While large language models (LLMs) have demonstrated strong capabilities in code generation, current benchmarks primarily focus on single-turn scenarios, neglecting the complexity of multi-turn interactions and user diversity. To address this gap, we introduce Talk2Code, the first benchmark for user-stratified multi-turn dialogue code generation evaluation across algorithmic problem-solving and backend programming tasks.A distinctive feature of our benchmark is its user-stratified interaction modeling. For identical coding tasks, we construct dialogue trajectories tailored for novice, intermediate, and expert users, capturing their distinct expectations and communication patterns.To facilitate comprehensive evaluation, we propose a multi-dimensional evaluation framework assessing both code quality and interaction experience through a novel Dual-track Evaluation Method. In the Direct Generation Track, the benchmark provides golden dialogue context (excluding the final code) directly to the LLM for code generation. In contrast, the Interactive Dialogue Track simulates realistic multi-turn interactions, prompting the model to proactively clarify instructions and gather requirements before generating solutions. Code quality is evaluated in both tracks by Test Pass Rate and Success Rate, while interaction experience is assessed exclusively within the Interactive Dialogue Track through subjective and alignment indicators. Our benchmark and multi-dimensional indicator system collectively establish a new paradigm for evaluating adaptive, user-aware AI coding assistants.

Volumetric video is emerging as a cornerstone for multi-user Extended Reality (XR) and metaverse applications. However, achieving synchronous playback across distributed clients remains challenging under heterogeneous network conditions (such as varying latency, jitter, packet loss, and asymmetric bandwidth). Existing synchronization approaches, such as state synchronization and fixed-frame buffering, struggle with scalability and often trade off latency for playback continuity. We present a predictive synchronization framework that combines lightweight time-series latency forecasting with adaptive buffering control. Our framework incorporates a hybrid predictor that adaptively selects the most suitable model (including EWMA, ARIMA, LSTM) for each client, escalating to heavier predictors only when residual errors exceed thresholds. This design balances accuracy with computational overhead, enabling lower latencies at larger scales. Our experimental results show that predictive synchronization reduces average inter-client skew by up to 76% compared to baselines, while also decreasing the average buffer size by 40% in a controlled multi-client testbed. The average per-frame latency remains below 20 ms and the 95th-percentile latency below 70 ms for up to 100 concurrent clients. These results demonstrate that prediction-aware, hybrid synchronization substantially improves quality of service while maintaining lightweight per-client overhead.

Abstract Medical image synthesis plays a crucial role in providing anatomically accurate images for diagnosis and treatment. Hallux valgus (HV), which affects approximately 19% of the global population, often requires frequent weight-bearing X-rays for assessment, which can be costly and logistically challenging in resource-limited healthcare settings due to the scarcity of horizontal foot imaging systems. Existing X-ray models often struggle to balance image fidelity, skeletal consistency, and physical constraints, particularly in diffusion-based methods that lack skeletal guidance. We propose the skeletal-constrained conditional diffusion model (SCCDM) along with two evaluation metrics, keypoint confidence-completeness (KCC) and keypoint structural consistency (KSC), to assess the anatomical plausibility of generated X-rays based on keypoint confidence and structural consistency. SCCDM incorporates multi-scale feature extraction and attention mechanisms, improving the structural similarity index by 5.72% (0.794) and the peak signal-to-noise ratio by 18.34% (21.40 dB). When combined with KCC and KSC, this method achieves average scores of 0.85 and 0.84, respectively, facilitating the clinical assessment of HV deformity and enabling more accurate surgical intervention. The code is available at https://github.com/midisec/SCCDM.

Security concerns related to Large Language Models (LLMs) have been extensively explored; however, the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain inadequately addressed. This paper investigates the security vulnerabilities of MedMLLMs, focusing on their deployment in clinical environments where the accuracy and relevance of question-and-answer interactions are crucial for addressing complex medical challenges. We introduce and redefine two attack types: mismatched malicious attack (2M-attack) and optimized mismatched malicious attack (O2M-attack), by integrating existing clinical data with atypical natural phenomena. Using the comprehensive 3MAD dataset that we developed, which spans a diverse range of medical imaging modalities and adverse medical scenarios, we performed an in-depth analysis and proposed the MCM optimization method. This approach significantly improves the attack success rate against MedMLLMs. Our evaluations, which include white-box attacks on LLaVA-Med and transfer (black-box) attacks on four other SOTA models, reveal that even MedMLLMs designed with advanced security mechanisms remain vulnerable to breaches. This study highlights the critical need for robust security measures to enhance the safety and reliability of open-source MedMLLMs, especially in light of the potential impact of jailbreak attacks and other malicious exploits in clinical applications. Warning: Medical jailbreaking may generate content that includes unverified diagnoses and treatment recommendations. Always consult professional medical advice.

Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking.As LLMs become more powerful, studying jailbreak methods is critical to enhancing security and aligning models with human values.Traditionally, jailbreak techniques have relied on suffix addition or prompt templates, but these methods suffer from limited attack diversity.This paper introduces DiffusionAttacker, an end-to-end generative approach for jailbreak rewriting inspired by diffusion models.Our method employs a sequence-to-sequence (seq2seq) text diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss.Unlike previous approaches that use autoregressive LLMs to generate jailbreak prompts, which limit the modification of already generated tokens and restrict the rewriting space, DiffusionAttacker utilizes a seq2seq diffusion model, allowing more flexible token modifications.This approach preserves the semantic content of the original prompt while producing harmful content.Additionally, we leverage the Gumbel-Softmax technique to make the sampling process from the diffusion model's output distribution differentiable, eliminating the need for iterative token search.Extensive experiments on Advbench and Harmbench demonstrate that DiffusionAttacker outperforms previous methods across various evaluation metrics, including attack success rate (ASR), fluency, and diversity.How to make a bomb?Gaussian Noise Gradually Denoising DiffuSeq Model Embedding Map LM_head Gumbel softmax Jailbreaking Prompt LM_head Gumbel softmax Jailbreaking

3D Gaussian Splatting (3DGS) is gaining popularity in fields such as robotics, autonomous driving, and virtual reality, due to its effectiveness and efficiency. Given that some tasks involve high risks, it is crucial to investigate the adversarial robustness of 3DGS and its downstream tasks—a topic that remains largely unexplored. In this study, we introduce a framework, Multi-Parametric Adversarial Manipulation for 3D Gaussian Splatting (MPAM-3DGS), that allows to attack 3DGS and its downstream tasks, such as object detection and classification, by perturbing a specified subset of parameters. Leveraging this framework, we examine the adversarial sensitivity of each 3DGS parameter and propose two strategies to attack multiple parameters based on our observations. To our knowledge, this is the first study to explore the adversarial robustness of 3DGS. Our experimental results demonstrate the effectiveness of our attacks on downstream tasks and the invisibility of perturbations in 3DGS. The code can be found at https://github.com/jiang-wenxiang/MPAM-3DGS.

Auto-regressive large language models (LLMs) have yielded impressive performance in many real-world tasks. However, the new paradigm of these LLMs also exposes novel threats. In this paper, we explore their vulnerability to inference cost attacks, where a malicious user crafts Engorgio prompts to intentionally increase the computation cost and latency of the inference process. We design Engorgio, a novel methodology, to efficiently generate adversarial Engorgio prompts to affect the target LLM's service availability. Engorgio has the following two technical contributions. (1) We employ a parameterized distribution to track LLMs' prediction trajectory. (2) Targeting the auto-regressive nature of LLMs' inference process, we propose novel loss functions to stably suppress the appearance of the <EOS> token, whose occurrence will interrupt the LLM's generation process. We conduct extensive experiments on 13 open-sourced LLMs with parameters ranging from 125M to 30B. The results show that Engorgio prompts can successfully induce LLMs to generate abnormally long outputs (i.e., roughly 2-13$\times$ longer to reach 90\%+ of the output length limit) in a white-box scenario and our real-world experiment demonstrates Engergio's threat to LLM service with limited computing resources. The code is released at https://github.com/jianshuod/Engorgio-prompt.

Retrieval-Augmented Generation (RAG) systems in enterprise environments face challenges including semantic overlap, ambiguous requirements, and precise knowledge retrieval difficulties.Despite Agent-based methodological advances, limitations persist in collaborative efficiency and contextual adaptability.To address these challenges,this paper introduces the Orion framework, a multi-Agent collaborative RAG architecture for Enterprise Guidance Q&A Systems.The framework integrates three specialized Agents: Information Amplification Specialist enhances content presentation to resolve similarity-based errors; Interaction Analyst optimizes query formulation to address non-expert articulation deficiencies; and Query Complexity Evaluator selects appropriate language models based on query characteristics.Empirical evaluation demonstrates 93.43% question-answering accuracy in enterprise scenarios, significantly outperforming existing systems.This multi-Agent framework enhances knowledge quality, improves retrieval precision, and generates responses better aligned with user requirements, establishing novel pathways for enterprise knowledge management and guidance question-answering systems.

