current state-of-the-art of Big Data from the aspects of organization and representation, cleaning and reduction, integration and processing, security and privacy, analytics and applications, then present a novel framework to provide high-quality so called Big Data-as-a-Service. The framework consists of three planes, namely sensing plane, cloud plane and application plane, to systemically address all challenges of the above aspects. Also, to clearly demonstrate the working process of the proposed framework, a tensor-based multiple clustering on bicycle renting and returning data is illustrated, which can provide several suggestions for rebalancing of the bicycle-sharing system. Finally, some challenges about the proposed framework are discussed.

In mixed-criticality (MC) systems, multiple activities with various certification requirements (thus with different criticality levels) can co-exist on shared hardware platforms, where multicore processors have emerged as the de facto computing engines. In this paper, by using the partitioned earliest-deadline-first with virtual deadlines (EDF-VDs) scheduler for a set of periodic MC tasks running on multicore systems, we derive a criticality-aware utilization bound for efficient feasibility tests and then identify its characteristics. Our analysis shows that the bound increases with increasing number of cores and decreasing system criticality level. We show that, since the utilizations of MC tasks at different criticality levels can vary considerably, the utilization contribution of a task on different cores may have large variations and thus can significantly affect the system schedulability under the EDF-VD scheduler. Based on these observations, we propose a novel and efficient criticality-aware task partitioning algorithm (CA-TPA) to compensate for the inherent pessimism of the utilization bound. In order to improve the system schedulability, the task priorities are determined according to their utilization contributions to the system in CA-TPA. Moreover, by analyzing the utilization variations of tasks at different levels, we develop several heuristics to minimize the utilization increment and balance the workload on cores. The simulation results show that the CA-TPA scheme is very effective in achieving higher schedulability ratio and yielding balanced workloads. The actual implementation in Linux operating system further demonstrates the applicability of CA-TPA with lower run-time overhead, compared to the existing partitioning schemes.

With the exponential growth of data volume, big data have placed an unprecedented burden on current computing infrastructure. Dimensionality reduction of big data attracts a great deal of attention in recent years as an efficient method to extract the core data which is smaller to store and faster to process. This paper aims at addressing the three fundamental problems closely related to distributed dimensionality reduction of big data, i.e., big data fusion, dimensionality reduction algorithm and construction of distributed computing platform. A chunk tensor method is presented to fuse the unstructured, semi-structured and structured data as a unified model in which all characteristics of the heterogeneous data are appropriately arranged along the tensor orders. A Lanczos based high order singular value decomposition algorithm is proposed to reduce dimensionality of the unified model. Theoretical analyses of the algorithm are provided in terms of storage scheme, convergence property and computation cost. To execute the dimensionality reduction task, this paper employs the transparent computing paradigm to construct a distributed computing platform as well as utilizes a four-objectives optimization model to schedule the tasks. Experimental results demonstrate that the proposed holistic approach is efficient for distributed dimensionality reduction of big data.

As the rapidly growing volume of data are beyond the capabilities of many computing infrastructures, to securely process them on cloud has become a preferred solution which can both utilize the powerful capabilities provided by cloud and protect data privacy. This paper puts forward a new approach to securely decompose tensor, the mathematical model widely used in data-intensive applications, to a core tensor and some truncated orthogonal bases. The structured, semi-structured as well as unstructured data are all transformed to low-order sub-tensors which are then encrypted using the fully homomorphic encryption scheme. A unified high-order cipher tensor model is constructed by collecting all the cipher sub-tensors and embedding them to a base tensor space. The cipher tensor is decomposed through a proposed secure algorithm, in which the square root operations are eliminated during the Lanczos procedure. The paper makes an analysis of the secure algorithm in terms of time consumption, memory usage and decomposition accuracy. Experimental results reveals that this approach can securely decompose tensor models. With the advancement of fully homomorphic encryption scheme, the proposed secure tensor decomposition method is expected to be widely applied on cloud for privacy-preserving data processing.

Load-balanced flow scheduling for big data centers in clouds, in which a large amount of data needs to be transferred frequently among thousands of interconnected servers, is a key and challenging issue. The OpenFlow is a promising solution to balance data flows in data center networks through its programmatic traffic controller. Existing OpenFlow based scheduling schemes, however, statically set up routes only at the initialization stage of data transmissions, which suffers from dynamical flow distribution and changing network states in data centers and often results in poor system performance. In this paper, we propose a novel dynamical load-balanced scheduling (DLBS) approach for maximizing the network throughput while balancing workload dynamically. We first formulate the DLBS problem, and then develop a set of efficient heuristic scheduling algorithms for the two typical OpenFlow network models, which balance data flows time slot by time slot. Experimental results demonstrate that our DLBS approach significantly outperforms other representative load-balanced scheduling algorithms Round Robin and LOBUS; and the higher imbalance degree data flows in data centers exhibit, the more improvement our DLBS approach will bring to the data centers.

The explosive growth of data brings new challenges to the data storage and management in cloud environment. These data usually have to be processed in a timely fashion in the cloud. Thus, any increased latency may cause a massive loss to the enterprises. Similarity detection plays a very important role in data management. Many typical algorithms such as Shingle, Simhash, Traits and Traditional Sampling Algorithm (TSA) are extensively used. The Shingle, Simhash and Traits algorithms read entire source file to calculate the corresponding similarity characteristic value, thus requiring lots of CPU cycles and memory space and incurring tremendous disk accesses. In addition, the overhead increases with the growth of data set volume and results in a long delay. Instead of reading entire file, TSA samples some data blocks to calculate the fingerprints as similarity characteristics value. The overhead of TSA is fixed and negligible. However, a slight modification of source files will trigger the bit positions of file content shifting. Therefore, a failure of similarity identification is inevitable due to the slight modifications. This paper proposes an Enhanced Position-Aware Sampling algorithm (EPAS) to identify file similarity for the cloud by modulo file length. EPAS concurrently samples data blocks from the head and the tail of the modulated file to avoid the position shift incurred by the modifications. Meanwhile, an improved metric is proposed to measure the similarity between different files and make the possible detection probability close to the actual probability. Furthermore, this paper describes a query algorithm to reduce the time overhead of similarity detection. Our experimental results demonstrate that the EPAS significantly outperforms the existing well known algorithms in terms of time overhead, CPU and memory occupation. Moreover, EPAS makes a more preferable tradeoff between precision and recall than that of other similarity detection algorithms. Therefore, it is an effective approach of similarity identification for the cloud.

