Accurate orbit prediction of lunar satellites is the foundation for providing precise positioning services to user terminals. However, due to limited ground tracking capability and simplifications in the orbital dynamics model, the prediction accuracy of lunar satellite orbits declines significantly over time when ground support is unavailable. Recently, orbit error prediction methods based on deep learning have shown the significant ability. However, exisiting deep learning models are mainly applied to Earth-orbiting satellites, and they typically extract orbital error features only in time domain or frequency domain. This results in information loss during the extraction process and limited ability to extract features from complex time signals. In this paper, we propose a novel model called DWC-Mixer for orbit correction of lunar navigation satellite, which combines frequency domain decomposition based on wavelet transform with time embedding of third body perturbation. The DWC-Mixer can effectively capture the perturbation effects not considered in the dynamical model. Extracting multi frequency and multi period variations from the orbit error sequence of the dynamic model using wavelet decomposition, ultimately achieving accurate correction of the Lunar orbit satellite trajectory prediction. First, one-dimensional convolution decomposes the lunar satellite orbit error data into several scales to obtain scale specific error variations. Next, wavelet transform and max-pooling break each scale into time and frequency domain components, extracting finer features. A time-embedding step is then applied to highlight the periodic patterns within the lunar orbit error sequence. Finally, a macro-detail fusion block recombines the refined features and feeds them into an Multi-Layer Perceptron(MLP) for training, yielding accurate orbit error predictions. We evaluate the performance on a simulated dataset. By employing the DWC-Mixer model to correct theJ2dynamic model, the ELFO orbit prediction error is reduced by 34.62% compared to other baseline network models. For PCO and LLO orbits, the errors decrease by 24.74% and 7.04%, respectively. This approach offers robust technical support for the development of lunar navigation constellations.

Recently, large models have shown significant potential for smart healthcare. However, the deployment of Large Vision-Language Models (LVLMs) for clinical services is currently hindered by three critical challenges: a tendency to hallucinate answers not grounded in visual evidence, the inefficiency of fixed-depth reasoning, and the difficulty of multi-institutional collaboration. To address these challenges, in this paper, we develop MedAlign, a novel framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA). Specifically, we first propose a multimodal Direct Preference Optimization (mDPO) objective to explicitly align preference learning with visual context. We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM (i.e., an expert), thereby mitigating hallucinations in LVLMs. To achieve adaptive reasoning and facilitate multi-institutional collaboration, we propose a federated governance mechanism, where the selected expert, fine-tuned on clinical datasets based on mDPO, locally performs iterative Chain-of-Thought (CoT) reasoning via the local meta-cognitive uncertainty estimator. Extensive experiments on three representative Med-VQA datasets demonstrate that MedAlign achieves state-of-the-art performance, outperforming strong retrieval-augmented baselines by up to 11.85% in F1-score, and simultaneously reducing the average reasoning length by 51.60% compared with fixed-depth CoT approaches.

In serverless vehicular edge computing (SVEC), a variety of vehicular services are encapsulated into the containers deployed on accessible edge computing nodes such as roadside edge servers and nearby vehicular terminals, aiming to bring remarkable benefits to the service management, e.g., simplifying the infrastructure management, improving the resource utilization, and dynamically scaling up or down in response to the resource demand. However, there still exists a challenging service scheduling problem between the requester vehicles and available SVEC processors, due to the the dynamic vehicle mobility and heterogeneous edge computing environment. In the problem, a set of request vehicles can locally process the service requests, or offload them to a nearest edge server and peripheral vehicular terminals. We particularly consider the essential difference of the edge server and hardware-constrained vehicular terminals in the storage capacity and computing capabilities for running the containers, and aim to minimize the total service cost of all requester vehicles subject to the mobility constraints of the vehicles. To address the problem, we propose a diffusion-based deep reinforcement learning (DRL) approach to quickly learn a high-accuracy solution. Numerical results demonstrate that compared with the baseline DRL approaches, the proposed approach has great advantages in both the learning accuracy and convergence rate.