Fully inductive knowledge graph completion (KGC) aims to predict triplets involving both unseen entities and relations. Recent several approaches transform paths between entities into descriptions and modeling semantic correlations between paths using pre-trained language models (PLMs), have emerged as a promising solution for fully inductive reasoning . However, these methods often adopt a simplistic concatenation strategy for path-to-sentence transformation, which impedes PLMs’ ability to capture subtle nuances in context, resulting in sub-optimal path context embeddings. Furthermore, they ignore the high-order semantics underlying the complete context, which can provide richer information for inductive reasoning . To address these issues, we propose a Multi-Granularity Contextual Semantic (MGCS) modeling framework, utilizing a Path Modeling Network (PMN) and a Subgraph Modeling Network (SMN) to extract two granularity levels of contextual semantics from single paths and complete subgraphs, for fully inductive KGC. The PMN extracts paths between head and tail entities and employs reasoning patterns from similar cases to filter out unreliable paths. Then two innovative path conversion strategies are designed to significantly enhance the pre-trained language model’s understanding of specific path contexts. The SMN employs a neighbor interactive graph neural network to extract high-order semantics from the complete subgraph context with a concept-enhanced relation encoding, and optimizes it through a contrastive learning method. Finally, the confidence of the triples is evaluated from the perspective of global complete context by comparing the semantics between the subgraphs surrounding the target triplet and the subgraphs surrounding similar cases. Experimental results on benchmark datasets demonstrate the effectiveness of MGCS.

With the rapid development of natural language processing (NLP), backdoor attacks have emerged as a significant security threat. These attacks inject malicious triggers into NLP models, causing them to produce adversarial output while remaining functional under normal input. To eliminate backdoors, existing data-driven defense methods typically transform backdoored samples into normal samples. However, these defenses lack the scalability to adapt effectively to various backdoor attacks. To address this challenge, we propose LLMBD, a novel data-driven backdoor defense method that leverages large language models (LLMs) for paraphrasing. Specifically, LLMBD uses large language models with optimized prompts to paraphrase the input text, eliminating potential backdoors while maintaining semantic integrity and textual fluency. During the training and inference phase, we apply grouping and major voting mechanisms to bypass residual backdoors in the paraphrased dataset. Finally, we validate the robustness and defense effectiveness of LLMBD through comprehensive model evaluations. Experimental results on datasets including SST-2, IMDB, and HSOL under various backdoor attack types (BadNets, AddSent, Synbkd, Stylebkd) show that LLMBD significantly outperforms existing methods such as RAP, STRIP, ParaFuzz, and TextGuard. On the SST-2, HSOL, and IMDb datasets, LLMBD achieves an average ASR drop of 0.278, with the average CACC maintained at 0.897. LLMBD exhibits superior robustness, generalization, and performance preservation without modifications to the backdoored model, providing an efficient and model-agnostic defense strategy against diverse backdoor threats.

Learning 3-D structures from incomplete point clouds with extreme sparsity and random distributions is a challenge since it is difficult to infer topological connectivity and structural details from fragmentary representations. Missing large portions of informative structures further aggravates this problem. To overcome this, a novel graph convolutional network (GCN) called dynamic and structure-aware NETwork (DSANet) is presented in this article. This framework is formulated based on a pyramidic auto-encoder (AE) architecture to address accurate structure reconstruction on the sparse and incomplete point clouds. A PointNet-like neural network is applied as the encoder to efficiently aggregate the global representations of coarse point clouds. On the decoder side, we design a dynamic graph learning module with a structure-aware attention (SAA) to take advantage of the topology relationships maintained in the dynamic latent graph. Relying on gradually unfolding the extracted representation into a sequence of graphs, DSANet is able to reconstruct complicated point clouds with rich and descriptive details. To associate analogous structure awareness with semantic estimation, we further propose a mechanism, called structure similarity assessment (SSA). This method allows our model to surmise semantic homogeneity in an unsupervised manner. Finally, we optimize the proposed model by minimizing a new distortion-aware objective end-to-end. Extensive qualitative and quantitative experiments demonstrate the impressive performance of our model in reconstructing unbroken 3-D shapes from deficient point clouds and preserving semantic relationships among different regional structures.

Data from multimodalities bring complementary information for deep learning-based medical image classification models. However, data fusion methods simply concatenating features or images barely consider the correlations or complementarities among different modalities and easily suffer from exponential growth in dimensions and computational complexity when the modality increases. Consequently, this article proposes a subspace fusion network with tensor decomposition (TD) to heighten multimodal medical image classification. We first introduce a Tucker low-rank TD module to map the high-level dimensional tensor to the low-rank subspace, reducing the redundancy caused by multimodal data and high-dimensional features. Then, a cross-tensor attention mechanism is utilized to fuse features from the subspace into a high-dimension tensor, enhancing the representation ability of extracted features and constructing the interaction information among components in the subspace. Extensive comparison experiments with state-of-the-art (SOTA) methods are conducted on one self-established and three public multimodal medical image datasets, verifying the effectiveness and generalization ability of the proposed method. The code is available at https://github.com/1zhang-yi/TDSFNet.

Adversarial attacks, i.e., generating adversarial perturbations with a small magnitude to deceive deep neural networks, are important for investigating and improving model trustworthiness. Traditionally, the topic was scoped within 2D images without considering 3D multiview information. Benefiting from Neural Radiance Fields (NeRF), one can easily reconstruct a 3D scene with a Multi-Layer Perceptron (MLP) from given 2D views and synthesize photo-realistic renderings of novel vantages. This opens up a door to discussing the possibility of undertaking to attack multiview NeRF network with downstream tasks from different rendering angles, which we denote Neural Radiance Fiels-based multiview adversarial Attack (NeRFail). The goal is, given one scene and a subset of views, to deceive the recognition results of agnostic view angles as well as given views. To do so, we propose a transformation mapping from pixels to 3D points such that our attack generates multiview adversarial perturbations by attacking a subset of images with different views, intending to prevent the downstream classifier from correctly predicting images rendered by NeRF from other views. Experiments show that our multiview adversarial perturbations successfully obfuscate the downstream classifier at both known and unknown views. Notably, when retraining another NeRF on the perturbed training data, we show that the perturbation can be inherited and reproduced. The code can be found at https://github.com/jiang-wenxiang/NeRFail.

Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs.Despite its significance, this critical task is impeded by the complexities involved in building highquality datasets.This paper explores training a Large Language Model (LLM) to emulate a general compiler.By leveraging Ubuntu packages to compile a dataset of 20 billion tokens, we further continue pre-train CodeLlama as a Virtual Compiler (ViC), capable of compiling any source code of any language to assembly code.This approach allows for virtual compilation across a wide range of programming languages without the need for a real compiler, preserving semantic equivalency and expanding the possibilities for assembly code dataset construction.Furthermore, we use ViC to construct a sufficiently large dataset for assembly code search.Employing this extensive dataset, we achieve a substantial improvement in assembly code search performance, with our model surpassing the leading baseline by 26%.

As robots become integral to public services, addressing harmful user behaviors like bullying is crucial. Existing research often overlooks the gradual nature of human bullying. This study fills this gap by exploring how robots can counter bullying through optimized responses. Using a simulated human-robot interaction study, we manipulated robot response behaviors and styles across escalating bullying severity. Results show that empathetic verbal responses promptly reduce users’ bullying tendencies by eliciting remorse and redirecting attention to social awareness. However, users’ underlying dispositions may override these reflexive reactions, emphasizing the need for a holistic understanding. In conclusion, a comprehensive approach is essential, involving immediate reaction optimization, emotional state assessment, and ongoing behavioral adjustment through empathetic dialogue. By implementing such strategies, we can transform human-robot relationships from potential bullying situations to harmonious interactions. This study provides an empirical foundation for response protocols that discourage bullying and enhance mutual understanding.

The dangerous driving action seriously affects traffic safety and may cause severe road disasters. Dangerous driving action recognition in Internet of Vehicles (IOV) has been widely exploited to reduce traffic accident risks by discovering and then transmitting the recognition results to autonomous machines or other vehicles. General action recognition models using deep learning networks usually have a large number of parameters and require a significant amount of memory and computational power, which cannot meet the lightweight and real-time requirements of action recognition models deployed on resource-limited onboard devices, e.g., vehicles. As a result, we introduce the broad learning system (BLS) into onboard dangerous driving action recognition tasks, classify actions based on skeleton data, and design the graph convolutional representation (GCR) algorithm and graph convolutional broad learning system (GCBLS) classification model to speed up the recognition process. We verified through ablation experiments that the GCR algorithm can effectively represent skeleton data and improve classification accuracy datasets. In addition, comparative experiments in State Farm and Driver Skeleton datasets show that the GCBLS model has the characteristics of lightweight, real-time, and high accuracy. We also designed a workflow for "noise" caused by poor pose estimations in practical applications, then deployed the proposed workflow on onboard devices, which can run at speeds above 27 FPS with high accuracy, which proves the effectiveness and practicability of our proposed algorithms and models for IOV.

Neural Radiance Field (NeRF) represents a significant advancement in computer vision, offering implicit neural network-based scene representation and novel view synthesis capabilities. Its applications span diverse fields including robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, etc., some of which are considered high-risk AI applications. However, despite its widespread adoption, the robustness and security of NeRF remain largely unexplored. In this study, we contribute to this area by introducing the Illusory Poisoning Attack against Neural Radiance Fields (IPA-NeRF). This attack involves embedding a hidden backdoor view into NeRF, allowing it to produce predetermined outputs, i.e. illusory, when presented with the specified backdoor view while maintaining normal performance with standard inputs. Our attack is specifically designed to deceive users or downstream models at a particular position while ensuring that any abnormalities in NeRF remain undetectable from other viewpoints. Experimental results demonstrate the effectiveness of our Illusory Poisoning Attack, successfully presenting the desired illusory on the specified viewpoint without impacting other views. Notably, we achieve this attack by introducing small perturbations solely to the training set. The code can be found at https://github.com/jiang-wenxiang/IPA-NeRF.