Cyber-physical-social systems (CPSS), integrating cyber, physical, and social spaces together, bring both conveniences and challenges to humans. For practical applications and user convenience, it is essential that the Big Data produced in CPSS be processed in real time. Therefore, Big Data computation should avoid redundant computations on historical data when dealing with periodic incoming data. In this paper, we propose a columnwise high-order singular value decomposition (HOSVD) algorithm to realize dimensionality reduction, extraction, and noise reduction for tensor-represented Big Data. First, the distributed HOSVD (DHOSVD) is proposed using the columnwise Jacobi-based approach to realize the distributed computation of HOSVD. Second, big streaming data are continuously produced and the intermediate results could be recorded for the next computational step. Third, we propose a similar columnwise incremental HOSVD (IHOSVD) scheme to support online computation on temporally incremental data streaming. The performance of the two HOSVD-based schemes will illustrate the scalability of our efficient real-time Big Data processing methods.

The emergence of coverage holes will dramatically degrade the quality of service of the industrial wireless sensor networks (IWSNs). Based on the novel confident information coverage (CIC) model, this work focuses on how to heal the CIC holes in hybrid IWSNs containing both static nodes and mobile nodes. We pinpoint the CIC hole healing (CICHH) problem with the goal of selecting and dispatching some randomly scattered mobile nodes to the CIC holes detected by the stationary nodes such that the CIC holes can be repaired and the CIC performance can be satisfied, and prove its NP-completeness. For handling the CICHH problem, we devise two energy-efficient heuristic solutions including a centralized CICHH algorithm and a distributed one. Both the proposed schemes aim at efficiently healing the CIC holes while minimizing the total moving energy consumption of the dispatched mobile nodes, or maximizing the mobile nodes' average remaining energy after movement, or minimizing the maximum mobile energy consumption of each dispatched mobile node. Experimental simulation results show the proposed schemes can energy-efficiently heal the CIC holes and outperform three peer algorithms in terms of energy efficiency and coverage ratio.

Currently, a large number of industrial data, usually referred to big data, are collected from Internet of Things (IoT). Big data are typically heterogeneous, i.e., each object in big datasets is multimodal, posing a challenging issue on the convolutional neural network (CNN) that is one of the most representative deep learning models. In this paper, a deep convolutional computation model (DCCM) is proposed to learn hierarchical features of big data by using the tensor representation model to extend the CNN from the vector space to the tensor space. To make full use of the local features and topologies contained in the big data, a tensor convolution operation is defined to prevent overfitting and improve the training efficiency. Furthermore, a high-order backpropagation algorithm is proposed to train the parameters of the deep convolutional computational model in the high-order space. Finally, experiments on three datasets, i.e., CUAVE, SNAE2, and STL-10 are carried out to verify the performance of the DCCM. Experimental results show that the deep convolutional computation model can give higher classification accuracy than the deep computation model or the multimodal model for big data in IoT.

Industrial communication systems (ICSs) have become an important part of many automated applications. Smart sensors for ICSs have attracted much attention. Using smart sensors for ICSs can allow the surrounding world to connect with the production equipment to reduce human resource requirements. However, due to their operating nature, smart sensors are often unattended and prone to different kinds of attacks. An on-off attack is one behavior that can cause serious damage to wireless sensor networks in ICSs. To ensure network security, a trust joint light probe based defense (TLPD) mechanism is proposed in which each smart sensor node selects a smart sensor node with high trust as the next hop to improve network security. The TLPD scheme is constituted by three major components, including light probe routing, trust estimation, and trust-aware routing. Light probe routing is adopted for increasing the operation times of malicious nodes, and a trust evaluation scheme evaluates nodes trust according to operation behavior of nodes. Thus, the discrimination degree of node trust between temporary errors and disguised malicious behaviors can be increased compared to existing trust evaluation schemes. Thus, a malicious smart sensor node can be quickly and easily identified. The analytical results of the TLPD mechanism assessed are with a simulation experiment.

The deep computation model has been proved to be effective for big data hierarchical feature and representation learning in the tensor space. However, it requires expensively computational resources including high-performance computing units and large memory to train a deep computation model with a large number of parameters, limiting its effectiveness and efficiency for industry informatics big data feature learning. In this paper, a tensor-train deep computation model is presented for industry informatics big data feature learning. Specially, the tensor-train network is used to compress the parameters significantly by converting the dense weight tensors into the tensor-train format. Furthermore, a learning algorithm is implemented based on gradient descent and back-propagation to train the parameters of the presented tensor-train deep computation model. Extensive experiments are carried on STL-10, CUAVE, and SNAE2 to evaluate the presented model in terms of the approximation error, classification accuracy drop, parameters reduction, and speedup. Results demonstrate that the presented model can improve the training efficiency and save the memory space greatly for the deep computation model with small accuracy drops, proving its potential for industry informatics big data feature learning.

Deep learning, as the most important architecture of current computational intelligence, achieves super performance to predict the cloud workload for industry informatics. However, it is a nontrivial task to train a deep learning model efficiently since the deep learning model often includes a great number of parameters. In this paper, an efficient deep learning model based on the canonical polyadic decomposition is proposed to predict the cloud workload for industry informatics. In the proposed model, the parameters are compressed significantly by converting the weight matrices to the canonical polyadic format. Furthermore, an efficient learning algorithm is designed to train the parameters. Finally, the proposed efficient deep learning model is applied to the workload prediction of virtual machines on cloud. Experiments are conducted on the datasets collected from PlanetLab to validate the performance of the proposed model by comparing with other machine-learning-based approaches for workload prediction of virtual machines. Results indicate that the proposed model achieves a higher training efficiency and workload prediction accuracy than state-of-the-art machine-learning-based approaches, proving the potential of the proposed model to provide predictive services for industry informatics.