Automated heartbeat classification in Holter monitoring is pivotal for IoT-enabled healthcare, enabling continuous cardiac surveillance. However, this task faces two major challenges: (1) weak pathological electrocardiogram (ECG) features are often obscured by noise, and (2) discriminative ECG patterns vary significantly in their temporal spans, depending on the heartbeat types and contextual rhythms. To address these issues, we propose a novel multi-view multi-range attention (MVMRA) network, which integrates three key modules: First, a multi-view feature extraction module employs 1-D and 2-D convolutional networks to respectively capture intra-beat morphological details and multi-band inter-beat correlations, enriching latent representations while disentangling weak pathological information. Next, a multi-view cross-attention fusion module adopts a lumpedbranch interactive structure, leveraging high-level semantic features to sequentially learn temporal-wise and channel-wise attention masks. This progressively refines multi-view features, enhancing adaptability to diverse ECG patterns. Finally, a multi-range group attention module dynamically aggregates discriminative information across multiple temporal ranges by using compressed and selected attention mechanisms, simulating variable diagnostic scopes and emphasizing pathology-specific contexts. Extensive evaluations on the MIT-BIH arrhythmia database confirm that our model outperforms existing approaches, achieving state-of-the-art accuracies of 97.23% and 98.23% for five-class and three-class tasks, respectively. Moreover, the network delivers real-time inference (< 27 ms) on an ARM64 embedded platform, highlighting its potential for practical IoT-based cardiovascular disease detection.

The rapid development of autonomous driving technologies and the expansion of the Internet of Things (IoT) have intensified the demand for timely and accurate vehicular perception, highlighting the potential of leveraging vehicular edge computing (VEC) systems to support perception tasks. Unmanned aerial vehicles (UAVs), owing to their flexible mobility and line-of-sight advantages, have emerged as promising IoT-enabling aerial platforms to enhance both vehicular perception and computation capabilities in VEC environments. In this paper, we propose an accuracy-oriented and computation-efficient framework for air-ground cooperative sensing and computing, wherein a UAV cooperates with a group of connected and autonomous vehicles (CAVs) to collect sensing data of the objects around them, followed by data fusion and computation for object classification. We formulate a joint optimization problem involving UAV trajectory planning and sensing task placement, aiming to minimize the sensing accuracy error and task processing delay. The joint optimization problem is reformulated as a Markov decision process (MDP), where a penalty term for constraint violations is incorporated into the reward function to ensure feasibility. Furthermore, we develop an improved twin delayed deep deterministic policy gradient (TD3)-based algorithm for UAV-assisted cooperative sensing and computing to derive an efficient UAV trajectory control and subtask placement strategy. Results demonstrate that the proposed algorithm achieves superior performance compared to baselines in terms of convergence speed, training stability, and cost-saving, validating its applicability in dynamic UAV-assisted VEC environments.

Decentralized federated learning (DFL) and efficient content delivery are critical in uncrewed aerial vehicle (UAV)-assisted internet of vehicles (IoV). However, the performance is hampered by dynamic topology, energy constraints, and fluctuating computational loads. In this paper, we present a unified optimization framework that reuses the DFL aggregation structure for cooperative edge caching in UAV-assisted IoV. In the first stage, we formalize the hierarchical DFL aggregation route as an NP-hard combinatorial problem and solve it with a graph neural network (GNN)-enhanced proximal policy optimization (PPO) algorithm for aggregation route (GPPO-R), which rapidly converges to near-optimal routing structures and achieves the trade-off balance between synchronization latency and energy consumption. In the second stage, we design a DFL-based multi-agent PPO caching strategy (DFL-MAPPO) that leverages the DFL aggregation structure and neighbor-state sharing. It consists of two phases: a long short-term memory (LSTM)-driven proactive caching phase, where the LSTM model is trained via DFL. And a real-time multi-agent reinforcement learning (MARL) phase for dynamic cache adjustment. Extensive simulations across varying number of UAVs, cache capacities, and user loads demonstrate that GPPO-R and DFL-MAPPO jointly reduce request latency and energy overhead compared to independent variants and classical schemes. The results validate the effectiveness and scalability of the proposed framework in dynamic UAV networks, providing a robust solution for integrated model aggregation and content caching in IoV.