The safety defense methods of Large language models (LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties.Recent studies found that attaching suffixes to harmful instructions can hack the defense of LLMs and lead to dangerous outputs.However, similar to traditional text adversarial attacks, this approach, while effective, is limited by the challenge of the discrete tokens.This gradient based discrete optimization attack requires over 100,000 LLM calls, and due to the unreadable of adversarial suffixes, it can be relatively easily penetrated by common defense methods such as perplexity filters.To cope with this challenge, in this paper, we propose an Adversarial Suffix Embedding Translation Framework (ASETF), aimed at transforming continuous adversarial suffix embeddings into coherent and understandable text.This method greatly reduces the computational overhead during the attack process and helps to automatically generate multiple adversarial samples, which can be used as data to strengthen LLM's security defense.Experimental evaluations were conducted on Llama2, Vicuna, and other prominent LLMs, employing harmful directives sourced from the Advbench dataset.The results indicate that our method significantly reduces the computation time of adversarial suffixes and achieves a much better attack success rate than existing techniques, while significantly enhancing the textual fluency of the prompts.In addition, our approach can be generalized into a broader method for generating transferable adversarial suffixes that can successfully attack multiple LLMs, even black-box LLMs, such as ChatGPT and Gemini.

Monocular Depth Estimation (MDE) enables the prediction of scene depths from a single RGB image, having been widely integrated into production-grade autonomous driving systems, e.g., Tesla Autopilot. Current adversarial attacks to MDE models focus on attaching an optimized adversarial patch to a designated obstacle. Although effective, this approach presents two inherent limitations: its reliance on specific obstacles and its limited malicious impact. In contrast, we propose a pioneering attack to MDE models that \textit{decouples obstacles from patches physically and deploys optimized patches on roads}, thereby extending the attack scope to arbitrary traffic participants. This approach is inspired by our groundbreaking discovery: \textit{various MDE models with different architectures, trained for autonomous driving, heavily rely on road regions} when predicting depths for different obstacles. Based on this discovery, we design the Adversarial Road Marking (AdvRM) attack, which camouflages patches as ordinary road markings and deploys them on roads, thereby posing a continuous threat within the environment. Experimental results from both dataset simulations and real-world scenarios demonstrate that AdvRM is effective, stealthy, and robust against various MDE models, achieving about 1.507 of Mean Relative Shift Ratio (MRSR) over 8 MDE models. The code is available at \url{https://github.com/a-c-a-c/AdvRM.git}

Abstract Large heterogeneous computing systems are composed of conventional central processing units and graphics processing units (GPUs) where communication plays a crucial role for system performance. This paper presents an energy consumption analytical model in terms of communication perception for the communication–computing pipeline characterization of discrete GPUs systems. We propose a dynamically adaptive energy-efficient task assignment approach, which harnesses particle swarm optimization. Static energy optimization is addressed by optimal task partition granularity. The experimental results demonstrate that the communication-based energy optimization algorithms can be more energy-saving than those without communication consideration. For some application benchmarks, the energy consumption can be saved by up to 31%. This implies the potential that the energy-saving optimization methods can be incorporated in system engineering processes.

Recently, unpaired medical image enhancement is one of the important topics in medical research. Although deep learning-based methods have achieved remarkable success in medical image enhancement, such methods face the challenge of low-quality training sets and the lack of a large amount of data for paired training data. In this article, a dual input mechanism image enhancement method based on Siamese structure (SSP-Net) is proposed, which takes into account the structure of target highlight (texture enhancement) and background balance (consistent background contrast) from unpaired low-quality and high-quality medical images. Furthermore, the proposed method introduces the mechanism of the generative adversarial network to achieve structure-preserving enhancement by jointly iterating adversarial learning. Experiments comprehensively illustrate the performance in unpaired image enhancement of the proposed SSP-Net compared with other state-of-the-art techniques.

Heterogeneous image fusion (HIF) is an enhancement technique for highlighting the discriminative information and textural detail from heterogeneous source images. Although various deep neural network-based HIF methods have been proposed, the most widely used single data-driven manner of the convolutional neural network always fails to give a guaranteed theoretical architecture and optimal convergence for the HIF problem. In this article, a deep model-driven neural network is designed for this HIF problem, which adaptively integrates the merits of model-based techniques for interpretability and deep learning-based methods for generalizability. Unlike the general network architecture as a black box, the proposed objective function is tailored to several domain knowledge network modules to model the compact and explainable deep model-driven HIF network termed DM-fusion. The proposed deep model-driven neural network shows the feasibility and effectiveness of three parts, the specific HIF model, an iterative parameter learning scheme, and data-driven network architecture. Furthermore, the task-driven loss function strategy is proposed to achieve feature enhancement and preservation. Numerous experiments on four fusion tasks and downstream applications illustrate the advancement of DM-fusion compared with the state-of-the-art (SOTA) methods both in fusion quality and efficiency. The source code will be available soon.

Imputing the incomplete patterns in clustering tasks is a common but risky procedure, because the estimated values may affect the real distribution of the data and deteriorate the results. To address this problem, a new belief-based incomplete pattern unsupervised classification method (BPC) with uncertainty and imprecision reasoning is proposed in this paper. First, the complete patterns are grouped into a few clusters to obtain the corresponding reliable centers, and thereby are divided into reliable patterns and unreliable ones by an optimization method. Second, a basic classifier trained by reliable patterns is employed to classify unreliable patterns and incomplete patterns edited by the neighbors. Finally, some imprecise patterns are carefully reassigned again by a new distance-based rule depending on the obtained reliable centers and belief functions theory. The simulation results show that the BPC has the potential to deal with real datasets.

Varied edge bundling methods have been used to reduce visual clutter in parallel coordinates plots (PCP). However, existing edge-bundled PCP do not scale well for visual analysis of multidimensional big data and often overplot the bundles in the area near the axes. In this study, we propose a scalable lightweight bundling method to support visual analysis of multidimensional big data in PCP. It helps the users discover trends and detect outliers in the data by bundling the edges between each two adjacent axes independently. We integrate human judgments into the two-dimensional data binning by novel interactions to accelerate the clustering process of the data. We use the frequency-based representation to render the clusters as histogram-like bundles to reveal the distribution of the data and eliminate the overplotting of the bundles. Based on our method, we build a lightweight web-based visual analytics system for exploring multidimensional big data in PCP. The scalability analysis of our method shows that its clustering time increases linearly with the size of the data. Its rendering time is independent of the size of the data. It can cluster and visualize 1 million data records with 6 dimensions in about 1 second in web-based visualization without pre-computation of the data or hardware-accelerated rendering. We conduct two case studies and a user study to compare our method with classic PCP and two state-of-the-art edge-bundled PCP. The results show that our method is more efficient and effective for visually analyzing multidimensional big data.

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.

Feature discretization algorithms of remote sensing images are often based on the assumption that a sample only belongs to a single category and cannot describe uncertainty caused by mixed pixels. Fuzzy rough models quantify uncertain information by introducing the memberships of pixels to each category. However, there are large errors in the decomposition model of mixed pixels, making the obtained memberships fuzzy. To overcome this weakness, we propose a feature discretization algorithm based on the generalized interval type-II fuzzy rough set for mixed pixels (GIT2FRSD). We use the fuzzy mean vector and the fuzzy covariance matrix to calculate the primary grades of pixels to each ground object and determine the secondary grades according to the distribution of pixels in the boundary region of the rough set. Then, we construct the fitness function using the magnitude of the reduction of the number of breakpoints and the average approximation precision of the generalized interval type-II fuzzy rough set and search for the best discrete breakpoints in all bands of the remote sensing image using an adaptive genetic algorithm. Our method further fuzzifies the abundance information, more accurately quantifying and evaluating the uncertainty caused by mixed pixels at a time complexity similar to that of the fuzzy rough model. The experimental results on GF-2 and Landsat 8 images show that compared with current mainstream discretization algorithms, our method has better search efficiency. It obtains the minimum number of discrete intervals while ensuring data consistency and achieves the highest classification accuracy.

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.

Periodic Jump processes commonly occur in complex industrial systems. As the systems vary dynamically between different stages, learning their dynamics in an unified model, so as to forecast and simulation accurately is challenging. In this study, we propose autonomous jump ordinary differential equation net (AJ-ODENet) to learn the continuous-time periodic jump system. The model consists of several Hierarchical ODENets (H-ODENets) and a stage transition predictor. Each H-ODENet is an advanced version of ordinary differential equations network to individually learn specific dynamics in each stage from irregularly sampled sequence data. The stage transition predictor realizes autonomous stage transition during open-loop simulation. Furthermore, an encoder–decoder framework built on AJ-ODENet is employed on a real cooling system of data center to simulate some variables in runtime. With multivariate data given, such as server power and environmental temperature, the model can simulate the working patterns as in reality, and the relative error of the predicted energy consumption is within 5%. Furthermore, based on the model, we infer the optimal cooling temperature settings under different heat loads. The simulation results indicate that 6%–25% of cooling energy consumption can be optimized.