To uncover latent data structures in big data, a high-order clustering algorithm by fast search and find of density peaks has emerged recently, and will bring great application values in industrial Internet-of-Things data management and analysis. With the popularity of cloud computing, it provides users with the convenience of outsourcing calculations while bringing the risk of privacy disclosure. Aiming at the problem above, from the characteristics of the secure cloud service system, this paper proposes a secure high-order clustering algorithm by fast search and find of density peaks on hybrid cloud. In the proposed scheme, the client first builds the encrypted object tensors with user data using homomorphic encryption, then uploads them to the cloud to completely implement the proposed protocols. In the end, clustering results perturbed with random numbers are returned to client for remove perturbation. The performance of the proposed method is evaluated on a smart grid dataset in terms of clustering accuracy, efficiency, and speedup ratio. Experimental results reveal that the proposed approach can accurately and effectively cluster big data without disclosing user privacy while ensuring that the client is very lightweight. Therefore, the proposed scheme with high security and scalability is suitable for clustering industrial Internet-of-Things big data.

Multiple clustering analysis has the clear advantages to discover latent data pattern in big data from different views, so it has tremendous practical values in automation industries. However, most of current algorithms are difficult to group heterogeneous data to multiple clusterings according to the requirements of different applications. This paper presents a flexible multiple clustering analytic and service framework, and a novel tensor-based multiple clusterings (TMC) approach. Heterogeneous data objects in cyber-physical-social systems are first represented as low-order tensors and a weight tensor construction approach is proposed to measure the importance of attributes combinations in heterogeneous feature spaces. Then, a selective weighted tensor distance is explored to cluster tensorized data objects for different applications. This paper, through a real-world smart bike maintenance system, illustrates TMC and evaluates its clustering performance. Experimental results reveal TMC can obtain higher quality clustering results but with lower redundancies to meet different requirements of applications in automation systems.

Over the past few years, software-defined networking (SDN) has stimulated worldwide interests in both academia and industry for its proven benefits. However, the reliability of SDN has become a significant barrier in adopting it. Many efforts have been made to enhance the reliability of SDNs. However, the research all assume a benign data plane, and overlook the fundamental question: what if the switches provide tainted network state information (controller's inputs) to the controller? To obtain a global view and produce networking decisions, SDN controllers must collect detailed and up-to-date network state information from the switches. Therefore, tainted inputs can easily disrupt the correctness of controller and reduce the reliability of SDN. In this paper, we argue that faulty switches can easily taint the controller's inputs in SDN, which would further mislead the controller. We investigate possible consequences of the existence of faulty switches with thorough analyses and practical examples. Aiming at enhancing the reliability of SDNs, we design and implement a prototype system that leverages Byzantine model to automatically tolerate faulty switches. Extensive experiments show that the proposed system can guarantee the correctness of the controller's inputs (specifically, flow statistics information) even when faulty switches exist with trivial overheads.

Establishing promising and efficient key distribution is the cornerstone of security when applying cryptographic methods to guard the privacy of smart devices in the Internet of Things (IoT). However, when using conventional key distribution methods in real-time mobile services, it is usually deficient to build multiple channels with strong security simultaneously on a single data server. Therefore, we focus our research on collecting or monitoring real-time and remote data, which is commonly observed in the health care field of the IoT. In this research, there are difficulties to apply the conventional key distribution approaches during interactions when considering both security and efficiency. Moreover, when preserving personal privacy, anonymity is also important in key distribution processes. We design a system of real-time mobile services and the related security requirements in this paper, and apply a novel and interesting Identity-Based Key Encapsulation Mechanism (IBKEM) to instantiate our system and achieve anonymous key distribution with only one-pass communication for mobile clients in batch. Our instantiated system demonstrates both strong security and practice.

Deep computation models achieve super performance for big data feature learning. However, training a deep computation model poses a significant challenge since a deep computation model typically involves a large number of parameters. Specially, it needs a high-performance computing server with a large-scale memory and a powerful computing unit to train a deep computation model, making it difficult to increase the size of a deep computation model further for big data feature learning on low-end devices such as conventional desktops and portable CPUs. In this paper, we propose an improved deep computation model based on the canonical polyadic decomposition scheme to compress the parameters and to improve the training efficiency. Furthermore, we devise a learning algorithm based on the back-propagation strategy to train the parameters of the proposed model. The learning algorithm can be directly performed on the compressed parameters to improve the training efficiency. Finally, we carry on the experiments on three representative datasets, i.e., CUAVE, SNAE2, and STL-10, to evaluate the performance of the proposed model by comparing with the conventional deep computation model and other two improved deep computation models based on the Tucker decomposition and the tensor-train network. Results demonstrate that the proposed model can compress parameters greatly and improve the training efficiency significantly with a low classification accuracy drop.