In recent years, numerous hashing techniques have been developed to boost efficient cross-modal retrieval. Once a retrieval model is deployed, the hash code length is fixed to achieve optimal performance. To address different retrieval scenarios while maintaining retrieval accuracy, a common approach is to redesign and retrain the original model with different hash code length. However, this retraining process can increase the training load and may lead to worse results. To tackle these challenges, we present Regenerated Cross-Modal Hashing (RCMH), a novel cross-modal hashing framework designed to improve the quality of existing hash codes and convert them to arbitrary lengths with high efficiency. First, we clip or pad the existing hash codes to initialize them with the target length, under the supervision of the similarity matrix generated by the augmented label information. Second, we introduce a linear-nonlinear competitive reconstruction approach to reduce the semantic gaps and further capture the deeper relationships from linear image features and nonlinear text features. In this way, each pair of samples is compared and selected to obtain reconstructed binary codes that can preserve the modality-specific properties. Finally, to reduce the training costs caused by iterations of variables, the regenerate hashing term is utilized to regenerate final hash codes with the reconstructed binary codes while preserving the information from the existing hash codes without iterative optimization. Notably, RCMH can be integrated with existing state-of-the-art (SOTA) methods with robustness, helping them to adjust the hash code length and achieve better retrieval performance.

The generative pre-training transformer (GPT) has been demonstrated to be remarkably effective in natural language processing. Motivated by advances in GPT, a geometric matching network with a generative pre-training transformer (GMNet) is proposed in this paper to provide high-quality automatic 3D object tracking for intelligent systems. Specifically, the characteristics of GMNet can be summarized as follows. First, a geometry-rebuild pre-training strategy is proposed to enhance the perception of incomplete geometry. Under this training strategy, the network is pre-trained on point cloud completion datasets to learn shape-inference capabilities and obtain a robust latent representation for tracking. After pre-training, the network is fine-tuned with the tracking data to achieve high-precision object tracking. Second, a shape reasoning module (SRM) with generative pre-training is designed to perform point cloud completion, aiming to refine geometric features by leveraging shape perception and reasoning abilities learned from geometry-rebuild pre-training. Third, an adaptive gated feature matching module (FMM) is designed to perform adaptive feature matching via a gate mechanism, which predicts the object’s location based on adaptively matched information derived from cosine similarity and SRM. Furthermore, extensive experiments demonstrate that the proposed GMNet outperforms state-of-the-art methods on KITTI, nuScenes, and Waymo open benchmarks.

This paper focuses on the Nash equilibrium problem for non-cooperative games over general directed graphs with application to energy allocation. Unlike previous Nash equilibrium-seeking works that typically required strongly connected or undirected graphs, we now relax the network to contain a spanning tree. To overcome the inaccessibility caused by the general graph, we introduce an information collector who gathers player profiles and acts as the leader. Under this framework, each player preserves the state observation from leader through the spanning-tree network, and uses gradient descent to adjust variables for converging to an equilibrium point. We also present an enhanced version that invests the solo coupling gain with adaptation through distributed consensus error. The proposed schemes ensure the globally asymptotic stability of the Nash equilibrium-seeking process through Lyapunov analysis. Finally, numerical studies, as well as hardware-in-the-loop experiments for energy allocation on the RT-Lab platform, are provided to demonstrate the effectiveness of the proposed protocols.

This article addresses the predefined-time optimal motion control problem of an autonomous surface vehicle (ASV) with disturbances under dynamic self-triggered frameworks via reinforcement learning (RL). Initially, to eliminate the influence of disturbance on the ASV, a predefined-time second-order integral sliding mode control (SOISM) strategy is formulated by establishing a novel integral sliding mode (ISM) function and a terminal sliding mode function. Subsequently, a predefined-time approximate optimal motion (AOM) control strategy is further developed to ensure the ASV maintains a stable state. Furthermore, a single critic network is used to obtain an approximate solution of the Hamilton-Jacobi-Bellman (HJB) equation. The above two strategies are established under the dynamic self-triggered framework, which relies on the current information to predict the next updating time, effectively reducing the computational and communication burden while avoiding the continuous monitoring of the ASV state. In the theoretical analysis, the main challenges lie in the design of Lyapunov functions and triggered conditions to ensure the stability of the sliding mode dynamics and the disturbed ASV. By applying the Lyapunov stability principle and designing two novel Lyapunov functions and triggered conditions that both contain dynamic variables, we demonstrate that the developed control strategies can ensure the stability within the specified time frame. Ultimately, simulation results verify the efficacy of the proposed motion control approach.