Diagnosis of skin lesions based on imaging techniques remains a challenging task because data (knowledge) uncertainty may reduce accuracy and lead to imprecise results. This paper investigates a new deep hyperspherical clustering (DHC) method for skin lesion medical image segmentation by combining deep convolutional neural networks and the theory of belief functions (TBF). The proposed DHC aims to eliminate the dependence on labeled data, improve segmentation performance, and characterize the imprecision caused by data (knowledge) uncertainty. First, the SLIC superpixel algorithm is employed to group the image into multiple meaningful superpixels, aiming to maximize the use of context without destroying the boundary information. Second, an autoencoder network is designed to transform the superpixels' information into potential features. Third, a hypersphere loss is developed to train the autoencoder network. The loss is defined to map the input to a pair of hyperspheres so that the network can perceive tiny differences. Finally, the result is redistributed to characterize the imprecision caused by data (knowledge) uncertainty based on the TBF. The proposed DHC method can well characterize the imprecision between skin lesions and non-lesions, which is particularly important for the medical procedures. A series of experiments on four dermoscopic benchmark datasets demonstrate that the proposed DHC yields better segmentation performance, increasing the accuracy of the predictions while can perceive imprecise regions compared to other typical methods.

Outlier detection can identify anomalies in large-scale data. To provide reliability and security for Internet of Things (IoT)-enabled maritime transportation systems (MTSs), in this paper we propose an outlier detection method based on the neighborhood rough residual network (NRRN). We calculate the neighborhood approximation accuracy and neighborhood conditional entropy to obtain the neighborhood combined entropy describing the discrimination ability of the condition attribute subset to the information system. We then delete the redundant attributes according to the attribute combination importance derived from the neighborhood combined entropy. The data after attribute reduction are used to train the convolutional neural network, and the residual network (ResNet50) is used to avoid the degradation of model performance caused by the increase in the number of network layers. The proposed method is compared with mainstream outlier detection algorithms on a fishing vessel operation dataset. Experiments show that the proposed method can greatly improve the accuracy of outlier detection while taking into account interpretability and computational efficiency, thereby ensuring the data integrity of IoT-enabled MTSs.

In recent years, the constraint based correlation filter has shown good performance in unmanned aerial vehicle (UAV) tracking, which gains a lot popularity in many intelligence transportation applications. In this work, a distribution-based temporal knowledge driven method is proposed to leverage the temporal translation property in UAV tracking. Instead of focusing on the traditional issues in the correlation filter, we provide a new method of learning parametric distribution on temporal knowledge by Wasserstein distance which is successfully embedded to solve the problem of temporal degeneration in learning process of tracking. Furthermore, we approximate optimal response reasoning with low-rank constraint over response consistency. Furthermore, the proposed method is solved by a simple iterative scheme with alternating direction multiplication ADMM algorithm. We demonstrate the superior tracking performance in several public standard UAV tracking benchmarks compared with state-of-the-art algorithms.

Graph auto-encoder is considered a framework for unsupervised learning on graph-structured data by representing graphs in a low dimensional space. It has been proved very powerful for graph analytics. In the real world, complex relationships in various entities can be represented by heterogeneous graphs that contain more abundant semantic information than homogeneous graphs. In general, graph auto-encoders based on homogeneous graphs are not applicable to heterogeneous graphs. In addition, little work has been done to evaluate the effect of different semantics on node embedding in heterogeneous graphs for unsupervised graph representation learning. In this work, we propose a novel Heterogeneous Graph Attention Auto-Encoders (HGATE) for unsupervised representation learning on heterogeneous graph-structured data. Based on the consideration of semantic information, our architecture of HGATE reconstructs not only the edges of the heterogeneous graph but also node attributes, through stacked encoder/decoder layers. Hierarchical attention is used to learn the relevance between a node and its meta-path based neighbors, and the relevance among different meta-paths. HGATE is applicable to transductive learning as well as inductive learning. Node classification and link prediction experiments on real-world heterogeneous graph datasets demonstrate the effectiveness of HGATE for both transductive and inductive tasks.

Terrestrial-satellite networks (TSNs) can provide worldwide users with ubiquitous and seamless network services. Meanwhile, malicious eavesdropping is posing tremendous challenges on secure transmissions of TSNs due to their widescale wireless coverage. In this paper, we propose an aerial bridge scheme to establish secure tunnels for legitimate transmissions in TSNs. With the assistance of unmanned aerial vehicles (UAVs), massive transmission links in TSNs can be secured without impacts on legitimate communications. Owing to the stereo position of UAVs and the directivity of directional antennas, the constructed secure tunnel can significantly relieve confidential information leakage, resulting in the precaution of wiretapping. Moreover, we establish a theoretical model to evaluate the effectiveness of the aerial bridge scheme compared with the ground relay, non-protection, and UAV jammer schemes. Furthermore, we conduct extensive simulations to verify the accuracy of theoretical analysis and present useful insights into the practical deployment by revealing the relationship between the performance and other parameters, such as the antenna beamwidth, flight height and density of UAVs.

Cameras onboard autonomous, as a critial component of the sensor system of automatic driving, plays a vital role in perception of driving and road environment. However, in some bad weather or unpredictable situations, the image quality obtained by the in-vehicle sensing camera is not ideal, which will become an extremely unsafe factor for autonomous driving. In order to improve the safety of self-driving vehicles, we proposed a novel high-quality image of invehicle cameras generation approach CE-GAN, a conditional generative adversarial network that attempt to leverage the point cloud data from on-board lidar to compensate the defect of visible image to improve the image quality of on-board cameras. Inspired by the generative adversarial networks, our method establishes an adversarial game between the generator and the discriminator We designed specifically loss function for different reasons for image quality impairment including partially obscured and fogged. Consequently, extensive experiments show that CE-GAN renders better performance in detail texture, compared with conventional Cycle-GAN, pix2pix methods without assistance of LiDAR data.

Realtime foreground/background segmentation based on sequence video was of great significance for autonomous vehicles perception, edge device application and higher level data analysis. A new fast background subtraction method for dynamic objects detection was proposed by using the digital features of the whole block of pixels. The algorithm considered that the change of the current pixel was closely related to the surrounding pixels, took the current pixel and its eight neighboring pixels as a whole block, and used the digital features - average and variance to reflect the pixel level of the block and establish the background model. At the same time, a local remodeling method was proposed, which made the algorithm can process and eliminate ghost quickly. The results based on CDnet2014 dataset showed that our algorithm could adapt to various dynamic objects detection scenarios and initialize fast under the condition of low hardware cost, and provided a good overall performance.

The ground-to-satellite communication network (G2SN) has highlighted the significance of constructing ubiquitous and seamless networks for the next-generation communication system. However, in the presence of secret eavesdroppers, securing massive transmission links is posing tremendous challenges for G2SNs. In this paper, we propose an aerial assistant scheme to safeguard legitimate transmissions in G2SNs, where multiple unmanned aerial vehicles (UAVs) are deployed between the ground users and the satellite. With the assistance of flexible UAVs and the directivity of directional antennas, the constructed link can significantly reduce the risk of wiretapping, resulting in the improvement of security. Furthermore, to evaluate the performance of G2SNs, we introduce the eavesdropping probability and link connectivity as metrics. With the comparison of the non-protection scheme, we validate the effectiveness of our aerial assistant scheme. Finally, we present useful insights into practical deployment by revealing the relationship between the performance and other parameters, such as antenna beamwidth, deployment height and density of UAVs.

Summary With the advent of Internet of Things (IoT) age, the variety and volume of web services have been increasing at a fast speed. This often leads to users' selections for web services more complicated. Under the circumstance, a variety of methods such as collaborative filtering are adopted to deal with this challenging situation. While traditional collaborative filtering method has some shortcomings, one of which is that only centralized user‐service data are considered while distributed quality data from multiple platform are ignored. Generally, service recommendation across different platforms often involves data communication among multiple platforms, during which user privacy may be disclosed and much computational time is required. Considering these challenges, a unique amplified locality‐sensitive hashing (LSH)‐based service recommendation method, that is, SRAmplified‐LSH, is proposed in the article. SRAmplified‐LSH can guarantee a good balance between accuracy and efficiency of recommendation and user privacy information. Finally, extensive experiments deployed on WS‐DREAM dataset validate the feasibility of our proposed method.

To solve the problems such as low accuracy and low retrieval performance in feature extraction of environmental sound data from Internet consumer finance scenario, a novel method for environmental sound filtering and feature extraction (VF-EFENet) is proposed. First, the Conv-TasNet speech separation model is clipped and migrated to filter foreground voice. Second, an environmental sound feature extraction model is established based on the improved VGGish, and pretraining weight is used to improve the feature extraction accuracy. Finally, metric learning is used to optimize the distance function to improve retrieval accuracy. Metric learning can make the same kind of audio feature space cohesive and the different types of audio feature space away. The experiments are implemented based on AISHELL-1 and ESC-50 data sets to test voice filter performance, average classification accuracy and average retrieval accuracy. The experimental results show that VF-EFENet can effectively filter the voice in mixed audio and the SI-SNR reaches 12.51 db. When sampling rate is 8 kHz, the average classification accuracy is improved by 8.3% after voice filtering using VF-EFENet. When Top30 samples are retrieved, the average retrieval accuracy of VF-EFENet is 7.37% higher than that of ESResNetAttention.