Recently, the demands of big data combining with cloud computing have enabled dramatically growing of intelligent data in various fields. Data security issues have been considered one of the most critical aspects for the implementations of big data and cloud computing. Big Data Security and Intelligent Data in Clouds (BDS-IDC) have been immerse in people's daily life and are promised to have a great growth in the future, such as smart data analysis, smart big data, sensitive-oriented information protection, and cloud-computing security. Multiple protection approaches and combined security schemes as well as intercrossed cloud platforms are becoming common requirements for many big data and cloud users. Considering the next generation of big data executions, it is expected to integrate big data with approaches of intelligent data in cloud systems. The main challenges of achieving this aim will go across most emerging technologies from cyber security and high performances including effective security mechanism against old and new threats, complex system architectures, computing resources allocation optimizations, distributed heterogeneous computing, energy-saving issues, and using smart data in cyber physical systems. This special issue presents a number of outstanding papers researching in the latest explorations and studies in Big Data Security and Intelligent Data in Clouds. We encourage audiences who are interested in high-performance pattern recognition to read following work. Li et al. 1 developed algorithms and investigated various classifiers to determine the authenticity of short social network postings, an average of 20.6 words, from Facebook. This work presented and discussed several experiments using a variety of classifiers. The research was one of the first works that focused on authorship authentication in short messages, such as posting on social network sites. Moreover, Yibin Li et al. 2 designed an approach to minimize the necessary calculations and memory space. The authors developed Field-Programmable Gate Array (FPGA)–based parallel architecture to apply Partial Dynamic Reconfiguration (PDR), which enables the remote configurations for the number of processing units. According to the experimental results, the detection precision could reach a miss rate less than 1.97% and a false positive rate of 1%. A reliable broadcast scheme is also a crucial issue in the target field. Xia et al. 3 investigate a novel reliable broadcast scheme that explored the advantages of lost data piggybacking. The scheme allowed all the vehicles to piggyback some received packets cooperatively to help other vehicles to recover the lost packets. The simulation results showed that the proposed cooperative offloading scheme could achieve much higher broadcast reliability and lower propagation delay, in comparison with existing solutions. Furthermore, the implementation of cloud computing is broad in multiple domains. Dou et al. 4 introduce an energy-aware dynamic VM scheduling method for QoS enhancement in clouds over big data to address the above challenge. This method consisted of 2 main VM migration phases to reduce service prices and execution time, which had been evaluated by experiments. In addition, Leng et al. 5 presented a balanced RDF graph partitioning algorithm for storing massive RDF data on cloud. The authors first devise a modularity-based multilevel label propagation algorithm to partition RDF graph roughly and then use a balanced K-mediods clustering algorithm for final k-way partitioning. This special issue also addresses the aspect of combining video with social networks. Cui et al. 6 proposed novel video recommendation algorithm based on the combination of video content and social network. The proposed algorithm consisted of the trust friends computing model and video's quality evaluation model. The trust friends computing method took into account similarity between users, interaction between users, and the active degree of a user. Son et al. 7 introduced a new conditional proxy re-encryption (CPRE) scheme, namely, the CPRE for Mobile Cloud (CPRE-M), which utilizes the back-end cloud to the extreme extent so that the overhead of terminals is drastically reduced. The scheme outsources a significant amount of computation overhead caused by re-encryption key generation, condition value change, and decryption, to the cloud. The proposed scheme allows users to verify the correctness of outsourced computation under refereed delegation of computation (RDoC) model. The simulation results show CPRE-M outperforms its existing alternatives. Cahyani et al. 8 examine the extent to which data acquisition from Windows phone is supported by 3 popular mobile forensics tools. The effect of device settings modification and alternative acquisition processes on the extraction results is also examined. The results show that current mobile forensic tool support for Windows Phone 8 remains limited. In this sense, the logical acquisition support was more complete in comparison to the physical one. Furthermore, enabling flight mode and disabling location services are recommended to limit data alteration during the acquisition process. Existing information security incident handling strategies may not be adequate as cloud data are generally virtualized, geographically distributed, and ephemeral, presenting both technical and jurisdictional challenges. Ab Rahman et al. 9 present an integrated cloud incident handling and forensic-by-design model. Afterwards, the authors validate the model using a set of controlled experiments on a cloud-related incident. Three popular cloud storage applications were deployed, namely, Dropbox, Google Drive, and OneDrive. This study demonstrates the utility of the model for organizational cloud users to undertake incident investigations. To improve the security of the microblog network, Liu et al. 10 proposed a defending scheme against malicious URL spreading in microblog networks with Hub nodes. After a node found a new malicious URL, it edits a warning message about the malicious URL. If the normal node gets malicious message, it sends private message to the Hub node and update its blog article. Malicious URL messages spread rapidly in the networks due to the influence of Hub nodes. So the security of entire microblog networks can be improved against malicious URL without increasing the network load. Experiments show that the scheme can effectively defend against malicious URL in the any scale of microblog networks. Man et al. 11 introduced a new social network access control model using logical authorization language, named as RuleSN, which can be efficiently used in cloud systems. The model provides high performance of authorization expressiveness and flexibility that can effectively describe relations of User to User, User to Resource, Resource to Resource, and attributes of users and resources. The paper elaborates the formal definitions of the RuleSN model, then the model's authorization specification and verification policies are described, and finally, the implementation, application, and expressiveness of the model are discussed. Recommender systems have shown great potential to address information overload problems, namely, to help users find interesting and relevant objects within a huge information space. To achieve more accurate recommendation, Jianxun et al. 12 investigate a recommendation algorithm INBIw, which improves on the original weighted network-based inference (NBIw) by introducing a tunable parameter β to depress the influence of high-degree nodes. To evaluate the recommendation performance of INBIw, ranking position rate and hitting rate are calculated. The results of experiments based on MovieLens data set show that the INBIw outperforms previous methods, including the global ranking method, collaborative filtering, network-based inference, and NBIw. The high-energy–consuming petroleum equipment in oilfield represents a high proportion in the total energy consumption of petroleum industry. Zhao et al. 13 analyzes the energy consumption constitutions in different production processes, focusing on the running state and energy-saving countermeasure of the high-energy–consuming mechanical equipment. The proposed model provides concurrent data processing for shortening the production cycle and the Fuzzy Weighting Subspace Clustering algorithm to implement the equipment comparability, applying the big data on the running status statistics and applying cloud computation analysis on the corresponding energy-saving countermeasure. Wang et al. 14 present a novel virtual network embedding (VNE) algorithm to increase revenue and utilization of substrate network as well as improve acceptance fairness of virtual networks. To this end, they present a virtual topology pretransformation mechanism leveraging reusable technology. Then they model the problem as an integer linear programming problem and solve the VNE problem with a discrete particle swarm optimization–based algorithm. An incentive convergence mechanism is proposed to reduce mapping complexity, which is used to accelerate convergence and to save more bandwidth. The results prove that the proposed method improves existing algorithms in terms of physical resource utilization, acceptance fairness, revenue/cost ratio, and searching efficiency. Li et al. 15 model the collaboration relations in the regional enterprise cluster as a generalized social collaboration network and explore the dynamic growth process of the Facilities Collaboration Network (FCN) for different strategies of facilities selection, including the random selection and the balanced selection. Using performance indexes such as network size, the distribution of node degree and act degree, clustering coefficient, the average shortest distance, and the number of n-cliques, they analyze the characteristics of these strategies for cloud manufacturing. Based on these characteristics, they propose 2 mechanisms for self-optimization, including the dynamic weighing of facilities and the concentrated processing of successive subtasks in the process. Finally, they analyze the mechanisms' effects on the characteristics of FCN and the performance in manufacturing. Anomaly detection plays a crucial part in identifying unforeseen attacks for network and information security. To address this issue, Li et al. 16 propose a Multilayer Anomaly Detection approach, which extracts and combines features from different network layers. To reduce redundancy and noise, an algorithm called RanPF is designed by applying principal components analysis (PCA) into random forest (RF) algorithm. RanPF uses features selected by PCA to decide the height of every tree in RF and provides a method to select which features for tree nodes to use. To obtain high-quality features, they adopt an attribute learning mechanism. Naive Bayes is used to characterize the attribute information. A series of experiments conducted on 2 real-life datasets demonstrate that the approach outperforms the state-of-the-art methods in terms of detection rate and false alarm rate. Tao et al. 17 investigated the cloud resource allocation for data access with noncooperative game based on a Gauss–Seidel iteration method. They proposed a repeated game scheme, which can approximately achieve the near Pareto-optimal flow allocation among the vehicles. Considering the vehicles' irrational behavior, a punishment strategy was designed to prevent the vehicles from behavior deviation. The analysis based on these models lays a theoretical method foundation on cloud resource allocation process. The validity of the modeling and the accuracy of the analysis were verified through extensive simulations. In the past decade, there has been a surge of interest in exploring the properties of scale-free networks. Two interesting properties have attracted much attention: assortativity and community structure. However, these properties have been studied separately in either theoretical models or real-world networks. Jiang et al. 18 show that both properties are highly related in scale-free networks. First, due to the positive degree of assortativity, assortative networks present high embeddedness. This leads to the high density of communities. Second, because of the negative degree of assortativity, disassortative networks exhibit great hubs in communities, which results in the high compactness of communities that nodes can reach each other via a few hops. Finally, as a result of the equal attractiveness of nodes in neutral networks, a big portion of links act as community bridges. Thus, neutral networks display sparse and less compact communities. Li et al. 19 investigate the selfish load balancing problem in mobile distributed crowdsourcing networks. This work leverages the d-choice method based on Ball and Bin theory for effective balancing under limited information and the proportional allocation scheme for selfish load balancing, maintaining good load balancing property among selfish users. The results show that, chance-choice outperforms several existing algorithms, comparing with proportional allocation scheme, it could decrease the load gap between the maximum and the minimum in system by 50% to 80% and reduce the overhead complexity from O(n) to O(1) comparing with the Max-weight Best Response algorithm. This special issue is composed of a collection of articles, which provide recent advances in some fields related to Big Data Security and Intelligent Data in Clouds. More precisely, the manuscripts investigate different topics including forensic in cloud-of-things devices, encryption in mobile cloud environments, defense against malicious URL spreading in microblog networks, social network access control model in cloud computing, dynamic resource sharing algorithms, load balancing for cloud computing, cloud-based audio/video streaming techniques, energy-aware scheduling in clouds, sensor network security in cloud computing, as well as real world applications related to industry, manufacturing, and vanets. We hope that the readers could benefit from the articles presented in this special issue and would contribute to these exciting research areas. The guest editors of this special issue wish to express their sincere gratitude to all of the authors who contributed to this issue. We extend our thanks to the reviewers for their hard work and their feedbacks. Likewise, we wish to express our gratitude to the Editor-in-Chief Geoffrey C. Fox for his valuable help in arranging this special issue and for giving the authors the opportunity to publish their work in Concurrency and Computation: Practice and Experience journal. Lastly, we wish to thank the journal's staff for their assistance.