Zero-shot anomaly detection (ZSAD) is a challenging task that aims to detect anomalies in images without any prior knowledge of the anomaly classes. This task is especially difficult because anomalies are rare, diverse, and often manifest differently across domains, making it hard for models to generalize when training data is scarce or unavailable. Recently, vision-language models (VLMs), such as CLIP, have shown great potential in ZSAD, but they often struggle to adapt to unseen domains due to the lack of domain-aware knowledge. To address these challenges, we propose the Domain Adaptation CLIP (DACLIP), a novel approach that adapts domain-aware knowledge to the VLM. Specifically, DACLIP leverages a Domain-Aware Knowledge Adaptation (DAKA) strategy to enhance CLIP for ZSAD across different domains. The DAKA strategy comprises multiple experts that specialize in target domains, enabling the model to dynamically select and combine specialized experts tailored to anomaly characteristics, thus improving its ability to generalize and detect a wide range of anomalies. Furthermore, we introduce learnable domain-aware prompts that are jointly learned by and injected into both the CLIP encoders (visual and text) and the DAKA modules. This dual-pathway learning enables the model to capture domain-specific features at multiple levels of the architecture, allowing for more effective adaptation to new domains and anomaly types. We evaluate our approach on several benchmark datasets spanning industrial and medical domains. Extensive experiments demonstrate that DACLIP consistently outperforms state-of-the-art methods in ZSAD, achieving significant improvements in both image-level and pixel-level anomaly detection tasks.

Dispersed computing has emerged as a promising paradigm that leverages underutilized resources from massive Internet of Things devices (IoTDs) to enhance the computing capacity at the network edge. However, existing works about the dispersed computing overlook the heterogeneous computing environment with parallel and serial computations and task reliability requirements for the hardware-constrained IoTDs, and they lack multi-objective optimization approaches to optimize the task offloading. To address the challenges, we propose a comprehensive scheme to achieve a delay-aware and economic-aware dispersed computing paradigm by using a multi-objective optimization approach. Particularly, we consider parallel processing at an edge server and serial processing at the lightweight IoTDs, and leverage the task redundancy to satisfy the task reliability requirements on the IoTD side. We further formulate a constrained multi-objective optimization problem (CMOP) aiming at jointly optimizing the task assignment, bandwidth allocation, and CPU frequency allocation to simultaneously minimize the total delay cost and the total charge cost of the tasks. To address the CMOP, we propose an improved constrained multi-objective evolutionary algorithm that employs a dual-population cooperative mechanism between two populations and a repairing constraint-handling technique. The dual-population cooperative mechanism can balance convergence toward Pareto optimality and solution diversity maintenance. The repairing constraint-handling technique is designed to guide solutions toward feasible regions, achieving efficient exploration of complex constrained search spaces. Simulation results demonstrate the superiority of our algorithm in seeking the better-converged and better-distributed Pareto optimal solutions to well address the tradeoffs between the two objectives.

The rising data demands of generative AI models, such as large language models (LLMs), underscore the value of utilizing edge device data in mobile computing, where federated learning (FL) provides a privacy-preserving approach via decentralized model training. To address data heterogeneity across edge devices, federated multi-view learning (FedMVL) has been proposed to improve global model performance by capturing consistency and complementarity among diverse data views. However, existing methods often assume ideal conditions and neglect data uncertainty in mobile edge devices environments. To overcome these challenges, we propose Federated Reliable Multi-view Classification (FedRMVL), a vertical FedMVL framework incorporates Subjective Logic for lightweight uncertainty quantification at local edge devices and applies the Dempster-Shafer combination rule for adaptive and reliable multi-view opinion fusion at the server. Additionally, a partial parameter-sharing strategy is introduced to address feature dimension heterogeneity during federated optimization. The effectiveness and robustness of FedRMVL are validated through theoretical analysis and extensive experiments on real-world datasets.