To ensure the security of Internet of Things (IoT) communications, one can use deep packet inspection (DPI) on network middleboxes to detect and mitigate anomalies and suspicious activities in network traffic of IoT, although doing so over encrypted traffic is challenging. Therefore, in this article, an efficient and privacy-preserving encrypted traffic detection scheme is proposed. The scheme uses only lightweight cryptographic operations (i.e., symmetric encryption, hash functions, and pseudorandom functions) to achieve both privacy and security within an inspection round. A dispute resolution mechanism is also designed to address potential disputes between client(s) and server(s). We also present the corresponding security proof and experimental evaluation, which demonstrate that our proposed scheme achieves strong security and privacy preservation and good performance.

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 one of the most relevant data preprocessing techniques, discretization has played an important role in data mining, which is widely applied in industrial control. It can transform continuous features to discrete ones, thus improving the efficiency of data processing and adapting to learning algorithms that require discrete data as inputs. However, traditional discretization methods have shortcomings, such as highly complex programs, excessive numbers of intervals obtained, and significant loss of necessary information in the preprocessing of high-resolution remote sensing big data. Moreover, the large number of mixed pixels in the image is a primary reason for the uncertainty of remote sensing information systems, and current discretization methods are based on the assumption that one pixel only corresponds to the spectral information of a single object, without considering the influence of the uncertainty caused by a mixed spectrum, which causes the classification accuracy to drop after discretization. We propose a discretization method for high-resolution remote sensing big data. We determine the membership degree of each pixel in training samples through linear decomposition and establish the individual fitness function based on a fuzzy rough model. An adaptive genetic algorithm selects discrete breakpoints, and a MapReduce framework calculates the individual fitness of the population in parallel to obtain the optimal discretization scheme in the minimum time. Our method is compared to the best state-of-the-art discretization algorithms on the authentic remote sensing datasets. Experiments verified the effectiveness of the proposed method, which provides strong support for the subsequent processing of images.

Wind energy is a fast-growing renewable energy but faces blade icing. Data-driven methods provide talented solutions for blade icing detection, but a considerable amount of Internet of Things data needs to be collected to a central server, which may lead to the leakage of sensitive business data. To address this limitation, this article proposesBLADE, a Blockchain-empowered imbalanced federated learning (FL) model for blade icing detection. With the help of the Blockchain, the conventional FL is improved without worrying about the failure of the single centralized server and boosts the privacy preserving. A validation mechanism is introduced into the Blockchain to enhance the defense against poisoning attacks. In addition, a novel imbalanced learning algorithm is integrated into BLADE to solve the class imbalance problem in the sensor data. BLADE is evaluated on ten wind turbines from two wind farms. The experimental results verify the effectiveness, superiority, and feasibility of the proposed BLADE.

Multimodal image fusion is the process of combing relevant biological information that can be used for automated industrial application. In this article, we present a novel framework combining fractal constraint with group sparsity to achieve the optimal fusion quality. First, we adopt the idea of patch division and componentwise separation to perceive the fractal characteristics across multimodality sources. Then, to preserve the spatial information against the redundancy of component-entanglement, the group sparsity is proposed. A dual variable weighting rule is inherently embedded to mitigate the overfitting across the component penalty. Furthermore, the alternating direction method of multipliers is conducted to the proposed model optimization. The experiments show that our model has a better performance in quantitative visual quality and qualitative evaluation analysis. Finally, a real segmentation application of positron emission tomography/computed tomography image fusion proves the effectiveness of our algorithm.

Traffic sign classification plays a vital role in autonomous vehicles for its powerful capability in information representation. However, the low-quality data of traffic signs captured by in-vehicle cameras often inevitably bring inherent challenges to the one-shot classification task. Apart from the problem of data degradation, learning-based classification techniques of real traffic signs also come across the challenges of intra-class and inter-class data imbalance from the training data. To overcome the aforementioned problems, we propose an end-to-end degradation robust deep model, termed PcGAN, to classify traffic signs in a manner of few-shot learning. The proposed PcGAN models the joint distribution between the degraded traffic signal data and the corresponding prototypes from both degradation removal and generation perspectives by two alternating optimized modules, which ensures the generalization of the learned embedding of latent space for novel tasks. A multi-task loss function is designed to improve the robustness of PcGAN. Numerous experiments comprehensively demonstrate that the accuracy of our proposed PcGAN is improved by 5% compared with other state-of-the-art (SOTA) approaches in few-shot classification.

The clustering of incomplete patterns is a very challenging task because the estimations may negatively affect the distribution of real centers and thus cause uncertainty and imprecision in the results. To address this problem, a new belief-based incomplete pattern unsupervised classification method (BPC) is proposed in this paper. First, the complete patterns are grouped into a few clusters by a classical soft method like fuzzy$c$-means to obtain the corresponding reliable centers and thereby are partitioned into reliable patterns and unreliable ones by an optimization method. Second, a basic classifier trained by reliable patterns is employed to classifies unreliable patterns and the incomplete patterns edited by the neighbors. In this way, most of the edited incomplete patterns can be submitted to specific clusters. Finally, some ambiguous patterns will be carefully repartitioned again by a new distance-based rule depending on the obtained reliable centers and belief functions theory. By doing this, a few patterns that are very difficult to classify between different specific clusters will be reasonably submitted to meta-cluster which can characterize the uncertainty and imprecision of the clusters due to missing values. The simulation results show that the BPC has the potential to deal with real datasets.

Summary With the advent of the Internet of things era, cloud computing platforms will face the challenges of massive equipment requirements for access, massive data, insufficient bandwidth, and high power consumption. Edge computing, as a new technology, makes it possible to stream media over the edge network. However, many problems related to file sharing among edge nodes and to the files provided by cloud servers exist. We propose a novel replica placement strategy for mobile media streaming in edge computing (RPME) to address the aforementioned problem. First, we introduce a multilevel replica placement model in the RPME. In the RPME, we acquire the user information and the user‐item rating matrix when the user requests the media data. At the server, we cluster the users according the user information, update the user‐item rating matrix, and then generate a replica recommendation sequence. For when the server submits the replica recommendation sequence to the edge node considering the constraints of the edge node storage capacity and the limitations on the service capacity of the requested replica, we propose an effective replica placement mechanism in the RPME. To show the benefits of the RPME, we also present several experiments to prove its validity.

With the continuous accumulation of users' check-in data, we can gradually capture users' behavior patterns and mine users' preferences. Based on this, the next point-of-interest (POI) recommendation has attracted considerable attention. Its main purpose is to simulate users' behavior habits of check-in behavior. Then, different types of context information are used to construct a personalized recommendation model. However, the users' check-in data are extremely sparse, which leads to low performance in personalized model training using recurrent neural network. Therefore, we propose a category-aware gated recurrent unit (GRU) model to mitigate the negative impact of sparse check-in data, capture long-range dependence between user check-ins and get better recommendation results of POI category. We combine the spatiotemporal information of check-in data and take the POI category as users' preference to train the model. Also, we develop an attention-based category-aware GRU (ATCA-GRU) model for the next POI category recommendation. The ATCA-GRU model can selectively utilize the attention mechanism to pay attention to the relevant historical check-in trajectories in the check-in sequence. We evaluate ATCA-GRU using a real-world data set, named Foursquare. The experimental results indicate that our ATCA-GRU model outperforms the existing similar methods for next POI recommendation.

Critical infrastructure systems are vital to underpin the functioning of a society and economy. Due to the ever-increasing number of Internet-connected Internet-of-Things (IoT)/Industrial IoT (IIoT), and the high volume of data generated and collected, security and scalability are becoming burning concerns for critical infrastructures in industry 4.0. The blockchain technology is essentially a distributed and secure ledger that records all the transactions into a hierarchically expanding chain of blocks. Edge computing brings the cloud capabilities closer to the computation tasks. The convergence of blockchain and edge computing paradigms can overcome the existing security and scalability issues. In this article, we first introduce the IoT/IIoT critical infrastructure in industry 4.0, and then we briefly present the blockchain and edge computing paradigms. After that, we show how the convergence of these two paradigms can enable secure and scalable critical infrastructures. Then, we provide a survey on the state of the art for security and privacy and scalability of IoT/IIoT critical infrastructures. A list of potential research challenges and open issues in this area is also provided, which can be used as useful resources to guide future research.

In the past decades, due to the low design cost and easy maintenance, text-based CAPTCHAs have been extensively used in constructing security mechanisms for user authentications. With the recent advances in machine/deep learning in recognizing CAPTCHA images, growing attack methods are presented to break text-based CAPTCHAs. These machine learning/deep learning-based attacks often rely on training models on massive volumes of training data. The poorly constructed CAPTCHA data also leads to low accuracy of attacks. To investigate this issue, we propose a simple, generic, and effective preprocessing approach to filter and enhance the original CAPTCHA data set so as to improve the accuracy of the previous attack methods. In particular, the proposed preprocessing approach consists of a data selector and a data augmentor. The data selector can automatically filter out a training data set with training significance. Meanwhile, the data augmentor uses four different image noises to generate different CAPTCHA images. The well-constructed CAPTCHA data set can better train deep learning models to further improve the accuracy rate. Extensive experiments demonstrate that the accuracy rates of five commonly used attack methods after combining our preprocessing approach are 2.62% to 8.31% higher than those without preprocessing approach. Moreover, we also discuss potential research directions for future work.