Increasingly, big data (including sensitive and commercial-in-confidence data) is being accessible and stored on a range of Internet of Things (IoT) devices, such as our mobile devices. Therefore, any vulnerability in IoT devices, operating system or software can be exploited by cybercriminals seeking to exfiltrate our data. In this paper, we use iOS devices as case studies and highlight the potential for pairing mode in iOS devices (which allows the establishment of a trusted relationship between an iOS device and a personal computer) to be exploited for covert data exfiltration. In our three case studies, we demonstrate how an attacker could exfiltrate data from a paired iOS device by abusing a library and a command line tool distributed with iTunes. With the aim of avoiding similar attacks in the future, we present two recommendations.

Summary Accurate resource requests prediction is essential to achieve optimal job scheduling and load balancing for cloud Computing. Existing prediction approaches fall short in providing satisfactory accuracy because of high variances of cloud metrics. We propose a deep belief network (DBN)‐based approach to predict cloud resource requests. We design a set of experiments to find the most influential factors for prediction accuracy and the best DBN parameter set to achieve optimal performance. The innovative points of the proposed approach is that it introduces analysis of variance and orthogonal experimental design techniques into the parameter learning of DBN. The proposed approach achieves high accuracy with mean square error of [10−6,10−5], approximately 72%reduction compared with the traditional autoregressive integrated moving average predictor, and has better prediction accuracy compared with the state‐of‐art fractal modeling approach. Copyright © 2016 John Wiley & Sons, Ltd.

Summary Emotion recognition is challenging for understanding people and enhances human–computer interaction experiences, which contributes to the harmonious running of smart health care and other smart services. In this paper, several kinds of speech features such as Mel frequency cepstrum coefficient, pitch, and formant were extracted and combined in different ways to reflect the relationship between feature fusions and emotion recognition performance. In addition, we explored two methods, namely, support vector machine (SVM) and deep belief networks (DBNs), to classify six emotion status: anger, fear, joy, neutral status, sadness, and surprise. In the SVM‐based method, we used SVM multi‐classification algorithm to optimize the parameters of penalty factor and kernel function. With DBN, we adjusted different parameters to achieve the best performance when solving different emotions. Both gender‐dependent and gender‐independent experiments were conducted on the Chinese Academy of Sciences emotional speech database. The mean accuracy of SVM is 84.54%, and the mean accuracy of DBN is 94.6%. The experiments show that the DBN‐based approach has good potential for practical usage, and suitable feature fusions will further improve the performance of speech emotion recognition. Copyright © 2017 John Wiley & Sons, Ltd.

Privacy becomes one of the major concerns of cloud-based multimedia applications such as cloud video surveillance. Privacy protection of surveillance videos aims to protect privacy information without hampering normal processing tasks of the cloud. Privacy Region Protection only protects the privacy region while keeping the non-privacy region visually intact to facilitate processing in the cloud. However, full reversibility, i.e. the complete recovery of the original video which is critical to digital investigation and law enforcement has not been properly addressed in privacy region protection. In this paper, we introduce fully reversible privacy region protection into cloud video surveillance and propose a novel fully reversible privacy protection method for H.264/AVC compressed video. All the operations are performed in the compressed domain and avoid lossy re-encoding, so the original H.264/AVC compressed video can be fully recovered. To our best knowledge, the proposed scheme is the first fully reversible one for privacy region protection. Experimental results and performance comparison demonstrate the effectiveness and efficiency of the proposed approach.