The vehicular metaverse is a novel physical-virtual fusion realm that aims to disrupt the current transportation paradigm. Within this landscape, the coexistence of moving vehicles and their digital counterparts inevitably brings new privacy concerns. Pseudonym exchange, where vehicles exchange temporary identifiers with neighbors to enhance anonymity, offers an affordable solution to protect the location privacy of vehicles. However, existing pseudonym exchange schemes primarily focus on physical vehicles, limiting their effectiveness across physical and virtual spaces in the vehicular metaverse. Furthermore, studies have shown that many vehicles care little about their location privacy, so incentivizing more vehicles to participate in pseudonym exchanges remains a challenge. Motivated by these issues, we propose a physical-virtual dual pseudonym exchange scheme, incorporating an Attribute-Matched Double Dutch Auction (AMDDA) incentive mechanism to facilitate pseudonym exchange transactions. We use a trajectory prediction model to evaluate vehicle attributes, ensuring pseudonym exchange between vehicles with high trajectory similarity to enhance location privacy preservation. Furthermore, we devise a Generative Diffusion Model (GDM)-based approach to derive the optimal pricing strategy in the AMDDA market. Extensive experiments on real-world datasets demonstrate that the proposed scheme significantly improves both the efficiency and degree of location privacy protection.

In long-distance and long-duration flight missions of unmanned aerial vehicles (UAVs), optimal scheduling of flight speed and energy replenishment is crucial to ensure flight efficiency and safety. This paper focuses on a UAV-based patrol inspection system, where a UAV is scheduled to visit multiple task nodes that are geographically distributed in the communication coverage of a base station (BS). The UAV hovers at each task node, performing data collection and data processing. The BS is equipped with a mobile edge computing (MEC) server and a battery swapping station, offering computation and energy support to the UAV. A decision-making model customized for the UAV is proposed, jointly optimizing flight speed selection, battery swapping, and task offloading to minimize the UAV's total operational cost in its flight. By introducing virtual nodes in the flight network, we construct a unidirectional extended graph, based on which the original nonconvex cost minimization problem is reformulated to a tractable mixed-integer convex problem. Further, a fast heuristic based on analytical target cascading (ATC) is developed to obtain suboptimal solutions to large-scale problems. Results demonstrate that the proposed model can lower the UAV's total operational cost by providing greater flexibility in terms of speed selection and battery swapping, and the proposed heuristic shows high computational efficiency for large-scale network scenarios.

The development of Deep Neural Networks (DNNs) has enabled AI-driven models to excel in recognizing a limited set of classes within static environments. As AI systems progress, few-shot class-incremental learning (FSCIL) aims to expand their understanding of novel classes from minimal samples while retaining knowledge of previously encountered ones. However, most existing FSCIL models face significant challenges, includinginadequate adaptabilityandcatastrophic forgetting, which hinder their ability to maintain robust forward and backward learning capabilities. To address these issues, this paper proposes a novel Forward-Backward Knowledge Transfer (FBKT) paradigm, which strategically integrates forward distribution adaptation (FDA) and backward semantic alignment (BSA) mechanisms to achieve bidirectional adaptability in knowledge transfer. The FDA mechanism enhances forward adaptability by expanding and reserving the embedding space for new classes using semantic-irrelevant masked images as virtual negative classes, thereby mitigating data overfitting. It also employs self-supervised representation learning to utilize semantic-relevant local embeddings as additional positive samples, fostering class separation and generalization. Meanwhile, the BSA mechanism ensures the semantic consistency of previously learned classes across sessions during class-incremental learning, promoting smoother backward adaptability and reducing model degradation. Extensive experiments conducted on multiple benchmark datasets consistently highlight the superior performance and effectiveness of our FBKT compared to state-of-the-art methods.