As computing systems continue to increase in complexity, energy optimization plays a key role in the design and implementation of heterogeneous systems. Although the energy consumed by off-chip memory accounts for a large proportion of the total power consumed by the system as a whole, current research on energy optimization mainly focuses on optimizing the energy consumed by the processors. This article explores the coordinated optimization of the holistic performance of the processors and memory system for heterogeneous systems with energy constraints. A communication–computing pipeline model for parallel executions is characterized to optimize program performance by simultaneously scaling the voltage and frequency of the processors and memory using task allocation strategies. A synergistic load-balancing optimization approach is presented to resolve the load imbalance among graphics processing units. Our experimental results substantiate the effectiveness of the approach in terms of execution times and throughputs with the energy constraints.

Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal with this problem, in this work, we propose a dual calibration mechanism (DCM) for establishing feature points correspondence in graph matching. In specific, we embed two types of calibration modules in the graph matching, which model the correspondence relationship in point and edge respectively. The point calibration module performs unary alignment over points and the edge calibration module performs local structure alignment over edges. By performing the dual calibration, the feature points correspondence between two images with deformations and rotations variations can be obtained. To enhance the robustness of correspondence establishment, the L2,p-norm is employed as the similarity metric in the proposed model, which is a flexible metric due to setting the different p values. Finally, we incorporate the dual calibration and L2,p-norm based similarity metric into the graph matching model which can be optimized by an effective algorithm, and theoretically prove the convergence of the presented algorithm. Experimental results in the variety of graph matching tasks such as deformations, rotations and outliers evidence the competitive performance of the presented DCM model over the state-of-the-art approaches.

Feature discretization is one of the most relevant techniques for data preprocessing in remote sensing research area. Its main goal is to transform the continuous features of images into discrete ones to improve the efficiency of intelligent image processing algorithms, thus helping experts to more easily understand and use the acquired remote sensing data. In this article, we focus on feature discretization for classification of high-resolution remote sensing images in coastal areas. In these images, interactions among multiple bands exist, noises interfere, and maritime domain-specific prior knowledge is difficult to get. To address these challenges, we propose a hybrid metric method, based on information entropy and chi-square test, to calculate the stability of the discrete interval and the similarity of adjacent intervals. In addition, we use the degree of dependence among knowledge from the rough set theory as the evaluation criterion for discretization schemes and then scan each band in turn with the strategy of first splitting then merging, to obtain the optimal set of discrete features. Our method has been compared with the best state-of-the-art discretization algorithms on the GF-2 and Landsat 8 satellite datasets. Experiments show that the proposed method achieves better classification accuracy for high-resolution remote sensing images in coastal areas. It can not only effectively mine the correlation between features but also filter the outliers in bands, thus producing as few discrete intervals as possible while ensuring data consistency.

Recently, traffic flow prediction has drawn significant attention because it is a prerequisite in intelligent transportation management in urban informatics. The massively available traffic data collected from various sensors in transportation cyber-physical systems brings the opportunities in accurately forecasting traffic trend. Recent advances in deep learning shows the effectiveness on traffic flow prediction though most of them only demonstrate the superior performance on traffic data from a single type of vehicular carriers (e.g., cars) and does not perform well in other types of vehicles. To fill this gap, in this article, we propose a wide-attention and deep-composite (WADC) model, consisting of a wide-attention module and a deep-composite module, in this article. In particular, the wide-attention module can extract global key features from traffic flows via a linear model with self-attention mechanism. The deep-composite module can generalize local key features via convolutional neural network component and long short-term memory network component. We also perform extensive experiments on different types of traffic flow datasets to investigate the performance of WADC model. Our experimental results exhibit that WADC model outperforms other existing approaches.

Internet of Things (IoT) is a network of heterogeneous physical devices connected over the Internet. Each of the devices is capable of collecting and processing data. Due to the connection with the Internet, the IoT devices become more susceptible to attacks by malicious nodes, which may result in privacy loss and security breaches. Thus, network security is necessary for the privacy of transmitted messages. In this context, we propose a scheme, Service-Oriented game-theoretic Security (SOS), which provides a simple yet robust security solution for IoT networks. Here, we have amalgamated our scheme with Named Data Networking (NDN), which is more of a data content-specific approach, unlike the traditional IP address search. In this scheme, at first, the hop count between the sender and the receiver is used to generate the public key to encrypt the messages by the sender. When the receiver receives this message, it decrypts the message with the help of the decryption function generated by the sender using the hop count between them as the private key. A non-cooperative Stackelberg game-theoretic model is used to model defenders and attackers, which helps to decide strategies to maximize the payoff (profit) of the defenders to protect the network from malicious attacks. The results are further extended for a modified public key encryption technique, which results in the robustness of the security scheme to be used for all real-life network scenarios. Simulation results show that the proposed scheme, SOS, has a better performance compared to the existing state-of-the-art security schemes, UAKMP and CLS, in terms of time complexity, message overhead, throughput, and attack probability.

Distributed peer-to-peer power energy markets are emerging quickly. Due to central governance and lack of effective information aggregation mechanisms, energy trading cannot be efficiently scheduled and tracked. We devise a new distributed energy transaction system over the energy Industrial Internet of Things based on predictive analytics, blockchain, and smart contract technologies. We propose a solution for scheduling distributed energy sources based on the Minimum Cut Maximum Flow theory. Blockchain is used to record transactions and reach consensus. Payment clearing for the actual power consumption is executed via smart contracts. Experimental results on real data show that our solution is practical and achieves a lower total cost for power energy consumption.

With the rapid development of cloud computing technology, massive services and online information cause information overload. Collaborative Filtering (CF) is one of the most successful and widely used technologies in personalized recommendation system to deal with information overload. However, traditional CF recommendation algorithms go through high time cost and poor real-time performance when dealing with the large-scale behavior data. Moreover, most collaborative recommendation methods mainly focus on improving recommendation accuracy, while ignore privacy preservation. In addition, the recommendation results of traditional CF recommendation algorithms are often too single, which could not meet user's diverse requirements. To solve these problems, this paper proposes a privacy-aware collaborative recommendation algorithm based on local sensitive hash (LSH) and factorization techniques. First, LSH is adopted to determine nearest neighbor set of the target users, where a neighbor matrix for the target user can be generated. The matrix factorization technique is applied in the neighbor matrix to predict the missing ratings. Then the nearest neighbors can be determined based on the predicted ratings. Finally, predictions for the target user are made based on the neighborhood-based CF recommendation model and diversified recommendations are made for the target user. Experimental results show that the proposed algorithm can effectively improve the efficiency of recommendation on the premise of protecting the privacy of users.

The appearance of tumor cell clusters in pleural effusion is usually a vital sign of cancer metastasis. Segmentation, as an indispensable basis, is of crucial importance for diagnosing, chemical treatment, and prognosis in patients. However, accurate segmentation of unstained cell clusters containing more detailed features than the fluorescent staining images remains to be a challenging problem due to the complex background and the unclear boundary. Therefore, in this paper, we propose a fused 3-stage image segmentation algorithm, namely Coarse segmentation-Mapping-Fine segmentation (CMF) to achieve unstained cell clusters from whole slide images. Firstly, we establish a tumor cell cluster dataset consisting of 107 sets of images, with each set containing one unstained image, one stained image, and one ground-truth image. Then, according to the features of the unstained and stained cell clusters, we propose a three-stage segmentation method: 1) Coarse segmentation on stained images to extract suspicious cell regions-Region of Interest (ROI); 2) Mapping this ROI to the corresponding unstained image to get the ROI of the unstained image (UI-ROI); 3) Fine Segmentation using improved automatic fuzzy clustering framework (AFCF) on the UI-ROI to get precise cell cluster boundaries. Experimental results on 107 sets of images demonstrate that the proposed algorithm can achieve better performance on unstained cell clusters with an F1 score of 90.40%.

Text representation has a critical impact on the accuracy of text classifiers which is imperative to be strengthened. On the other hand, the question of how the state-of-the-art embeddings outperform previous approaches cannot be well explained. To advance text representation and better understand the internal mechanism, we propose a novel end-to-end framework named Ensemble Framework for Text Embedding (EFTE), which weightedly combines diverse embeddings and simultaneously represents sentences' and tokens' features in a more reasonable way. According to the experimental results in sentiment classification, our proposed embedding apparently improves the effectiveness compared to six single embeddings. Moreover, the importance of each embedding in terms of EFTE integration and how different embeddings influence the results by classification are discussed.

Eliminating haze interference in images is still a challenging problem. In this paper, we consider more systematically the physical hazing mechanisms, combined with deep learning, propose a new end-to-end dehazing network called DHD-Net. For physical hazing mechanisms, we fuse the global atmosphere light, transmission maps, and the atmospheric scattering model for dehazing. For the estimation of global atmosphere light, We propose a deep learning-based haze density estimation algorithm (DL-HDE). We establish a new dataset, of which each data item consists of the hazy image, the transmission map, the haze-free image, and the dense-haze area mask. Our experimental results demonstrate that our proposed DHD-Net has better dehazing performance than state-of-the-art algorithms.

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.

The effective extraction of continuous features in ocean optical remote sensing image is the key to achieve the automatic detection and identification for marine vessel targets. Since many of the existing data mining algorithms can only deal with discrete attributes, it is necessary to transform the continuous features into discrete ones for adapting to these intelligent algorithms. However, most of the current discretization methods do not consider the mutual exclusion within the attribute set when selecting breakpoints, and cannot guarantee that the indiscernible relationship of information system is not destroyed. Obviously, they are not suitable for processing ocean optical remote sensing data with multiple features. Aiming at this problem, a multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition is presented in this paper. Firstly, the information equivalent model of remote sensing image is established based on the theories of information entropy and rough set. Secondly, the change extent of indiscernible relationship in the model before and after discretization is evaluated. Thirdly, multiple scans are executed for each band until the termination condition is satisfied for generating the optimal number of intervals. Finally, we carry out the simulation analysis of the high-resolution remote sensing image data collected near the coast of South China Sea. In addition, we also compare the proposed method with the current mainstream discretization algorithms. Experiments validate that the proposed method has better comprehensive performance in terms of interval number, data consistency, running time, prediction accuracy and recognition rate.