A Semi Random Circle routing for mobile Sink joint Ray Routing for data (SRCRR) scheme is proposed for preserving sink-location privacy with a delay guaranteed. In the SRCRR scheme, the data are directionally routed along ray paths and stored at intermediate nodes probabilistically. The Sink moves in a semirandom circular pattern to collect data from the local nodes occasionally, which guarantees that the data will be collected with an acceptable delay and prevents attackers from predicting their locations and movements. The experimental results indicate that the performance of the SRCRR scheme is better than that of the previous schemes.

A multi-representative re-fusion (MRRF) approximate data collection approach is proposed in which multiple nodes with similar readings form a data coverage set (DCS). The reading value of the DCS is represented by an R-node. The set near the Sink is smaller, while the set far from the Sink is larger, which can reduce the energy consumption in hotspot areas. Then, a distributed data-aggregation strategy is proposed that can re-fuse the value of R-nodes that are far from each other but have similar readings. Both comprehensive theoretical and experimental results indicate that the MRRF approach increases lifetime and energy efficiency.

When competing in eBay bidding, online games, or e-exams in embedded computing environments, people naturally face asynchronous starts from different computing devices, which is treated as a security risk of online contests. The security risks of online contests also include eavesdropping during data transmission without intended rights, and false starts by malicious competitors, which also means asynchrony in contests. Accordingly, online contests need security guarantees, especially on synchronization. In this article, for synchronic and secure starts in a contest, we update security requirements of confidentiality, anonymity, and synchrony, comparing the current work to our previous work. Based on the updated requirements, we propose a general framework for the Advanced Secure Synchronized Reading (ASSR) system, which can hold multiple contests simultaneously in the cloud. It is important to note that the system can ignore the impacts of heterogeneity among competitors. Considering the heterogeneity both on transmission and computing, we construct a novel Randomness-reused Identity Based Key Encapsulation Mechanism (RIBKEM) to support separable decapsulation, which can shorten both decryption delay and transmission delay with the best efforts. Finally, ASSR enhances synchronization achievement for contest starts with heterogeneous delays of competitors while satisfying other security requirements. As a complement, the analysis on the provable security of ASSR is given, as well as a further analysis on the achievement of synchronization.

Cyber-physical-social systems (CPSS), an emerging computing paradigm, have attracted intensive attentions from the research community and industry. We are facing various challenges in designing secure, reliable, and user-satisfied CPSS. In this article, we consider these design issues as a whole and propose a system-level design optimization framework for CPSS design where energy consumption, security-level, and user satisfaction requirements can be fulfilled while satisfying constraints for system reliability. Specifically, we model the constraints (energy efficiency, security, and reliability) as the penalty functions to be incorporated into the corresponding objective functions for the optimization problem. A smart office application is presented to demonstrate the feasibility and effectiveness of our proposed design optimization approach.

Cognitive radio significantly mitigates the spectrum scarcity for various applications built on wireless communication. Current techniques on mobile cognitive ad hoc networks (MCADNs), however, cannot be directly applied to time-critical applications due to channel interference, node mobility as well as unexpected primary user activities. In multichannel multiflow MCADNs, it becomes even worse because multiple links potentially interfere with each other. In this paper, we propose a delay-minimized routing (DMR) protocol for multichannel multiflow MCADNs. First, we formulate the DMR problem with the objective of delay minimization. Next, we propose a delay prediction model based on a conflict probability. Finally, we design the minimized path delay as a routing metric, and propose a heuristic joint routing and channel assignment algorithm to solve the DMR problem. Our DMR can find out the path with a minimal end-to-end (e2e) delay for time-critical data transmission. NS2-based simulation results demonstrate that our DMR protocol significantly outperforms related proposals in terms of average e2e delay, throughput, and packet loss rate.

With the rapid advances of sensing technologies and wireless communications, large amounts of dynamic data pertaining to industrial production are being collected from many sensor nodes deployed in the industrial Internet of Things. Analyzing those data effectively can help to improve the industrial services and mitigate the system unprepared breakdowns. As an important technique of data analysis, clustering attempts to find the underlying pattern structures embedded in unlabeled information. Unfortunately, most of the current clustering techniques that could only deal with static data become infeasible to cluster a significant volume of data in the dynamic industrial applications. To tackle this problem, an incremental clustering algorithm by fast finding and searching of density peaks based on k-mediods is proposed in this paper. In the proposed algorithm, two cluster operations, namely cluster creating and cluster merging, are defined to integrate the current pattern into the previous one for the final clustering result, and k-mediods is employed to modify the clustering centers according to the new arriving objects. Finally, experiments are conducted to validate the proposed scheme on three popular UCI datasets and two real datasets collected from industrial Internet of Things in terms of clustering accuracy and computational time.

Mobile opportunistic networking is a promising technology that can supplement existing cellular and WiFi networks to provide desirable services for smart and connected communities. Message routing is the most compelling challenge in mobile opportunistic networks due to the lack of contemporaneous end-to-end paths and the resource constraints at mobile devices. To improve the probability of successful message delivery, most existing routing schemes use the past contact history to predict future contacts for message forwarding, and exploit message replication and redundancy for multicopy routing. However, most existing prediction-based routing schemes simply use the average pairwise contact probability as the routing metric and neglect the benefits of exploring fine-grained contact information such as pairwise repeated contact patterns to improve the accuracy of predicting future contacts. Moreover, there is no efficient mechanism that can adaptively control message replication in a decentralized manner to achieve both high probability of successful message delivery and low message overhead. To address these problems, we present FGAR, a routing protocol designed for mobile opportunistic networks by leveraging fine-grained contact characterization and adaptive message replication. In FGAR, contact history is characterized in a fine-grained manner with timing information using a sliding window mechanism, and future contacts are predicted based on the fine-grained contact information, thereby improving the accuracy of contact prediction. We further design an efficient message replication scheme in which message replication is controlled in a fully decentralized manner by taking into account the expected message delivery probability, the replication history, and the quality of the encountered device. A replica is generated only when it is necessary to fulfill the expected message delivery probability. We evaluate our scheme through trace-driven simulations, and the simulation results show that FGAR outperforms existing schemes. In comparison with PRoPHET, FGAR can achieve more than 20% improvement on average on successful message delivery, whereas the message overhead has been reduced by a factor up to 15.

