Background Quantum support vector machines and quantum kernel methods have emerged as promising approaches within quantum machine learning, with the goal of leveraging quantum computing to enhance classification performance and computational efficiency. This review systematically surveys recent advances in QSVM and kernel‐based quantum classifiers, and analyzes their algorithmic frameworks, experimental implementations, and practical challenges. Methods We systematically examine QSVM approaches, including three schemes based on HHL algorithm, Hadamard test, and variational optimization, alongside multi‐class extension and quantum feature mapping. Result Findings indicate that QSVM can offer theoretical speed‐ups in specific settings, particularly when combined with quantum feature mappings that encode data into high‐dimensional Hilbert spaces. However, current implementations remain constrained by hardware limitations, and a lack of large‐scale general validation. Most studies focus on proof‐of‐principle experiments with limited real‐world applicability. Conclusion While promising, QSVM requires further work on scalability, noise resilience, and real‐world integration. Future research should focus on robust algorithms and empirical studies.

The rapid expansion of electric vehicles (EVs) charging stations underscores the urgent need for robust anomaly detection systems capable of identifying potential malfunctions while preserving data privacy. Federated Learning (FL) has emerged as a promising solution, enabling collaborative model training without requiring raw data sharing. However, applying conventional FL approaches to charging station networks presents significant challenges, including non-independent and identically distributed (non-IID) data and gradient conflicts among clients. To address these challenges, we introduce FedPareto, a novel Pareto-optimal FL framework designed to manage gradient conflicts and counter malicious attacks in charging station anomaly detection. FedPareto features a gradient conflict-aware aggregation method, which adaptively adjusts client weights based on cosine similarity between gradients, and a gradient magnitude reshaping strategy to enhance model convergence. Theoretical analysis demonstrates that FedPareto achieves a convergence rate of O($\frac{1}{T}$) and attains Pareto-optimal solutions under standard smoothness and convexity assumptions. Extensive experiments on real-world charging station datasets validate FedPareto’s effectiveness. It outperforms state-of-the-art methods, exhibits better robustness against gradient-based attacks, and ensures equitable performance distribution across clients. These results highlight FedPareto’s potential as a reliable and scalable solution for anomaly detection in EV charging station networks.

The surge in Internet video traffic driven by 5G advancement strains network infrastructure. Edge computing emerges as a solution for video distribution, yet faces challenges from limited cache capacity and dynamic user requests. To address these challenges, we propose IceCache - a recommendationdriven edge Caching architecture for the life cycle of video streaming. IceCache enhances Quality of Experience (QoE) while reducing backhaul traffic through two-stage caching: cache placement before playback, dynamic prefetching and cache admission during playback. A user behavior simulation integrating recommender systems was developed to evaluate the proposed caching strategy. Experiments on real-world MovieLens and synthetic datasets validated the strategy's performance.

federated graph learning (FGL) has emerged as a promising paradigm for privacy-preserving collaborative learning in Social Internet of Things (SIoT), where nodes form complex interconnected networks. Existing FGL approaches face significant challenges including model degradation in handling nonindependent and identically distributed (non-IID) data and maintaining model performance across heterogeneous nodes. This article proposes framework via layer-wised clustering (FedLWC), a novel layer-wised clustering framework inspired by evolutionary processes is proposed to enhance the effectiveness of FGL. FedLWC designs three key aspects: 1) a fisher information matrix-based layer selection mechanism that identifies and evaluates critical model layers, which can reduce parameter redundancy; 2) a layer intersection clustering algorithm that preserves common key layers while accommodating local features; and 3) an adaptive layer merge strategy that effectively combines global shared layers with clustered key layers. To make sure that the proposed approach is rigorous, we conduct theoretical convergence analysis for the proposed framework under non-IID conditions. Extensive experiments on multiple benchmark graph datasets demonstrate FedLWC’s performance, achieving an average accuracy improvement of 7.01% compared to state-of-the-art federated learning methods.

Federated learning (FL) faces significant challenges in scenarios with nonindependent and identically distributed (non-IID) data distributions across participating clients. Traditional aggregation-based approaches often struggle with the inherent misalignment between local and global optimization objectives, which leads to gradient divergence and suboptimal generalization performance. This article proposes a novel FL framework that replaces conventional aggregation with a biologically inspired model symbiosis approach called FedSym, which employs a dual-level symbiotic mechanism. Ectosymbiosis performs coarse-grained hierarchical parameter recombinations through random layer-wise model combination, while endosymbiosis enables fine-grained intralayer parameter fusion through weighted averaging, collectively steering model updates toward flatter loss landscapes. Our theoretical analysis demonstrates that FedSym’s convergence rate is$O({}{1}/{T})$under non-IID conditions, which matches the convergence properties of FedAvg. Extensive evaluations across multiple datasets and model architectures show that FedSym achieves substantial improvements over state-of-the-art FL methods, particularly in challenging scenarios with high data heterogeneity, and demonstrates robust performance across varying numbers of participating clients and federation scales.

Fault diagnosis is important for predictive maintenance in smart manufacturing, which involves intelligent human-machine interactions in order to make smart decisions for potential problems. Large language model (LLM) is promising in providing general artificial intelligence capabilities in this regard. However, LLM itself can not accurately analyze faults due to heterogeneous data from different Industrial Internet of Things (IIoT) devices in different processes during the complete production process. To accurately diagnose faults and facilitate human-machine interaction, this article proposes a brain-like cognition-driven model factory (BC-MF), using an LLM as a supervisor to adaptively generate personalized small-scale models according to the features of these heterogeneous data, where the vertical federated learning (VFL) idea is adopted. This BC-MF-based fault diagnosis approach includes a preliminary diagnosis phase and a precise diagnosis phase. The preliminary diagnosis is accomplished by prompting the LLM using a brain-like chain of thoughts (BLCoTs). A hypernetwork uses the preliminary diagnostic results and the feature maps trained by each node in the VFL to generate dedicated diagnostic small models and uses these models for final precise diagnostics. The LLM provides fault maintenance recommendations interactively according to the final diagnostic results. Comprehensive evaluations are conducted using four open IIoT datasets and one self-made dataset. It shows that the proposed BC-MF approach is significantly better than the existing approaches, in terms of model accuracy, comprehension of faults, and so on.

IoT devices have been widely deployed in medical industry, in the objective of improving diagnostic accuracy and increasing the efficiency of healthcare systems. However, traditional centralized learning approaches often fall short in meeting strict privacy requirements and adapting to emerging diseases in clinical environment. To address this, we propose a novel federated continual learning (CL) framework for disease diagnosis (FCL4DD), designed to enable distributed and incremental learning of new disease classes while safeguarding data privacy. To combat catastrophic forgetting in CL, FCL4DD integrates a replay strategy powered by a weakly supervised diffusion model (WSDM) to generate historical data for diagnosis model training. The WSDM leverages weak supervision into diffusion model to capture the diverse characteristics of the real data, enabling the generation of high-quality synthetic samples that maintain the data’s inherent variability. To overcome the challenges of nonindependent and identically distributed (non-IID) data in federated learning, WSDM is deployed at the central server to generate synthetic disease data that conforms to the global distribution. This synthetic data is then used to retrain client models, reducing discrepancies and enhancing performance consistency across clients. Evaluations on various datasets demonstrates that our method outperforms other state-of-the-art approaches, such as FedEWC, FedLwF, FedWeIT, TARGET, and DDDR, achieving up to a 4.85% accuracy improvement over the second-best method. Code are available athttps://github.com/hysshy/FCL4DD.