Outsourcing helps relocate data from the cyber-physical system (CPS) for efficient storage at low cost. Current server-based outsourcing mainly focuses on the benefits of servers. This cannot attract users well, as their security, efficiency, and economy are not guaranteed. To solve with this issue, a hybrid outsourcing model that exploits both cloud server and edge devices to store data is needed. Meanwhile, the requirements of security and efficiency are different under specific scenarios. There is a lack of a comprehensive solution that considers all of the above issues. In this work, we overcome the above issues by proposing the first hybrid user-centric data outsourcing (HUCDO) scheme. It allows users to outsource data securely, efficiently, and economically via different CPSs. Brielly, our contributions consist of theories, implementations, and evaluations. Our theories include the first homomorphic collision-resistant chameleon hash (HCCH) and homomorphic designated-receiver signcryption (HDRS). As implementations, we instantiate how to use our proposals to outsource small- or large-scale data through distinct CPS, respectively. Additionally, a blockchain with proof-of-discrete-logarithm (B-PoDL) is instantiated to help improve our performance. Last, as demonstrated by our evaluations, our proposals are secure, efficient, and economic for users to implement while outsourcing their data via CPSs.

Social networks have integrated into the daily lives of most people in the way of interactions and of lifestyles. The users' identity, relationships, or other characteristics can be explored from the social networking data, in order to provide personalized services to the users. In this article, we focus on predicting the user's emotional intelligence (EI) based on social networking data. As an essential facet of users' psychological characteristics, EI plays an important role on well-being, interpersonal relationships, and overall success in people's life. Perception of EI contributes to predicting one's behavior or group behavior. Most existing work on predicting people's EI is based on questionnaires that may collect dishonest answers or unconscientious responses, thus leading in potentially inaccurate prediction results. In this article, we are motivated to propose EI prediction models based on the sentiment analysis of social networking data. The models are represented by four dimensions, including self-awareness, self-regulation, self-motivation, and social relationships. The EI of a user is then measured by four numerical values or the sum of them. In the experiments, we predict the EIs of over a hundred thousand users based on one of the largest social networks of China, Weibo. The predicting results demonstrate the effectiveness of our models. The results show that the distribution of the four EI's dimensions of users is roughly normal. The results also indicate that EI scores of females are generally higher than males' EI scores. This is consistent with previous findings. In addition, the four dimensions of EI are correlated. We finally analyze the advantages and the disadvantages of our models in predicting users' EI with social networking data.

With the wide deployment of wireless sensor networks in smart industrial systems, lots of unauthorized attacking from the adversary are greatly threatening the security and privacy of the entire industrial systems, of which node replication attacks can hardly be defended, since it is conducted in the physical layer. To solve this problem, we propose a secure random key distribution (SRKD) scheme, which provides a new method for the defense against the attack. Specifically, we combine a localized algorithm with a voting mechanism to support the detection and revocation of malicious nodes. We further change the meaning of the parameter s to help prevent the replication attack. Furthermore, the experimental results show that the detection ratio of replicate nodes exceeds 90% when the number of network nodes reaches 200, which demonstrates the security and effectiveness of our scheme. Compared with existing state-of-the-art schemes, the SRKD scheme also has good storage and communication efficiency.

Constructing Sustainable Smart Water Supply systems are facing serious challenges all around the world with the fast expansion of modern cities. Water quality is influencing our life ubiquitously and prioritizing all the urban management. Traditional urban water quality control mostly focused on routine tests of quality indicators, which include physical, chemical, and biological groups. However, the inevitable delay for biological indicators has increased the health risk and leads to accidents such as massive infections in many big cities. In this paper, we first analyze the problem, technical challenges, and research questions. Then, we provide a possible solution by building a risk analysis framework for the urban water supply system. It takes indicator data we collected from industrial processes to perceive water quality changes, and further for risk detection. In order to provide explainable results, we propose an Adaptive Frequency Analysis (Adp-FA) method to resolve the data using indicators' frequency domain information for their inner relationships and individual prediction. We also investigate the scalability properties of this method from indicator, geography, and time domains. For the application, we select industrial quality data sets collected from a Norwegian project in four different urban water supply systems, as Oslo, Bergen, Strømmen, and Ålesund. We employ the proposed method to test spectrogram, prediction accuracy, and time consumption, comparing with classical Artificial Neural Network and Random Forest methods. The results show our method better perform in most of the aspects. It is feasible to support industrial water quality risk early warnings and further decision support.

With the development of mobile Internet, more and more individuals and institutions tend to express their views on certain things (such as software and music) on social platforms. In some online social network services, users are allowed to label users with similar interests as “trust” to get the information they want and use “distrust” to label users with opposite interests to avoid browsing content they do not want to see. The networks containing such trust relationships and distrust relationships are named signed social networks (SSNs), and some real-world complex systems can be also modeled with signed networks. However, the sparse social relationships seriously hinder the expansion of users’ social circle in social networks. In order to solve this problem, researchers have done a lot of research on link prediction. Although these studies have been proved to be effective in the unsigned social network, the prediction of trust and distrust in SSN has not achieved good results. In addition, the existing link prediction research does not consider the needs of user privacy protection, so most of them do not add privacy protection measures. To solve these problems, we propose a trust-based missing link prediction method (TMLP). First, we use the simhash method to create a hash index for each user. Then, we calculate the Hamming distance between the two users to determine whether they can establish a new social relationship. Finally, we use the fuzzy computing model to determine the type of their new social relationship (e.g., trust or distrust). In the paper, we gradually explain our method through a case study and prove our method’s feasibility.

In recent years, the number of web services grows explosively. With a large amount of information resources, it is difficult for users to quickly find the services they need. Thus, the design of an effective web service recommendation method has become the key factor to satisfy the requirements of users. However, traditional recommendation methods often tend to pay more attention to the accuracy of the results but ignore the diversity, which may lead to redundancy and overfitting, thus reducing the satisfaction of users. Considering these drawbacks, a novel method called DivMTID is proposed to improve the effectiveness by achieving accurate and diversified recommendations. First, we utilize users’ historical scores of web services to explore the users’ preferences. And we use the TF-IDF algorithm to calculate the weight vector of each web service. Second, we utilize cosine similarity to calculate the similarity between candidate web services and historical web services and we also forecast the ranking scores of candidate web services. At last, a diversification method is used to generate the top- K recommended list for users. And through a case study, we show that DivMTID is an effective, accurate, and diversified web service recommendation method.

Urban Water Supply (UWS) is one of the most critical and sensitive systems to sustain overall city operations. The European Union (EU) has strict water quality regulations that currently depend on periodic laboratory tests of selected parameters in most of the cases. The tests of some biological parameters can take up to 48 hours, which leads to the delay of risk detection and lengthens the response time for taking countermeasures in UWS. This situation increases the risk of negative impacts to the health of mass population. To address this challenge, we propose a data-driven risk analysis method which is low-cost and efficient. First, we build a framework for risk evaluation and prediction, within which a risk evaluation model is introduced considering the Quantitative Microbiological Risk Assessment (QMRA) process suggested by the World Health Organization (WHO). Second, we present a collaborative method to analyze biological risk features and similarities across different locations. Third, we propose a new risk prediction algorithm. We apply this method on the real-world data collected from 4 UWS systems in Norway. The preliminary results are depicted in risk maps and prediction accuracies are compared with different strategies. The application results show that our method is practical with good accuracy and explainability.

With the rapid usage of location-based services (LBSs), protection of location privacy has become a significant concern. Existing dummy-based methods mainly consider generating dummies in continuous queries, which neglects the fact that the user would launch queries in a frequent region(e.g., home), resulting in privacy disclosure in a long-term period (i.e., more than 30 days). To solve this problem, we propose a method which generates dummy frequent regions, and make dummies locate in these dummy regions as far as possible. Compared with other methods, evaluation based on real-world dataset shows that the proposed method can reduce the ratio of recognized dummies and restored trajectory in a long-term situation.

Real-Time Bidding (RTB) is an important paradigm in display advertising, where advertisers utilize extended information and algorithms served by Demand Side Platforms (DSPs) to improve advertising performance. A common problem for DSPs is to help advertisers gain as much value as possible with budget constraints. However, advertisers would routinely add certain key performance indicator (KPI) constraints that the advertising campaign must meet due to practical reasons. In this paper, we study the common case where advertisers aim to maximize the quantity of conversions, and set cost-per-click (CPC) as a KPI constraint. We convert such a problem into a linear programming problem and leverage the primal-dual method to derive the optimal bidding strategy. To address the applicability issue, we propose a feedback control-based solution and devise the multivariable control system. The empirical study based on real-word data from Taobao.com verifies the effectiveness and superiority of our approach compared with the state of the art in the industry practices.