Recently, the deep computation model, as a tensor deep learning model, has achieved super performance for multimedia feature learning. However, the conventional deep computation model involves a large number of parameters. Typically, training a deep computation model with millions of parameters needs high-performance servers with large-scale memory and powerful computing units, limiting the growth of the model size for multimedia feature learning on common devices such as portable CPUs and conventional desktops. To tackle this problem, this article proposes a Tucker deep computation model by using the Tucker decomposition to compress the weight tensors in the full-connected layers for multimedia feature learning. Furthermore, a learning algorithm based on the back-propagation strategy is devised to train the parameters of the Tucker deep computation model. Finally, the performance of the Tucker deep computation model is evaluated by comparing with the conventional deep computation model on two representative multimedia datasets, that is, CUAVE and SNAE2, in terms of accuracy drop, parameter reduction, and speedup in the experiments. Results imply that the Tucker deep computation model can achieve a large-parameter reduction and speedup with a small accuracy drop for multimedia feature learning.

In mixed-criticality (MC) system, diverse application activities with various certification requirements (different criticality) can share a computing platform, where multicore processors have emerged as the prevailing computing engines. Focusing on the problem of resource access contention in multicore MC systems, we analyze the synchronization issues and blocking characteristics of the Multiprocessor Stack Resource Policy (MSRP) with both priority and criticality inversions among MC tasks being considered. We develop the first criticality-aware utilization bound under partitioned Earliest Deadline First (EDF) and MSRP by taking the worst case synchronization overheads of tasks into account. The non-monotonicityof the bound where it may decrease when more cores are deployed is identified, which can cause anomalies in the feasibility tests. With the objective to improve system schedulability, a novel criticality-cognizant and resource-oriented analysis approach is further studied to tighten the bound on the synchronization overheads for MC tasks scheduled under partitioned EDF and MSRP. The simulation results show that the new analysis approach can effectively reduce the blocking times for tasks (up to 30 percent) and thus improve the schedulability ratio (e.g., 10 percent more). The actual implementation in Linux kernel further shows the practicability of partitioned-EDF with MSRP (with run-time overhead being about 3 to 7 percent of the overall execution time) for MC tasks running on multicores with shared resources.

With the progressive development of information and communication technologies, we are now forming a new world called hyperworld that is composed by the cyber world and the physical world with various digital explosions including data, connectivity, service and intelligence. Therefore, Cyber-I has been proposed, which is a real individual's counterpart in cyberspace, and is to create a unique, digital, comprehensive description for every individual person. As similar to our human, a Cyber-I once born should be able to grow. Therefore, a Cyber-I's model must be a dynamic one, and can be built successively by utilizing an increasing amount of personal data with adaptive methods. Namely, a growable Cyber-I model is necessary to achieve the adaptation for successive approximations to its corresponding real individual (Real-I). This paper presents our research and development of an adaptable system, called Cyber-I growth modeling system (CGMS). This research is mainly to (1) schedule a Cyber-I's growth according to data and time; (2) manage the quantity of raw data that is involved in a specific growth process; (3) generate the Cyber-I model data with appropriate growth forms, and (4) keep the update records of a Cyber-I model's growth process into a log file in personal database.

Summary The deblocking filter inhigh‐efficiency video coding(HEVC) has huge computational complexity because of its high content‐adaptive coding structure as well as high‐definition. Parallelization for it based on massively parallel architectures such asgraphics processing unitbecomes an urgent demand. However, a large number of conditional branches and data dependencies severely hinder its efficient parallelization. In this paper, a novel parallel optimization strategy based on graphics processing unit is presented for concurrent deblocking in HEVC/H.265 standard to improve the parallel performance. First, by reducing various conditional branches, a normalization mechanism for instruction stream based on feature vector is proposed, which improves the efficiency of boundary strength computation dramatically. The idea can also be applied to edge discrimination. Second, a parallel mechanism based on an adaptive post‐correction is presented to process vertical and horizontal edges filtering concurrently, which improves the processing speed obviously, while producing negligible quality loss. Experimental results show that the strategy presented outperforms the existing state‐of‐the‐art method with accelerating factor up to 32. Copyright © 2016 John Wiley & Sons, Ltd.

Device-to-device (D2D) communication is a key enabler to facilitate the realization of the Internet of Things (IoT). In this paper, we study the deployment of D2D communications as an underlay to long-term evolution-advanced (LTE-A) networks based on novel architectures such as cloud radio access network (C-RAN). The challenge is that both energy efficiency (EE) and quality of service (QoS) are severely degraded by the strong intracell and intercell interference due to dense deployment and spectrum reuse. To tackle this problem, we propose an energy-efficient resource allocation algorithm through joint channel selection and power allocation design. The proposed algorithm has a hybrid structure that exploits the hybrid architecture of C-RAN: distributed remote radio heads (RRHs) and centralized baseband unit (BBU) pool. The distributed resource allocation problem is modeled as a noncooperative game, and each player optimizes its EE individually with the aid of distributed RRHs. We transform the nonconvex optimization problem into a convex one by applying constraint relaxation and nonlinear fractional programming. We propose a centralized interference mitigation algorithm to improve the QoS performance. The centralized algorithm consists of an interference cancellation technique and a transmission power constraint optimization technique, both of which are carried out in the centralized BBU pool. The achievable performance of the proposed algorithm is analyzed through simulations, and the implementation issues and complexity analysis are discussed in detail.

How to construct barrier coverage efficiently is a critical problem for many wireless sensor network applications, such as boundary surveillance and intrusion detection. In this paper, we study the belt barrier coverage in bistatic radar sensor networks. Much different from the disk and sector coverage, the coverage area of bistatic radar is dependent on the distance between a pair of radar transmitter and receiver. To improve coverage quality, we require to construct a belt barrier with the breadth not smaller than a predefined threshold. Furthermore, the unit cost of a radar transmitter may be different from a receiver. The bistatic radar placement problem is to construct a belt barrier with the minimum total placement cost. To solve the minimum cost placement problem, we propose a line-based equipartition placement strategy such that all radars placed on a deployment line can form a barrier with some breadth and one or more such placement lines can form a belt barrier with the required breadth. We first study the barrier property of different placement patterns on one deployment line, and prove the structure property of the optimal placement sequence on one deployment line. When multiple deployment lines are needed for belt barrier construction, we propose algorithms to find out the number of deployment lines and the number of receivers in the optimal placement pattern on each deployment line to minimize the total placement cost. The efficiency of the proposed algorithm is also validated by our simulation results.