Room-temperature superconductors (esp. LK-99 in the recent) have attracted extensive academic attention in recent years, both in academic circles and among the general public. This topic has spread through a number of social media channels, a plethora of contradiction in information has emerged within social networks. There arises the question on how to analyze the consistency and controversy of such scientific knowledge in the dissemination process, and how this process impact on public cognition on the scientific knowledge. In this article, taking room-temperature superconductor as example, we first designed a large language model based factual consistency detection approach to analyze the consistency between research papers and media reports. Then the consistency between media reports and comments is analyzed, by proposing a novel quantification method for media agenda-setting capability, which evaluates the agenda-setting capability of media based on emotional and positional consistencies. The results indicate that two significant deviations occur when room-temperature superconductor knowledge is spread from specialized fields to the public through the various media. One deviation is due to the specialized nature of room-temperature superconductor knowledge, leading to discrepancies between reported content and factual information in research papers. The other deviation is caused by conflicting knowledge, resulting in disparities between media reports and public perception.

In February 2024, Lionel Messi's absence from a Hong Kong exhibition match ignited extensive debate across social media platforms, capturing the attention of the public and sparking controversies that extended into realms such as business partnerships and diplomatic implications. This incident not only reflects the public's reaction and pattern of stance changes toward such a complex Incident but also significantly demonstrates the close connection between cyberspace and the real world. Research on this incident has important practical significance for predicting and intervening in the evolution of similar hot incidents. In this article, the case of Messi's absence from the Hong Kong match is delved into. A stance detection method and a quantification approach for stance divergence have been devised to analyze the evolution of the stance surrounding the incident. Furthermore, by examining topic clusters over time, the topical progression of public stances is tracked. Findings reveal that nearly 60% of posts expressed an explicit stance throughout the incident, with the majority (66.9%) taking an opposing stance. Additionally, it was noted that the topics discussed at various stages followed a long-tail distribution, indicating that most discussions revolved around a few dominant themes. Within more segmented and specific topics, stance divergences were often more prominent.

Federated learning (FL) is a promising distributed learning framework in terms of privacy protection and communication saving. Most existing FL techniques are developed for independent-and-identically-distributed (IID) datasets, but suffer from performance degradation under Non-IID datasets. To cope with this issue, most existing work designs solutions from data perspectives (e.g., sharing some data samples between local devices) to eliminate the heterogeneity of distributed datasets, which causes extra communication overhead and may expose user privacy that contradicts FL's original intention. Unlike the existing data-based methods, we propose a generative adversarial network (GAN) based FL, named as GANFed, which is designed from a feature perspective. Specifically, we embed a discriminator into the FL network, which works with the shallow layers as a generator to form a GAN in FL. By incorporating such a GAN, the output of the shallow layers tends to present more IID features compared with the original Non-IID input data. These extracted features from the shallow layers are then used to train the deep layers of the FL network. In this way, the proposed GANFed reduces the weight divergence of the local models, and hence improves the performance of FL. Without data exchange, our GANFed avoids the leakage of user privacy and reduces the communication overhead. Experimental results show that our GANFed outperforms the standard FedAvg on Non-IID dataset in terms of improved test accuracy.

For future intelligent communication systems, radiomap estimation (RME) is essential for acquiring panoramic awareness of spectrum spatial distribution in wireless environments. Recently, deep learning-based RME methods have been developed to reconstruct radiomaps from spectrum measurements collected at distributed sensors. However, these methods rely on gathering all input data at a central fusion center, resulting in large communication overheads, high computation costs, and privacy leakage concerns. To address these challenges, this work proposes a FedRME approach that makes federated learning applicable for distributed RME over a large-scale network, accommodating geographically heterogeneous transmitter locations and propagation environments. Specifically, we partition the large area into smaller regions to reduce the model complexity required for learning the radiomap in each region. Meanwhile, we incorporate the landscape map as an auxiliary input to induce a common learning model that adheres to the same propagation physics across all these heterogeneous regions. In doing so, fusion centers in all regions can collaborate through federated learning to enhance the overall RME performance. Simulation results indicate that our proposed method outperforms existing benchmarks, particularly under limited data, achieving higher learning accuracy with reduced model complexity and lower computational cost.

Since the data samples on client devices are usually non-independent and non-identically distributed (non-IID), this will challenge the convergence of federated learning (FL) and reduce communication efficiency. This paper proposes FedQMIX, a node selection algorithm based on multi-agent reinforcement learning(MARL), to address these challenges. Firstly, we observe a connection between model weights and data distribution, and a clustering algorithm can group clients with similar data distribution into the same cluster. Secondly, we propose a QMIX-based mechanism that learns to select devices from clustering results in each communication round to maximize the reward, penalizing the use of more communication rounds and thereby improving the communication efficiency of FL. Finally, experiments show that FedQMIX can reduce the number of communication rounds by 11% and 30% on the MNIST and CIFAR-10 datasets, respectively, compared to the baseline algorithm(Favor).

Since fog nodes are resource-constrained and imperfectly trusted heterogeneous devices, guaranteeing a real-time response to Internet of Things (IoT) tasks while optimizing system energy consumption remains a significant challenge. To overcome this, we first propose a acrlong DBC-enabled cloud–fog collaborative task scheduling architecture. Second, a task scheduling model is constructed to optimize system energy consumption and task deadline violation time while adhering to the IoT task response time restriction. Finally, two blockchain-enabled task scheduling algorithms are developed: 1) the reputation-based priority-aware algorithm (DB_RP) and 2) the accelerated ant colony system algorithm (DB_AACS). Extensive experiments are conducted to assess the proposed algorithm in four dimensions: 1) task completion rate; 2) system makespan; 3) system energy consumption; and 4) task deadline violation time. The experimental results demonstrate that the proposed algorithm is superior to the existing literature, and the acceleration strategy in DB_AACS is effective.

Federated learning (FL) can train a model collaboratively through multiple remote clients without sharing raw data. The challenge of federated learning (FL) is how to decrease network transmissions. This article aims to reduce network traffic by transmitting fewer neural network parameters. We first investigate similarities of different corresponding layers of convolutional neural network (CNN) models in FL, and find that there is a lot of redundant information in its model feature extractors. For this, we propose a communication-efficient federated aggregation algorithm named FedSL (Federated Split Layers) to reduce the communication overhead. Based on the number of global model layers, the FedSL divides client models into groups in the depth dimension. A Max-Min client selection strategy is employed to select participants for each layer. Each client only transfers partial parameters of those layers that are selected, which reduces the number of parameters. FedSL aggregates the global model in each group and concatenates the parameters of all groups according to the order of layers. The experimental results demonstrate that FedSL improves communication efficiency compared to the algorithms (e.g., FedAvg, FedProx, and MOON), decreasing 42% communication cost with VGG-style CNN and 70% with ResNet-9, while maintaining a similar model accuracy with baseline algorithms.