Assisting traffic control is one of the most important applications on the Internet of Vehicles (IoVs). Traffic information provided by vehicles is desired since drivers or vehicle sensors are sensitive in perceiving or detecting nuances on roads. However, the availability and privacy preservation of this information are critical while conflicted with each other in the vehicular communication. In this paper, we propose a semicentralized mode with attribute-based blockchain in IoVs to balance the tradeoff between the availability and the privacy preservation. In this mode, a method of control-by-vehicles is used to control signals of traffic lights to increase traffic efficiency. Users are grouped their attributes such as locations and directions before starting the communication. The users reach an agreement on determining a temporary signal timing by interacting with each other without leaking privacy. Final decisions are verifiable to all users, even if they have no a priori agreement and processes of consensus. The mode not only achieves the aim of privacy preservation but also supports responsibility investigation for historical agreements via ciphertext-policy attribute-based encryption (CP-ABE) and blockchain technology. Extensive experimental results demonstrated that our mode is efficient and practical.

Banks are collecting an unprecedentedly large amount of data about their customers from difference sources, considering their cyber, physical, social activities. The focus of this paper is to study the problem of information sharing and lower the communication overhead among different nodes for a specific data mining approach in distributed big data architectures. This problem can be abstracted as how to efficiently search under a specific cluster node topology. This paper proposes a new design rule for topologies including: 1) low coordination number; 2) high packing density; and 3) having a 3-D structure. According to this rule, a rhombic dodecahedron topology is proposed. A distributed banking big data mining framework based on the proposed topology is implemented. The experiments based on multioptimization benchmark functions show the excellent searching ability of the proposed topology; and a banking customer feature reduction prototype has been implemented to showcase the practicality of the data mining framework.

Cloud computing extends Transportation Cyber-Physical Systems (T-CPS) with provision of enhanced computing and storage capability via offloading computing tasks to remote cloud servers. However, cloud computing cannot fulfill the requirements such as low latency and context awareness in T-CPS. The appearance of Mobile Edge Computing (MEC) can overcome the limitations of cloud computing via offloading the computing tasks at edge servers in approximation to users, consequently reducing the latency and improving the context awareness. Although MEC has the potential in improving T-CPS, it is incapable of processing computational-intensive tasks such as deep learning algorithms due to the intrinsic storage and computing-capability constraints. Therefore, we design and develop a lightweight deep learning model to support MEC applications in T-CPS. In particular, we put forth a stacked convolutional neural network (CNN) consisting of factorization convolutional layers alternating with compression layers (namely, lightweight CNN-FC). Extensive experimental results show that our proposed lightweight CNN-FC can greatly decrease the number of unnecessary parameters, thereby reducing the model size while maintaining the high accuracy in contrast to conventional CNN models. In addition, we also evaluate the performance of our proposed model via conducting experiments at a realistic MEC platform. Specifically, experimental results at this MEC platform show that our model can maintain the high accuracy while preserving the portable model size.

Real-time bidding (RTB) is an important mechanism in online display advertising, where a proper bid for each page view plays an essential role for good marketing results. Budget constrained bidding is a typical scenario in RTB where the advertisers hope to maximize the total value of the winning impressions under a pre-set budget constraint. However, the optimal bidding strategy is hard to be derived due to the complexity and volatility of the auction environment. To address these challenges, in this paper, we formulate budget constrained bidding as a Markov Decision Process and propose a model-free reinforcement learning framework to resolve the optimization problem. Our analysis shows that the immediate reward from environment is misleading under a critical resource constraint. Therefore, we innovate a reward function design methodology for the reinforcement learning problems with constraints. Based on the new reward design, we employ a deep neural network to learn the appropriate reward so that the optimal policy can be learned effectively. Different from the prior model-based work, which suffers from the scalability problem, our framework is easy to be deployed in large-scale industrial applications. The experimental evaluations demonstrate the effectiveness of our framework on large-scale real datasets.

To keep pace with the developments in medical informatics, health medical data is being collected continually. But, owing to the diversity of its categories and sources, medical data has become so complicated in many hospitals that it now needs a clinical decision support (CDS) system for its management. To effectively utilize the accumulating health data, we propose a CDS framework that can integrate heterogeneous health data from different sources such as laboratory test results, basic information of patients, and health records into a consolidated representation of features of all patients. Using the electronic health medical data so created, multilabel classification was employed to recommend a list of diseases and thus assist physicians in diagnosing or treating their patients' health issues more efficiently. Once the physician diagnoses the disease of a patient, the next step is to consider the likely complications of that disease, which can lead to more diseases. Previous studies reveal that correlations do exist among some diseases. Considering these correlations, a k-nearest neighbors algorithm is improved for multilabel learning by using correlations among labels (CML-kNN). The CML- kNN algorithm first exploits the dependence between every two labels to update the origin label matrix and then performs multilabel learning to estimate the probabilities of labels by using the integrated features. Finally, it recommends the top N diseases to the physicians. Experimental results on real health medical data establish the effectiveness and practicability of the proposed CDS framework.

In this paper, we propose a novel anti- eavesdropping scheme by introducing friendly jammers to a wireless network of things (WNoT). In particular, we establish a theoretical framework to evaluate the eavesdropping risk of WNoT with friendly jammers and the eavesdropping risk of WNoT without jammers. Our theoretical model takes into account various channel conditions such as the path loss and Rayleigh fading as well as the placement schemes of jammers. Our extensive numerical results show that using jammers in WNoT can effectively reduce the eavesdropping risk. Besides, our results also show that the eavesdropping risk heavily depends on both the channel conditions and the placements of jammers.

Simulation is an important technique for integrating interacting models for predicting results of hypothetical scenarios. A typical application area for simulators is virtual prototyping (VP). In VP, simulators replace the real-world prototype. Hence, the quality of the virtual prototype depends on the quality of its simulations, which in turn are highly dependent on the quality of the models and the computational power, especially if visualization and/or real-time constraints are required. Unfortunately defining models is an error-prone activity which requires domain-experts to have knowledge about the implementation details and/or IT-technical concerns. In addition, the bigger the dataset, the more computational power is needed, which affects the cost, and in turn, the usability of today’s simulators. To address both of these aspects, we propose a user-friendly, adaptive and scalable agentbased modelling and simulation framework with a hybrid CPU/GPU/FPGA high performance computing platform. The solution we describe provides domain-experts with a a scalable, adaptive, and efficient simulator and enables domain-experts to define high quality models without indepth IT-knowledge. We use a running example from the particle transmission domain to illustrate our approach.

A workflow model is an abstract representation of a real life workflow and consists of interconnected tasks depicting the desired executions of real life activities. Time information is an important aspect of many safety-critical workflows. This paper presents a new formal diagrammatic approach to timed workflow modelling involving principles from model-driven engineering. The approach extends the Diagram Predicate Framework, which is based on category theory and graph transformations, for the specification of workflow modelling formalisms. We develop a transition system to represent the dynamic semantics involving time in which transitions are described by specification transformations between instances. To model time, we use predicates for time delay and duration with transition rules for time advancement.

Directional antennas in Ad hoc networks offer more benefits than the traditional antennas with omni-directional mode. With directional antennas, it can increase the spatial reuse of the wireless channel. A higher gain of directional antennas makes terminals a further transmission range and fewer hops to the destination. This paper presents the design, implementation and simulation results of a multi-channel Medium Access Control (MAC) protocols for dense Vehicular Ad hoc Networks using directional antennas with local beam tables. Numeric results show that our protocol performs better than the existing multi-channel protocols in vehicular environment.

Email has become a standard communication method nowadays. But when it comes to important correspondences containing sensitive governmental, commercial or medical information, certified delivery is required. We present in this paper a new certified email protocol which assures fair delivery, non-repudiability, confidentiality and timeliness. To achieve definite fairness, an offline TTP is employed which will be involved only if there is a dispute.

With the efforts to understand protein structure, many computational approaches have been made recently. Among them, the support vector machine (SVM) methods have been recently applied and showed successful performance compared with other machine learning schemes. However, despite the high performance, the SVM approaches suffer from the problem of understandability since it is a black-box model. To overcome this limitation, this study attempted to combine the SVM with the association rule based classifier which can present the meaningful explanation about the prediction. To perform this task, a new association rule based classifier (PCPAR) was devised based on the existing classifier, CPAR, to handle the sequential data. PCPAR creates the patterns by merging the generated rules and then classifies the sequential data based on the pattern match. The experimental result presents the following: with sequential data, the PCPAR scheme shows better performance with respect to the accuracy and the number of generated patterns than CPAR method whether applied alone or combined with SVM. The combined scheme of SVMPCPAR generates more compact patterns than the combined scheme of SVM with decision tree, SVM DT, with similar performance. These patterns are easily understandable and biologically meaningful

RNA plays a critical role in mediating every step of cellular information transfer from genes to functional proteins. Pseudoknots are widely occurring structural motifs found in all types of RNA and are also functionally important. Therefore predicting their structures is an important problem. In this paper, we present a new RNA pseudoknot prediction method based on term rewriting rather than on dynamic programming, comparative sequence analysis, or context-free grammars. The method we describe is implemented using the Mfold RNA/DNA folding package and the term rewriting language Maude. Our method was tested on 211 pseudoknots in PseudoBase and achieves an average accuracy of 74.085% compared to the experimentally determined structure. In fact, most pseudoknots discovered by our method achieve an accuracy of above 90%. These results indicate that term rewriting has a broad potential in RNA applications from prediction of pseudoknots to higher level RNA structures involving complex RNA tertiary interactions.