Partial Multi-Label Learning (PML) deals with a practical scenario where each instance is associated with a set of candidate labels, among which only a subset corresponds to the ground-truth labels while the others are unrelated. Existing PML methods typically employ label association recovery as a structural disambiguation strategy to identify credible labels. However, these methods attempt to recover associations directly from candidate labels, which leads to unreliable disambiguation due to the distorted label structures. To this end, this paper proposes a novel PML method via dual label association recovery (PML-DLAR).The essential strategy is to first eliminate the spurious correlations in label space before recovering dual label associations. Specifically, a biorthogonal transformation is employed to decouple the instance-level and label-level association structures affected by noisy labels. Subsequently, reliable instance-level associations are reconstructed through global geometric structure alignment between feature and pseudo-label spaces. Finally, class specific feature representations are constructed through class prototypes to guide label-level semantic association recovery in label space. Comprehensive experiments validate the superior performance of PML-DLAR over state-of-the-art methods.

Federated learning is essential for enabling collaborative model training across decentralized data sources while preserving data privacy and security. This approach mitigates the risks associated with centralized data collection and addresses concerns related to data ownership and compliance. Despite significant advancements in federated learning algorithms that address communication bottlenecks and enhance privacy protection, existing works overlook the impact of differences in data feature dimensions, resulting in global models that disproportionately depend on participants with large feature dimensions. Additionally, current single-view federated learning methods fail to account for the unique characteristics of multi-view data, leading to suboptimal performance in processing such data. To address these issues, we propose a Self-expressive Hypergraph Based Federated Multi-view Learning method (FedMSGL). The proposed method leverages self-expressive character in the local training to learn uniform dimension subspace with latent sample relation. At the central side, an adaptive fusion technique is employed to generate the global model, while constructing a hypergraph from the learned global and view-specific subspace to capture intricate interconnections across views. Experiments on multi-view datasets with different feature dimensions validated the effectiveness of the proposed method.

Taking into account the flexible deployment and Line-of-Sight (LoS) communication links of uncrewed aerial vehicles (UAVs), this article proposes a multi-UAV-assisted vehicular edge computing networks (VECNs) architecture to provide instantaneous computation support at multiple congestion road segments. Given that the computation resources of a single UAV are insufficient, and offloading tasks directly to the cloud computing center (CCC) in intelligent transportation systems (ITSs) introduces significant latency, multiple UAVs with precached service or content caching data are deployed optimally for the vehicle users. In order to address the tradeoff between system costs and service efficiency, we propose a novel cost-efficient layered optimization scheme, in which the number and deployment positions of UAVs are jointly optimized. According to the varying vehicular network environments and the dynamic requirements of vehicle users, we design a hierarchical reinforcement learning algorithm, combining double deep Q network (DDQN) and multiagent deep deterministic policy gradient (MADDPG), the former is used to optimize the number of UAVs, and the deployment of UAVs are optimized via the MADDPG. Simulation results demonstrate the effectiveness of the proposed scheme in lowering total task completed latency and increasing the system profits. The service efficiency in dealing with the vehicle users’ requirements also be improved.

Unsupervised learning provides efficient analytical tools for data-centric Internet of Things (IoT) applications. Nonnegative matrix factorization (NMF) is a fundamental tool in unsupervised machine learning, offering interpretable and part-based feature representations. While NMF is provably robust to bounded additive perturbations, the emergence of adversarial attacks highlights the need to reassess the certified robustness under strategically crafted perturbations. In this work, we propose a novel attack method that more effectively disrupts NMF factorization than existing adversarial methods by incorporating two key strategies: i) imposing low-rank constraints to guide perturbations toward principal subspaces; and ii) relaxing nonnegativity constraints on perturbations to inject negative components that effectively alter original feature additivity. We present analyses including ablation studies, convergence performance, and computational complexity. Extensive experiments on benchmark datasets show that the proposed method effectively attacks both vanilla NMF and existing adversarial NMF variants by disrupting the factorization and degrading performance in downstream tasks such as feature extraction and clustering.