Millions of patients suffer from rare diseases around the world. However, the samples of rare diseases are much smaller than those of common diseases. Hospitals are usually reluctant to share patient information for data fusion due to the sensitivity of medical data. These challenges make it difficult for traditional AI models to extract rare disease features for disease prediction. In this paper, we propose a Dynamic Federated Meta-Learning (DFML) approach to improve rare disease prediction. We design an Inaccuracy-Focused Meta-Learning (IFML) approach that dynamically adjusts the attention to different tasks according to the accuracy of base learners. Additionally, a dynamic weight-based fusion strategy is proposed to further improve federated learning, which dynamically selects clients based on the accuracy of each local model. Experiments on two public datasets show that our approach outperforms the original federated meta-learning algorithm in accuracy and speed with as few as five shots. The average prediction accuracy of the proposed model is improved by 13.28% compared with each hospital's local model.

The dynamics of public opinion on social media affects people’s feeling and minds about international affairs and leads to the reconstruction of societal states for international conflicts. In this article, we analyze the topics’ evolution on social media during the Pelosi visit. Such kind of analysis should help the related departments sense and beware the situation effectively and efficiently, and may provide technical supports for proper policy making and responses. To facilitate this purpose, a new method is proposed and an abbreviated large-graph clustering (ALGC) algorithm has been designed to generate documents and topic representation for alleviating the overhead of high computational complexity of large graphs by reducing the dimensionality of the attention matrix and adjacency matrix. The evolution pattern of topics is also analyzed in and between different time periods. Experiment results show that the proposed method performs well, achieving a high clustering accuracy with lower computational cost. The dataset used in this article is also released for public analysis.

Large language models (LLMs) are becoming powerful engines for social productivity in the manufacturing lifecycle. Existing application-level LLMs inference services focus on large datacenter and small edge intelligence (EI) scenarios, adopting iteration-level batch schedulers to solve resource utilization and inference speed problems. However, these services are incompatible with the scene of medium-sized local heterogeneous graphics processing unit (GPU) clusters with specific patterns, whose scale is between the two aforementioned scenarios. This type of scene proposes tradeoff problems for inference resource and speed, as well as user satisfaction problems for the semisparse frequency of queries with streaming responses. We propose suboptimal load balancing (SLoB), a distributed LLMs inference service scheduler in medium-sized local heterogeneous GPU clusters. SLoB leverages a multilevel adapter to accommodate LLMs usage patterns of scenes and balance resource utilization with inference efficiency. For semisparse problems, it adopts a mixed-priority pipeline scheduler with the least-padding principle to improve users’ satisfaction, a metric considering the weights of different tokens in streaming responses. Based on the system prototype, our experiments under simulated workloads demonstrate that SLoB gains a maximum improvement of 29.4$\times$under the satisfaction metric compared with the traditional run-to-completion scheduling solution while improving by up to 3.0$\times$compared with the state-of-the-art (SOTA) solution Orca.

Knowledge question and answering (Q&A) is widely used. However, most existing semantic parsing methods in Q&A usually use cascading, which can incur error accumulation. In addition, using only one institution’s Q&A data definitely will limit the Q&A performance, while data privacy prevents sharing between institutions. This article proposes a knowledge graph-based reinforcement federated learning (KGRFL)-based Q&A approach to address these challenges. We design an end-to-end multitask semantic parsing model [MSP-bidirectional and auto-regressive transformers (BART)] that identifies question categories while converting questions into SPARQL statements to improve semantic parsing. Meanwhile, a reinforcement learning (RL)-based model fusion strategy is proposed to improve the effectiveness of federated learning, which enables multi-institution joint modeling and data privacy protection using cross-domain knowledge. In particular, it also reduces the negative impact of low-quality clients on the global model. Furthermore, a prompt learning-based entity disambiguation method is proposed to address the semantic ambiguity problem because of joint modeling. The experiments show that the proposed method performs well on different datasets. The Q&A results of the proposed approach outperform the approach of using only a single institution. Experiments also demonstrate that the proposed approach is resilient to security attacks, which is required for real applications.

Examining the perceptual differences between China and the United States can facilitate a better understanding of their opinions and perspectives, helping to promote peaceful interactions among the two nations as well as the world. This study presents a data-driven approach to measure cognitive differences, investigating these differences from topical and sentimental angles regarding the unmanned balloon event that had been shot down by U.S. warplanes. We also explore the cognitive differences between news media and the followers, and the evolution of topics over time. Our findings reveal those discussions about “balloons” on social media in China and the United States display certain differences in terms of sentiment. In addition, we assess the impact of this event on U.S.–China relationship, particularly in trade. To evaluate the analytical capabilities of the popular ChatGPT model, we use this event as a case study to demonstrate that ChatGPT-like models may have limited capabilities for such kind of specialized analysis. The dataset utilized here is made available for public usage for further investigation on public opinion dynamics for similar events.

Based on an investigation of online public opinion on the Nahel Merzouk protests in France, an approach for analyzing and predicting public opinion on protests based on large language model (LLM) is proposed, revealing the impact of emerging social media on the protests. We demonstrate that protests generate public opinion on social media with some lag, but that comment sentiment and expression are consistent with protest trends. As the protests unfolded, we analyzed the evolution of public sentiment. We constructed the prompt based on historical data to predict the protests using the p-tuning and Lora approach to fine-tune LLM. In addition, we discuss how to use blockchain technology to optimize distributed, self-organizing protests and reduce the potential for disinformation and violent conflict.

Multiple organizations in social manufacturing can collaborate on high-quality product defect detection with social networks. Federated learning (FL) is an emerging paradigm where multiple clients can collaboratively train a defect detection model in a privacy-preserving manner. A prevalent issue in FL, concept drift, is discussed in this article. Feature representations of the same label may vary at different clients which affects the performance of FL. To address this issue, a novel community aware personalized federated learning (CA-PFL) is proposed in this article. A graph structured federation social network is constructed with local model updates. Communities in federation network are discovered with community detection to ensure that the same label at different clients have similar representations in each community. Shared layers of local models are aggregated in each community and each local client keeps their personalized layers. Furthermore, a federation community contrastive loss (FedCCL) is proposed to accelerate training convergence by constraining the direction of local model updating. Experimental results on nine datasets demonstrate that CA-PFL achieves higher accuracy and faster convergence than state-of-the-art personalized federated learning methods in concept drifts scenarios.

Data-driven machine learning techniques have been advocated for signal detection in complex wireless environments. However, when applied to wideband spectrum sensing scenarios, they face practical challenges including very large data dimensionality, insufficient training data, and implicit inter-band dependencies. Current literature focuses on deep convolutional models, whose inherent model structure is not well suited for representing the diverse spectrum occupancy patterns of practical wideband networks, causing inefficient performance-complexity tradeoff and excessive sensing time. To address these issues, this paper develops a novel Spectrum Transformer with multi-task learning for wideband spectrum sensing at high sample efficiency. Empowered by the multi-head self-attention mechanism, the transformer architecture is designed to effectively learn both the inner-band spectral features and the inter-band spectrum occupancy correlations in the wideband regime. Simulations show that the proposed Spectrum Transformer outperforms the existing methods based on convolutional neural networks especially in the small-data case, by achieving higher sensing accuracy with an 89% reduction in model complexity.