To improve the efficiency of big data feature learning, the paper proposes a privacy preserving deep computation model by offloading the expensive operations to the cloud. Privacy concerns become evident because there are a large number of private data by various applications in the smart city, such as sensitive data of governments or proprietary information of enterprises. To protect the private data, the proposed model uses the BGV encryption scheme to encrypt the private data and employs cloud servers to perform the high-order back-propagation algorithm on the encrypted data efficiently for deep computation model training. Furthermore, the proposed scheme approximates the Sigmoid function as a polynomial function to support the secure computation of the activation function with the BGV encryption. In our scheme, only the encryption operations and the decryption operations are performed by the client while all the computation tasks are performed on the cloud. Experimental results show that our scheme is improved by approximately 2.5 times in the training efficiency compared to the conventional deep computation model without disclosing the private data using the cloud computing including ten nodes. More importantly, our scheme is highly scalable by employing more cloud servers, which is particularly suitable for big data.

Cyber-physical systems (CPSs) have recently become an important research field not only because of their important and varied application scenarios, including transportation systems, smart homes, surveillance systems, and wearable devices but also because the fundamental infrastructure has yet to be well addressed. Wireless sensor networks (WSNs), as a type of supporting infrastructure, play an irreplaceable role in CPS design. Specifically, secure communication in WSNs is vital because information transferred in the networks can be easily stolen or replaced. Therefore, this paper presents a novel distributed low-storage clone detection protocol (LSCD) for WSNs. We first design a detection route along the perpendicular direction of a witness path with witness nodes deployed in a ring path. This ensures that the detection route must encounter the witness path because the distance between any two detection routes must be smaller than the witness path length. In the LSCD protocol, clone detection is processed in a nonhotspot region where a large amount of energy remains, which can improve energy efficiency as well as network lifetime. Extensive simulations demonstrate that the lifetime, storage requirements, and detection probability of our protocol are substantially improved over competing solutions from the literature.

Cooperative data delivery among mobile nodes can improve the performance of data delivery in mobile social networks. However, data routing in the presence of socially selfish (SS) nodes is challenging, where they mitigate the degree of their cooperation level based on their social features and ties to achieve their social objectives. This issue becomes more challenging when they prevent revealing their reactions about incoming messages, which leads data forwarding under uncertain behavior. In this paper, we propose a signaling game approach, namely, Sig4UDD, to study the impact of uncertain cooperation among well-behaved and SS nodes on the performance of data forwarding. In Sig4UDD, we employ Bayesian Nash equilibrium to analyze one-stage interactions among nodes. Then, perfect Bayesian equilibrium is applied to analyze their multistage interactions. In this stage, we establish a belief system to help SS nodes predict the type of their opponents and take appropriate actions to maximize their utilities. To update the beliefs of SS nodes, we devised the weighted social distance metric to measure the global social distance among nodes. Finally, we compare the performance of Sig4UDD to some benchmark cooperative and noncooperative data forwarding protocols using Reality Mining and Social Evolution data sets.

The design of cyber-physical-social systems (CPSS) is a novel and challenging research field due that it emphasizes the deep fusion of cyberspace, physical space, and social space. In this article, we extend our previously proposed system-level design framework [Zeng et al. 2015] to tailor it to the needs of social scenario of multiple users. A hierarchical Petri net-based model and social flow are presented to extend the control flow and formally describe the social interactions of multiple users, respectively. By using the extended model, the system-level optimization for CPSS can be achieved by the improved design flow. Specifically, object emplacement and user satisfaction are further extended into the social environment. Also maximal power estimation algorithm is improved, leveraging the extended intermediate representation model. Finally, we use a smart office case to demonstrate the feasibility and effectiveness of our improved design approach for multiple users.

During past decades, the capacity of NAND flash memory has been increasing dramatically, leading to the use of nonvolatile flash in the system’s memory hierarchy. The increasing capacity of NAND flash memory introduces a large RAM footprint to store the logical to physical address mapping. The demand-based approach can effectively reduce and well control the RAM footprint. However, extra address translation overhead is also introduced which may degrade the system performance. In this article, we present CDFTL, an adaptive Caching mechanism for Demand-based Flash Translation Layer, for NAND flash memory storage systems. CDFTL adopts both the fine-grained entry-based caching mechanism to exploit temporal locality and the coarse-grained translation-page-based caching mechanism to exploit spatial locality of workloads. By selectively caching the on-demand address mappings and adaptively changing the space configurations of two granularities, CDFTL can effectively utilize the RAM space and improve the cache hit ratio. We evaluate CDFTL under a real hardware embedded platform using a variety of I/O traces. Experimental results show that our technique can achieve an 11.13% reduction in average system response time and a 35.21% reduction in translation block erase counts compared with the previous work.

Multimedia has been exponentially increasing as the biggest big data, which consist of video clips, images, and audio files. Processing and analyzing them on a cloud data center have become a preferred solution that can utilize the large pool of cloud resources to address the problems caused by the tremendous amount of unstructured multimedia data. However, there exist many challenges in processing multimedia big data on a cloud data center, such as multimedia data representation approach, an efficient networking model, and an estimation method for traffic patterns. The primary purpose of this article is to develop a novel tensor-based software-defined networking model on a cloud data center for multimedia big-data computation and communication. First, an overview of the proposed framework is provided, in which the functions of the representative modules are briefly illustrated. Then, three models,—forwarding tensor, control tensor, and transition tensor—are proposed for management of networking devices and prediction of network traffic patterns. Finally, two algorithms about single-mode and multimode tensor eigen-decomposition are developed, and the incremental method is employed for efficiently updating the generated eigen-vector and eigen-tensor. Experimental results reveal that the proposed framework is feasible and efficient to handle multimedia big data on a cloud data center.