Wearable single-lead electrocardiogram (ECG) devices exhibit significant advantage for capturing subtle variations in cardiac activity, offering new potential for the continuous assessment and management of chronic pain. An essential task of ECG-based monitoring is the accurate recognition of pain intensity. However, developing an online pain intensity recognition method presents several critical challenges, including high computational complexity, limited robustness to noise, etc. To address these challenges, this article proposes an end-to-end neural network by integrating multiple temporal feature compression and fusion strategies. The proposed algorithm comprises three primary sequential stuctures: 1) feature compression module (FCM); 2) pain-related feature extraction module (PFEM); and 3) hidden feature fusion complementary module (HFFCM). First, FCM utilizes a Resnet compression to exploit the latent information embedded in the autocorrelation of ECG time series. Subsequently, PFEM extracts the hidden pain features through self-attention. Finally, HFFCM dynamically integrates and complements these features through a cross-attention mechanism built upon large-kernel convolutions. Evaluated on the public biovid dataset, the proposed algorithm outperforms state-of-the-art methods, achieving accuracy of 72.41%, in pain tolerance stimulus or no pain state classification. In addition, the proposed algorithm simplifies the attention mechanism through large-kernel convolutional modulation, reducing the model’s computational complexity to only 0.43 GFLOPs, which is 65.6% less than the existing transformer-based approaches. Overall, this article proposes an efficient online method for pain intensity recognition, offering a reliable solution that enhances chronic pain monitoring in the field of Internet of Things (IoT).

Wearable electroencephalogram (EEG) devices have shown great potential in enabling real-time monitoring of subtle changes in brain activity, providing new possibilities for the assessment and management of chronic pain. However, recognizing pain-related biomarkers from EEG data remains a complex, multitask challenge. Most existing research focuses on single-task approaches and rarely addresses this issue within a unified framework. In this article, we propose a novel deep neural network (DNN) model called multiscale frequency domain MetaFormer (MFDFormer), which is designed to simultaneously predict the presence, type, and intensity of chronic pain. The proposed MFDFormer comprises two primary subnetworks: 1) multiscale feature extractor (MFE) and 2) frequency domain MetaFormer (FDFormer) encoder. The MFE extracts diverse EEG features through convolutions with different kernel sizes, while a self-attention mechanism is integrated into MFE to emphasize the importance of interdependency among these features. The FDFormer encoder refines the output MFE features using causal convolutions to capture local patterns and projects them into a higher dimensional representation domain. Additionally, it incorporates spatial and temporal frequency domain learners (TFDLs) in parallel to effectively capture the spatial-temporal information of EEG data. Based on the publicly available brain function in chronic pain (BFCP) dataset, the proposed MFDFormer demonstrates superior performance over state-of-the-art algorithms, achieving accuracies of 97.59%, 96.02%, and 83.48% in pain or nonpain state classification (P/NSC), pain type classification (PTC), and pain intensity classification (PIC) tasks, respectively. This article proposes a unified, end-to-end DNN-based framework for multitask chronic pain recognition, providing a reliable solution with the potential to advance pain diagnosis and management in IoT and smart wearable applications.

The growing adoption of electric vehicles (EVs) and expansion of Internet of Things (IoT) in-vehicle applications enhance vehicle intelligence and connectivity but also drive higher demand for both charging and computing services. Charging and computing stations (CCSs), integrating bidirectional chargers and edge computing servers and allowing optimal joint energy-computation management, has been taken as an effective solution to address this demand. This article introduces a new concept called charging and computing service vehicle (CCSV) fleets, which are equipped with high-capacity batteries and edge servers, serving as mobile resources to support the stationary CCSs at different locations in a wide area. We propose a two-timescale model integrating temporal-spatial scheduling, charging/discharging management, and computation task offloading of the CCSV fleets. Our goal is to minimize the total system cost by optimizing the energy-computation coordination between the mobile CCSV fleets and the stationary CCSs. We construct an extended time-space network (TSN) with congestion nodes, providing a clearer depiction of the time-varying congestion conditions in the traffic network. For practical implementation, we develop a heuristic based on the convex-concave procedure (CCP) and penalty alternating direction method (PADM) to solve the problem quickly. Simulation results in a traffic network based on Guangzhou city demonstrate that the proposed model effectively leverages the mobility and multidimensional resources of the CCSV fleets to reduce the system cost significantly.