Choreography refers to creation of dance motions according to both music and dance knowledge, where the created dances should be style-specific and consistent. However, most of the existing methods generate dances using the given music as the only reference, lacking the stylized dancing knowledge, namely, the flag motion patterns contained in different styles. Without the stylized prior knowledge, these approaches are not promising to generate controllable style or diverse moves for each dance style, nor new dances complying with stylized knowledge. To address this issue, we propose a novel music-to-dance generation framework guided by style embedding, considering both input music and stylized dancing knowledge. These style embeddings are learnt representations of style-consistent kinematic abstraction of reference dance videos, which can act as controllable factors to impose style constraints on dance generation in a latent manner. Hence, we can make the style embedding fit into any given style while allowing the flexibility to generate new compatible dance moves by modifying the style embedding according to the learnt representations of a certain style. We are the first to achieve knowledge-driven style control in dance generation tasks. To support this study, we build a large multi-style music-to-dance dataset referred to as I-Dance. The qualitative and quantitative evaluations demonstrate the advantage of the proposed framework, as well as the ability to synthesize diverse moves under a dance style directed by style embedding.

Video Compression Artifact Reduction aims to reduce the artifacts caused by video compression algorithms and improve the quality of compressed video frames. The critical challenge in this task is to make use of the redundant high-quality information in compressed frames for compensation as much as possible. Two important possible compensations: Motion compensation and global context, are not comprehensively considered in previous works, leading to inferior results. The key idea of this paper is to fuse the motion compensation and global context together to gain more compensation information to improve the quality of compressed videos. Here, we propose a novel Spatio-Temporal Compensation Fusion (STCF) framework with the Parallel Swin-CNN Fusion (PSCF) block, which can simultaneously learn and merge the motion compensation and global context to reduce the video compression artifacts. Specifically, a temporal self-attention strategy based on shifted windows is developed to capture the global context in an efficient way, for which we use the Swin transformer layer in the PSCF block. Moreover, an additional Ada-CNN layer is applied in the PSCF block to extract the motion compensation. Experimental results demonstrate that our proposed STCF framework outperforms the state-of-the-art methods up to 0.23dB (27% improvement) on the MFQEv2 dataset.

Semantic image editing provides users with a flexible tool to modify a given image guided by a corresponding segmentation map. In this task, the features of the foreground objects and the backgrounds are quite different. However, all previous methods handle backgrounds and objects as a whole using a monolithic model. Consequently, they remain limited in processing content-rich images and suffer from generating unrealistic objects and texture-inconsistent backgrounds. To address this issue, we propose a novel paradigm, Semantic Image Editing by Disentangling Object and Background (SIEDOB), the core idea of which is to explicitly leverages several heterogeneous subnetworks for objects and backgrounds. First, SIEDOB disassembles the edited input into background regions and instance-level objects. Then, we feed them into the dedicated generators. Finally, all synthesized parts are embedded in their original locations and utilize a fusion network to obtain a harmonized result. Moreover, to produce high-quality edited images, we propose some innovative designs, including Semantic-Aware Self-Propagation Module, Boundary-Anchored Patch Discriminator, and Style-Diversity Object Generator, and integrate them into SIEDOB. We conduct extensive experiments on Cityscapes and ADE20K-Room datasets and exhibit that our method remarkably outperforms the baselines, especially in synthesizing realistic and diverse objects and texture-consistent backgrounds. Code is available at https://github.com/WuyangLuo/SIEDOB.

Video data is the biggest IoT data which is challenging for effective analysis with good performance. Object misdetection is usually inevitable in edge-based distributed cross-scene video analysis. Traditional centralized model training can potentially result in edge data leakage. Even though joint model can be trained with federated learning while maintaining data privacy, the size of gradient data transmitted is large for computer vision models used. To address these problems, this article proposed an accurate and efficient federated learning-based edge intelligence for effective video analysis method called EIEVA-AEFL. In EIEVA-AEFL, a federation misdetection reinforcement network (FMRN) is designed to alleviate the misdetection problem. FMRN contains a vanilla object detection network and a misdetection reinforcement branch, which finetunes object detection via feature re-extraction to reduce object misdetection. To reduce the communication cost in training, an efficient federated learning strategy is designed. In this strategy, an oscillation suppression loss function is proposed to suppress the loss fluctuation resulting from data on edge clients. Average accuracy and recall increase 0.5 and 0.7 with FMRN on the Microsoft common objects in context (MS COCO) data set, respectively, and with improvements of 4.5 and 5.5 with FMRN on our self-made mis-detection data set, respectively. EIEVA-AEFL can reduce the training speed on the premise of ensuring the accuracy of the model. The model parameters, data amount, transmission delay, and convergence epochs on EIEVA-AEFL model training are reduced by 78%, 89%, 84%, and 36%, respectively.

Federated learning is an emerging distributed machine learning paradigm that can break through data silos and make use of data from different clients in a secure way. However, for deep neural networks in federated learning, the models on clients may learn the same pattern with different weight distributions despite the same data distribution of local data sets, which limits the performance of neural networks after weight fusions. Therefore, in this article, we propose a homophily learning-based federated intelligence (HLFI) approach, where hierarchical federated learning strategy and dynamic elimination learning strategy are designed to alleviate the problem. The experiments on equipment failure prediction show that the proposed approach can improve the failure prediction F1-score up to 9.32%. Our approach also has good generalization capabilities and can be applied in other federated learning methods to improve the model performance.

Federated learning can collaboratively train AI models while protecting data privacy. In practical industry environment, non-independent and identically distributed (Non-IID) characteristics of data affect the effectiveness of federated learning. Personalized federated learning can help resolve this, but it cannot adapt to unknown data. In addition, practical applications also call for trusted training environment and remain stable when there are security threats. In this article, we propose a credible federated self-learning (CFSL), based on the idea of hypernetwork supported by blockchain to achieve secured, credible, personalized federated self-learning, especially, for unknown data in Non-IID environment. Extensive experiments on three Non-IID data sets demonstrate the capabilities on adaptive resilience for security attacks and on accuracy of recognizing unknown objects, with good performance at the same time. CFSL outperforms the existing personalized federated learning methods, with an increase in average accuracy by 4.11%.

Artificial intelligence (AI) continues demonstrating its positive impact on society and successful adoptions in data-rich domains including social computing systems. There are serious ethical and legal concerns about AI’s ability to make decisions in a responsible way. Many principles and guidelines for responsible AI (RAI) have been issued by governments, research organizations, and enterprises. For instance, the Institute for Ethical Machine Learning provides various RAI resources[1], including higher level guidelines and frameworks, tools, standards, regulations, course, and so on. However, high-level principles are far from ensuring the trustworthiness of AI systems.

Face inpainting aims at plausibly predicting missing pixels of face images within a corrupted region. Most existing methods rely on generative models learning a face image distribution from a big dataset, which produces uncontrollable results, especially with large-scale missing regions. To introduce strong control for face inpainting, we propose a novel reference-guided face inpainting method that fills the large-scale missing region with identity and texture control guided by a reference face image. However, generating high-quality results under imposing two control signals is challenging. To tackle such difficulty, we propose a dual control one-stage framework that decouples the reference image into two levels for flexible control: High-level identity information and low-level texture information, where the identity information figures out the shape of the face and the texture information depicts the component-aware texture. To synthesize high-quality results, we design two novel modules referred to as Half-AdaIN and Component-Wise Style Injector (CWSI) to inject the two kinds of control information into the inpainting processing. Our method produces realistic results with identity and texture control faithful to reference images. To the best of our knowledge, it is the first work to concurrently apply identity and component-level controls in face inpainting to promise more precise and controllable results.

Federated learning has become an emerging hot research field in industry because of its ability to perform large-scale distributed learning while preserving data privacy. However, recent studies have shown that in the actual use of federated learning, there are device heterogeneity and data not identically and independently distributed (Non-IID) characteristics between client nodes, which will affect the effect of federated learning. In this work, we propose resilient reinforcement federated learning (R$^{2}$Fed), a R$^{2}$Fed method, which applies reinforcement learning to federated learning and uses reinforcement learning for weighted fusion of client models instead of average fusion. We conduct experiments on object detection, object classification, and sentiment classification tasks in the context of Non-IID and heterogeneity, and the experimental results show that the R$^{2}$Fed method outperforms traditional federated learning, increasing the average accuracy by 4.7%. Experiments also demonstrate that R$^{2}$Fed is resilient to federation attacks.

Customer volume prediction is crucial for a variety of urban applications, such as store location selection. So far, the key challenge lies in how to fuse multiple modalities from different data sources, on account of the massive amount of data accessible, for example, spatio-temporal data and satellite images. In this article, we investigate three dynamic weighting ensemble learning models to fuse spatio-temporal features and visual features for predicting customer volume in the urban commercial district of interest. Specifically, we propose the shared-private dynamic weighting model by incorporating graph neural networks, which is proposed to capture geographic dependencies (i.e., competitiveness or dependencies) between urban commercial districts in an end-to-end manner. To the best of our knowledge, it is the first work to utilize graph neural networks to model such geographic relationships. We conduct a series of experiments to demonstrate the effectiveness of the proposed models based on two real datasets. Furthermore, an elaborated visualization method is performed for knowledge discovery.

Automatic generation of medical reports can provide diagnostic assistance to doctors and reduce their workload. To improve the quality of the generated medical reports, injecting auxiliary information through knowledge graphs or templates into the model is widely adopted in previous methods. However, they suffer from two problems: 1) The injected external information is limited in amount and difficult to adequately meet the information needs of medical report generation in content. 2) The injected external information increases the complexity of model and is hard to be reasonably integrated into the generation process of medical reports. Therefore, we propose an Information Calibrated Transformer (ICT) to address the above issues. First, we design a Precursor-information Enhancement Module (PEM), which can effectively extract numerous inter-intra report features from the datasets as the auxiliary information without external injection. And the auxiliary information can be dynamically updated with the training process. Secondly, a combination mode, which consists of PEM and our proposed Information Calibration Attention Module (ICA), is designed and embedded into ICT. In this method, the auxiliary information extracted from PEM is flexibly injected into ICT and the increment of model parameters is small. The comprehensive evaluations validate that the ICT is not only superior to previous methods in the X-Ray datasets, IU-X-Ray and MIMIC-CXR, but also successfully be extended to a CT COVID-19 dataset COV-CTR.

Multi-source data fusion is widely utilized to enrich the dataset for artificial intelligence methods. However, it also suffers the limitation that samples should have same format and can not be applied to some tasks where input has a different dimension. In the case of dividing coefficients evaluation on water well, the number of injection layers is variable based on the general injection plan of a field. No exiting methods can learn the input with dynamic data format. In order to address this challenge, we propose an intelligent water injection splitting method based on a dynamic temporal convolution network. Specifically, two improvements are proposed: 1) We design a dynamic activation strategy to build data groups according to the number of injection layers and the geographical relationship of each layer. 2) We design a dynamic temporal convolution network to evaluate the dividing coefficient with logging and production data in time series. The input has the data with different injection layers which enrich the samples for model training. We evaluate the model with real-world data from an oil field. The experimental results show the effectiveness of the model. We also compare it with CNN whose input is in the same format, the experimental results show that multi-source information fusion improves the accuracy.

Regular safety inspection is critical to reduce safety risk in industry. Applying the consortium blockchain technology to safety inspection can ensure the effectiveness of the inspection process and tracing of problems. However, there are two major issues when using conventional consortium blockchain. It is challenging to guarantee the authenticity of the retrieved data source, and meanwhile, achieving a balance between performance and security is not easy. Hence, this article proposes a blockchain-based performance-security balanced safety inspection framework (PSB-SIF), in which a safety inspection box is designed to ensure the authenticity of the inspector’s identity while inspection logic is executed automatically via smart contracts. In addition, this article also proposes a novel credit scoring-based Byzantine fault-tolerant (BFT) consensus algorithm, named safety inspection BFT consensus algorithm (SIBFT), which is used to balance the performance and security of consensus network in a safety inspection. We evaluate the proposed approach by comparing with the solutions using RAFT, Practical BFT (PBFT), and SIBFT consensus algorithms in terms of throughput, transaction latency, scalability, and security of PSB-SIF. The evaluation results show that PSB-SIF is efficient for all these quality metrics.

Network virtualization (NV) is a technology with broad application prospects. Virtual network embedding (VNE) is the core orientation of VN, which aims to provide more flexible underlying physical resource allocation for user function requests. The classical VNE problem is usually solved by the heuristic method, but this method often limits the flexibility of the algorithm and ignores the time limit. In addition, the partition autonomy of physical domain and the dynamic characteristics of virtual network request (VNR) also increase the difficulty of VNE. This article proposed a new type of VNE algorithm, which applied reinforcement learning (RL) and graph neural network (GNN) theory to the algorithm, especially the combination of graph convolutional neural network (GCNN) and RL algorithm. Based on a self-defined fitness matrix and fitness value, we set up the objective function of the algorithm implementation, realized an efficient dynamic VNE algorithm, and effectively reduced the degree of resource fragmentation. Finally, we used comparison algorithms to evaluate the proposed method. Simulation experiments verified that the dynamic VNE algorithm based on RL and GCNN has good basic VNE characteristics. By changing the resource attributes of physical network and virtual network, it can be proved that the algorithm has good flexibility.

Trajectory segmentation is a technique of dividing sequential trajectory into segments. These segments are building blocks to various applications. Hence a system framework is essential to support trajectory segment indexing, storage, and query. When the size of segments is beyond the computing capacity of a single processing node, a distributed solution is proposed. In this article, we develop a distributed trajectory segmentation framework that includes a greedy-split segmentation method. This framework consists of distributed in-memory processing and a cluster of graph storage respectively. For fast trajectory queries, we design a distributed spatial R-tree index of trajectory segments. Using the indexes, we build scalable query operations from both in-memory processing and access to graph storage. Based on this framework, we define two metrics to measure trajectory similarity and chance of collision. These two metrics are further applied to identify moving groups of trajectories. We quantitatively evaluate the effects of data partition, parallelism, and data size on the system. We identify the bottleneck factors at the data partition stage and validate two mitigation techniques to data skew. The evaluation demonstrates our distributed segmentation method and the system framework scale as the growth of the workload and the size of the parallel cluster.

The intensity and scale of the opinion fightings in cyberspace on the Russia–Ukraine war (RUW) have opened a new chapter in the history of world warfare. This is a magnificent demonstration of social cognitive war fighting with cyber-physical-social systems (CPSS) that would impact our humankind significantly now and for a long time to come, not just on our understanding of wars, but every aspect of our life. Therefore, it is worth of studying the opinion dynamics of the RUW in the cyberspace. This article will start this direction with an analysis of the evolutionary dynamics of the public opinion fighting, only using Chinese Weibo texts as a case study due to the time constraint. It first clusters the Weibo texts into four categories with unsupervised learning method using Latent Dirichlet Allocation and then collects opinions by extracting keywords. Meanwhile, an opinion adversarial evolution algorithm is proposed to dynamically model the dominance degree of an opinion in the evolutionary processes. We release a dataset of Chinese Weibo associated with RUW. The proposed approach of modeling and analyzing data-driven public opinion dynamics provides a new way for accessing opinion warfare in CPSS.

With the convergence of modern computing technology and social sciences, both theoretical research and practical applications of social computing have been extended to new domains. In particular, social computing was significantly influenced by the recent advances of artificial intelligence (AI). However, the conventional technologies of AI have various drawbacks in dealing with complicated and dynamic problems. Such deficiency can be rectified by hybrid human-artificial intelligence (H-AI), which integrates both human intelligence and AI into one unity, forming a new enhanced intelligence. H-AI in dealing with social problems shows some advantages over the conventional AI. This article firstly reviews the latest research progresses of AI in social computing. Secondly, it summarizes typical challenges AI faces in social computing, which motivate the necessity to introduce H-AI to tackle social-oriented problems. Finally, we discuss the concept of H-AI and propose a holistic architecture of H-AI in social computing, which consists of three layers: object layer, intelligent processing layer, and application layer. The proposed architecture shows that H-AI has significant advantages over AI in solving social problems.

ZigBee is one of the communication protocols used in the Internet of Things (IoT) applications. In typical deployment scenarios involving low-cost and low-power IoT devices, many communication features are disabled, consequently affecting the security offered by ZigBee. The ZigBee specification assumes that deployment of frame counters is sufficient to mitigate replay attacks in secure ZigBee networks. However, we demonstrate that it is insufficient in this paper (i.e., the network is no longer secure after the coordinator restarts). As a countermeasure, we present a timestamp-based scheme to mitigate replay attacks. Our mitigation strategy does not consume power significantly, and fully powered devices will be responsible for providing power-constrained devices with the current timestamp. The proposed scheme is designed for all ZigBee topologies and different states of ZigBee End Devices (ZEDs). Findings from our evaluation show that the proposed scheme can successfully mitigate replay attacks, with no significant network performance degradation even assuming a worst-case scenario (i.e., many devices are sending data simultaneously).

Federated learning learns from scattered data by fusing collaborative models from local nodes. However, conventional coordinate-based model averaging by FedAvg ignored the random information encoded per parameter and may suffer from structural feature misalignment. In this work, we propose Fed2, a feature-aligned federated learning framework to resolve this issue by establishing a firm structure-feature alignment across the collaborative models. Fed2 is composed of two major designs: First, we design a feature-oriented model structure adaptation method to ensure explicit feature allocation in different neural network structures. Applying the structure adaptation to collaborative models, matchable structures with similar feature information can be initialized at the very early training stage. During the federated learning process, we then propose a feature paired averaging scheme to guarantee aligned feature distribution and maintain no feature fusion conflicts under either IID or non-IID scenarios. Eventually, Fed2 could effectively enhance the federated learning convergence performance under extensive homo- and heterogeneous settings, providing excellent convergence speed, accuracy, and computation/communication efficiency.

Device failure detection is one of most essential problems in Industrial Internet of Things (IIoT). However, in conventional IIoT device failure detection, client devices need to upload raw data to the central server for model training, which might lead to disclosure of sensitive business data. Therefore, in this article, to ensure client data privacy, we propose a blockchain-based federated learning approach for device failure detection in IIoT. First, we present a platform architecture of blockchain-based federated learning systems for failure detection in IIoT, which enables verifiable integrity of client data. In the architecture, each client periodically creates a Merkle tree in which each leaf node represents a client data record, and stores the tree root on a blockchain. Furthermore, to address the data heterogeneity issue in IIoT failure detection, we propose a novel centroid distance weighted federated averaging (CDW_FedAvg) algorithm taking into account the distance between positive class and negative class of each client data set. In addition, to motivate clients to participate in federated learning, a smart contact-based incentive mechanism is designed depending on the size and the centroid distance of client data used in local model training. A prototype of the proposed architecture is implemented with our industry partner, and evaluated in terms of feasibility, accuracy, and performance. The results show that the approach is feasible, and has satisfactory accuracy and performance.

Medical diagnostic image analysis (e.g., CT scan or X-Ray) using machine learning is an efficient and accurate way to detect COVID-19 infections. However, the sharing of diagnostic images across medical institutions is usually prohibited due to patients' privacy concerns. This causes the issue of insufficient data sets for training the image classification model. Federated learning is an emerging privacy-preserving machine learning paradigm that produces an unbiased global model based on the received local model updates trained by clients without exchanging clients' local data. Nevertheless, the default setting of federated learning introduces a huge communication cost of transferring model updates and can hardly ensure model performance when severe data heterogeneity of clients exists. To improve communication efficiency and model performance, in this article, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections. First, we design an architecture for dynamic fusion-based federated learning systems to analyze medical diagnostic images. Furthermore, we present a dynamic fusion method to dynamically decide the participating clients according to their local model performance and schedule the model fusion based on participating clients' training time. In addition, we summarize a category of medical diagnostic image data sets for COVID-19 detection, which can be used by the machine learning community for image analysis. The evaluation results show that the proposed approach is feasible and performs better than the default setting of federated learning in terms of model performance, communication efficiency, and fault tolerance.

Real-time intelligent video processing on embedded devices with low power consumption can be useful for applications like drone surveillance, smart cars, and more. However, the limited resources of embedded devices is a challenging issue for effective embedded computing. Most of the existing work on this topic focuses on single device based solutions, without the use of cloud computing mechanisms for parallel processing to boost performance. In this paper, we propose a cloud platform for real-time video processing based on embedded devices. Eight NVIDIA Jetson TX1 and three Jetson TX2 GPUs are used to construct a streaming embedded cloud platform (SECP), on which Apache Storm is deployed as the cloud computing environment for deep learning algorithms (Convolutional Neural Networks - CNNs) to process video streams. Additionally, self-managing services are designed to ensure that this platform can run smoothly and stably, in the form of a metric sensor, a bottleneck detector and a scheduler. This platform is evaluated in terms of processing speed, power consumption, and network throughput by running various deep learning algorithms for object detection. The results show the proposed platform can run deep learning algorithms on embedded devices while meeting the high scalability and fault tolerance required for real-time video processing.

Federated ecology can provide an effective solution forthe serious isolated data island issues caused by data privacy protection and information security requirements in the era of artificial intelligence (AI). As the data foundation of federated ecology, federated data include the data of all the nodes in the federation, as wellas their storage, computation, and communication resources. For privacy-preserving, federated data are divided into private data and non-private data, and through the federated control of these data, data federalization can be realized. In data-driven AI technologies, federated data play an important role, and it can help realize effective data retrieval, pre-processing, processing, mining, and visualization for AI-based applications. It can also provide effective solutionsfor the dilemmas faced by AI technologies, such as training AI models without sufficient data, increasing the generality of AI models for different application scenarios and establishing a unified processing workflow for data security and privacy control in AI-based applications.

The unprecedented development of the Internet of Things (IoT), artificial intelligence (AI), and Big Data has stimulated a boom of social networks such as Twitter, WeChat, Facebook, etc., generating a huge amount of social data that are worth further analysis. Social computing has an important focus on mining the deep relationships between social organizations, networks, and media. The increasing volumes and complexities make big social data mining more and more difficult. Hybrid Human–Artificial Intelligence (H-AI) is an approach combining both human intelligence and AI, so as to handle demanding problems in a harmonious way. By adopting H-AI in social computing, it would provide more possibilities for social data analysis, relationship discovery, outlier detection, and prediction, and is proving to be an emerging and promising direction for AI and big data research.

Traditional character segmentation has low accuracy for container scene text recognition. Convolutional recurrent neural network (CRNN) and connectionist text proposal network (CTPN) methods cannot extract container text features effectively. This paper proposes a novel Container Text Detection and Recognition Network (CTDRNet) for accurately detecting and recognizing container scene text. The CTDRNet consists of three components: (1) CTDRNet text detection enables to improve detection accuracy for single words; (2) CTDRNet text recognition has faster convergence speed and detection accuracy; (3) CTDRNet post-processing improves detection and recognition accuracy. In the end, the CTDRNet is implemented and evaluated with an accuracy of 96% and processing rate of 2.5 fps.

Recently, there is a rising interest in perceiving image aesthetics. The existing works deal with image aesthetics as a classification or regression problem. To extend the cognition from rating to reasoning, a deeper understanding of aesthetics should be based on revealing why a high‐ or low‐aesthetic score should be assigned to an image. From such a point of view, the authors propose a model referred to as Neural Aesthetic Image Reviewer, which can not only give an aesthetic score for an image, but also generate a textual description explaining why the image leads to a plausible rating score. Specifically, they propose three models based on shared aesthetically semantic layers and task‐specific embedding layers at a high level for performance improvement on different tasks. To facilitate researches on this problem, they collect the AVA‐Reviews dataset, which contains 52,118 images and 312,708 comments in total. Through multi‐task learning, the proposed models can rate aesthetic images as well as produce comments in an end‐to‐end manner. It is confirmed that the proposed models outperform the baselines according to the performance evaluation on the AVA‐Reviews dataset. Moreover, they demonstrate experimentally that the authors’ model can generate textual reviews related to aesthetics, which are consistent with human perception.

The ubiquitous connections of physical objects in Internet of Things (IoT) is undoubtedly challenging the consistency mapping between physical space and cyberspace. As the key techniques for establishing the correspondences between physical objects and cyber entities, the objects identification and resolution (IR) attracted extensive attention. Conventional IR schemes in IoT generally rely on a single-mode of identification (ID) or nonidentification (nID) IR, which has big limitations in adaptability and reliability. In this case, a combined IR scheme based on ID and nID is proposed in this paper. In our proposed scheme, the ID code and nID features complement each other so as to break the restrictions of application domain and to provide better and humanized services. In order to improve the efficiency of the scheme, edge computing is introduced to reduce network transmission load and the computing burden of cloud, especially when the input data requires large amount of computing and storage resources. Furthermore, we design and implement a prototype of electronic product code (EPC) (ID) and fingerprint (nID) combined IR. Simulation results show that the edge computing-based ID and nID combined IR scheme has advantages in resolution accuracy and efficiency.

Ship plate recognition is challenging due to variations of plate locations and text types. This paper proposes an effcient Fully Convolutional Network based Plate Recognition approach FCNPR, which uses a CNN (Convolutional Neural Network) to locate ships, then detects plate text lines with the fully convolutional network (FCN). The recognition accuracy is improved with integrating the AIS (Automatic Identification System) information. The actual FCNPR deployment demonstrates that it can work reliably with a high accuracy for satisfying practical usages.

Seeking effective measures to characterize the chaotic patterns of EEG signals for seizure diagnosis is a long-term endeavor in the literature. We propose to count the number of zero-crossing (ZC) points on Poincaré surface as a feature when the time series of interest is embedded into the reconstructed state space. The experiments show that Poincaré surface can act as a platform to observe the chaotic patterns of EEG signals and the ZC feature on Poincaré surface is a promising pattern descriptor to discriminate different categories of EEG signals. When used alone for EEG classification, the ZC feature achieves 100%, 99.27%, and 94.68% accuracy in 2-class, 3-class, and 5-class classification on a widely used benchmark.

Social data from online social networks is expanding rapidly as the number of users and articles posted increases, making public opinion analysis a greater challenge. Real-time topic detection is a key part of public opinion analysis. The complex data processing involved in traditional clustering and text categorization can lead to time delays in topic detection. In this paper we construct similar networks and detect topics from similar communities that reduces the processing overhead in obtaining real-time topics. The similar communities consist of users with high similarity between them. We collect public topics from the microposts of delegates selected from each similar community. Selecting delegates can reduce the processing time of large amounts of redundant data during topic detection. Obtaining public opinion keywords in real time allows organizations to respond to public opinion security incidents in real time. Experiments showed that our scheme can find public topics faster and more effectively than two traditional algorithms.

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

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

Email spam consumes a lot of network resources and threatens many systems because of its unwanted or malicious content. Most existing spam filters only target complete-spam but ignore semispam. This paper proposes a novel and comprehensive CPSFS scheme: Credible Personalized Spam Filtering Scheme, which classifies spam into two categories: complete-spam and semispam, and targets filtering both kinds of spam. Complete-spam is always spam for all users; semispam is an email identified as spam by some users and as regular email by other users. Most existing spam filters target complete-spam but ignore semispam. In CPSFS, Bayesian filtering is deployed at email servers to identify complete-spam, while semispam is identified at client side by crowdsourcing. An email user client can distinguish junk from legitimate emails according to spam reports from credible contacts with the similar interests. Social trust and interest similarity between users and their contacts are calculated so that spam reports are more accurately targeted to similar users. The experimental results show that the proposed CPSFS can improve the accuracy rate of distinguishing spam from legitimate emails compared with that of Bayesian filter alone.

There arises the needs for fast processing of continuous video data using embedded devices, for example the one needed for UAV aerial photography. In this paper, we proposed a distributed embedded platform built with NVIDIA Jetson TX1 using deep learning techniques for real time video processing, mainly for object detection. We design a Storm based distributed real-time computation platform and ran object detection algorithm based on convolutional neural networks. We have evaluated the performance of our platform by conducting real-time object detection on surveillance video. Compared with the high end GPU processing of NVIDIA TITAN X, our platform achieves the same processing speed but a much lower power consumption when doing the same work. At the same time, our platform had a good scalability and fault tolerance, which is suitable for intelligent mobile devices such as unmanned aerial vehicles or self-driving cars.

A large number of video applications require real-time response. The high-speed video processing then requires a distributed and parallelized framework utilizing all possible computing resources, i.e., both Central Processing Unit (CPU) and Graphics Processing Unit (GPU) at their best. The CPU-GPU collaboration may cause resource imbalance where GPU-based jobs consume less computing resources while occupying more memory compared with CPU-based jobs. In this paper, we propose a load-aware pluggable cloud framework for real-time video processing where CPU-GPU switching based on workload status can be performed at runtime. Furthermore, we design aspect-oriented monitors to collect framework metrics and propose a distance coverage algorithm to detect performance degradation in order to make sure that the framework runs optimally to achieve good performance when a load-aware task switching is made. We have comprehensively evaluated the framework and the evaluation results show that the proposed framework has good performance, reusability, pluggability, and scalability.

Cloud system management is complex due to their diversity and frequent runtime changes. Cloud systems were previously managed through cloud specific management tools that focus on optimising technical metrics, such as performance. However, business users care business metrics (such as cost and revenue) more than technical metrics. To address these issues, this paper proposes a unified business-driven cloud management framework, which enables optimisation of business metrics without limiting business to a specific cloud provider. The main contributions include: (1) a taxonomy which defines a set of actions, events and metrics for unified cloud management; (2) a cloud management policy language that specifies cloud management policies from a business perspective; and (3) middleware architecture that allows business-driven management of diverse clouds. The proposed solutions are evaluated in terms of feasibility, functional correctness, generality, usefulness, and performance.

Crowd motion in surveillance videos is comparable to heat motion of basic particles. Inspired by that, we introduce Boltzmann Entropy to measure crowd motion in optical flow field so as to detect abnormal collective behaviors. As a result, the collective crowd moving pattern can be represented as a time series. We found that when most people behave anomaly, the entropy value will increase drastically. Thus, a threshold can be applied to the time series to identify abnormal crowd commotion in a simple and efficient manner without machine learning. The experimental results show promising performance compared with the state of the art methods. The system works in real time with high precision.

Microblog plays an important role in the dissemination of information now, especially on some sensitive topics. We established the propagation model of the microblog was constructed in this paper. The weak ties are used in the microblog network to obtain independent communities. We analyzed degree centrality, betweenness centrality and closeness centrality of microblog network. Various messages disseminate from different nodes with various feature which can be preset. The characteristics of some nodes in the information dissemination process become clearer according to the comparison among results after message dissemination. We analyzed the impacts of some nodes with information entropy during the information dissemination, which is so important to guide public opinion and maintain social stability.

Planning (for example choosing most suitable services for self-configuration) is one important task in self-management for pervasive service computing, and can be reduced to the problem of multi-objective services selection with constraints. Genetic algorithms (GAs) are effective in solving such multi-objective optimization problems, and are one of the most successful computational intelligence approaches currently available. GAs are beginning to be used in planning for self-management, but there is a lack of comprehensive work that evaluates GAs performance and solution quality, and guides the setting of GAspsila parameters.This situation makes the application of GAs difficult in the pervasive service computing domain in which performance may be critical and the settings of parameters may have big consequences for performance. In this paper, we will present our evaluations of two GAs, namely NSGA-II and MOCell, in the GA framework JMetal2.1, for achieving multi-objective selection of available services. From these evaluations, suggestions on how and when to use NSGA-II and MOCell are given in the planning for self-management.Our experiences show that to get a true Pareto front for a problem, combining solutions set from different GAs is abetter way than using a single GA.

There is a growing trend to develop open world software with the forthcoming of the pervasive computing era.Traditional research on software architecture, components,and connectors is not geared towards the characteristics of open world software, and are not easily used in open world environments. In this paper, we present an extensible knowledge base called SACoCo (Semantic Architectural styles, Components, and Connectors), by applying Web Ontology Language (OWL) and Semantic Web Rule Language(SWRL) where an Open World Assumption (OWA)is adopted. Runtime validations of component configurations and software architectural styles can be specified with SWRL rules. SACoCo improves the semantics of classical architectural styles, components and connectors, andcan be used to dynamically validate software architectural styles and component configurations. Experiments with a pervasive web service compiler using OSGi and the Repository style show that the knowledge base is effective in improving the semantics of components and connectors, and is effective to validate component configurations and architectural styles, especially in open world environments.

There is a growing trend to deploy Web services in pervasive computing environments. Implementing Web services on networked, embedded devices leads to a set of challenges, including productivity of development, efficiency of Web services, and handling of variability and dependencies of hardware and software platforms. To address these challenges, we developed a Web service compiler called Limbo, in which Web Ontology Language (OWL) ontologies are used to make the Limbo compiler aware of its compilation context such as device hardware and software details, platform dependencies, and resource/power consumption. The ontologies are used to configure Limbo for generating resource-efficient Web service code.The architecture of Limbo follows the Blackboard architectural style and Limbo is implemented using the OSGi declarative services component model. The component model provides high flexibility for adding new compilation features. A number of evaluations show that the Limbo compiler is successful in terms of performance, completeness, and usability.

Mobile games are one of the primary entertainment applications at present. Limited by scarce resources, such as memory, CPU, input and output, etc, mobile game development is more difficult than desktop application development, with performance as one of the top critical requirements. As object-oriented technology is the prevalent programming paradigm, most of the current mobile games are developed with object-orientation (OO) technologies. Intuitively OO is not a perfect paradigm for embedded software. Questions remain such as how OO and to what degree OO will affect the performance, executable file size, and how optimization strategies can improve the qualities of mobile game software. These questions are investigated in this paper within the mobile Role-Playing-Game (RPG) domain using five industrial mobile games developed with OO. We analyzed them and found excessive usage of OO features used for the development of mobile device applications (but normal for usual desktop applications). We then apply some optimization strategies along the way of structural programming. The experiment shows that the total jar file size of these five optimized games decreases 71 % the lines of codes decreases 59%, and the loading time of each optimized game decreases 22.73%, 34.62% 25.79% 24.65% and 16.70% respectively. Therefore, we conclude from our experiments that 00 should be used with great care in the development of mobile games, and that structural programming can be a very competitive alternative.

Current mobile middleware is designed according to a 'one-size-fits-all' paradigm, which lacks the flexibility for customization and adaptation to different situations, and does not support user-centered application scenarios well. In this paper we describe an ongoing intelligent mobile middleware research project called PLIMM that focuses on user-centered application scenarios. PLIMM is designed based on software product line ideas which make it possible for specialized customization and optimization for different purposes and hardware/software platforms. To enable intelligence, the middleware needs access to a range of context models. We model these contexts with OWL, focusing on user-centered concepts. The basic building block of PLIMM is the enhanced BDI agent where OWL context ontology logic reasoning will add indirect beliefs to the belief sets. Our approach also addresses the handling of ontology evolutions resulting from the timely adaptation of ontology to changes and the consistent propagation of these changes to all related artifacts, using Frame based product line configuration techniques.

XVCL (XML-based Variant Configuration Language) is a meta-programming technique and tool that provides effective reuse mechanisms [2]. XVCL is an open source software (http://fxvcl.sourceforge.net) developed at the National University of Singapore. Being a modem and versatile version of Bassett's frames [1], a technology that has achieved substantial gains in industry, the underlying principles of the XVCL have been thoroughly tested in practice. Unlike original frames, XVCL blends with contemporary programming paradigms and complements other design techniques. XVCL uses "composition with adaptation" rules to generate a specific program from generic, reusable meta-components. Program generation rules are 100% transparent to a programmer, who retains full control over fine-tuning the generated code. Despite its simplicity, XVCL can effectively manage a wide range of program variants from a compact base of metacomponents, structured for effective reuse.