As a representative technical approach in Global Navigation Satellite System (GNSS) high-precision positioning, Precise Point Positioning (PPP), using a single receiver, can obtain absolute positioning accuracy ranging from decimeter-level to centimeter-level. An accurate stochastic model of observations is crucial for enhancing the PPP positioning quality. Currently, the stochastic model of observation is mainly established through empirical formulas. However, in urban environments, due to the influence of Non-Line-of-Sight (NLOS) errors, empirical formulas cannot reliably characterize the actual error magnitudes of observations, thereby degrading the PPP positioning accuracy. To address this issue, this study develops a resilient stochastic model scheme based on the intelligent identification results of NLOS, aiming to enhance PPP positioning accuracy in complex scenarios. Firstly, a stochastic model based on intelligent recognition result of NLOS signals is developed. This model utilizes the recognition results to calculate the Position Dilution of Precision (PDOP) accurately, and dynamically adjusts the observation weights of LOS and NLOS signals according to the quantity ratio of LOS and NLOS signals and the corresponding satellite geometry. Secondly, a graph neural network (GNN)-based model for NLOS signal recognition is introduced. The model leverages a GNN to extract environmental features from sky satellite images, enabling accurate identification of NLOS signals across different scenarios. Next, by integrating the designed stochastic model method and the intelligent NLOS identification model, an Enhanced Precise Point Positioning (EPPP) algorithm is proposed to improve positioning accuracy in urban environments. Finally, four real-world datasets from the urban forest scenarios and two datasets from the overpass scenarios were selected to verify the effectiveness of the proposed method. The experimental results show that the proposed EPPP model outperforms empirical stochastic models, and the PPP static positioning accuracy is improved by 38.8%-78.44%, 45.31%-69.19%, 20.52%-71.0%, 31.77%-75.7% in the east, north, up and three-dimensional directions, respectively, and the PPP dynamic positioning accuracy is improved by 19.67%-58.02%, 14.43%-57.35%, 6.56%-34.80%, 10.96%-44.87% in the east, north, up and three-dimensional directions, respectively.

Connected and automated vehicles (CAVs) have emerged as an efficient solution to improve the driving experience in the intelligent transportation systems (ITSs), in which the targeted vehicle (TV) can switch between the human-driven (HD) and autonomous-driven (AD) modes to act as server or terminal in vehicular edge computing networks (VECNs). However, due to the dynamic nature of traffic networks and the moving of vehicles, distribution of computational resources is imbalanced and variable, it is a challenge to design the cooperative resource management scheme for the whole journey of vehicle users. In this article, we propose a joint driving model selection and resource management scheme for TV in each road segment, to maximize the vehicle users’ satisfaction of the whole journey. For the complex formulated joint optimization problem, we design a three-stage hierarchical optimization (3SHO) framework, using deep Q-network (DQN) for driving mode optimization in the first stage and deep deterministic policy gradient (DDPG) for optimizing resource management under different selected driving modes. And a terminal-server matching mechanism is introduced to enable dynamic service quality improvement for TV. Specially, we design a new user satisfaction function with the quality of service, traffic revenue, and the gap between expected and actual revenues of users are considered. Experimental results showcase the robust convergence of the 3SHO algorithm, the adeptness to dynamic traffic networks, and the capacity to enhance user satisfaction significantly.

The reception of nonline-of-sight (NLOS) signals in urban areas, such as urban canyons and overpasses, can cause severe errors in global navigation satellite system (GNSS) positioning. Machine learning-based NLOS mitigation methods have become increasingly popular. However, existing methods cannot obtain satisfactory NLOS recognition accuracy across multiple locations or scenarios. Furthermore, in scenarios with severe occlusion, directly removing recognized NLOS signals may reduce the number of available satellites for positioning algorithms, resulting in lower positioning precision. To address these issues, this study proposes a deep learning-based NLOS interference mitigation method to improve the precision of GNSS single-point positioning (SPP). First, to improve NLOS signal recognition across multiple locations, we propose the dual self-attention mechanism (DSN) model for NLOS recognition, which utilizes self-attention networks to construct both spatial and temporal channels for modeling spatial environmental characteristics and signal temporal features, respectively. Second, to mitigate the interference from NLOS signals, we design a novel weighting scheme using NLOS recognition results to revise the elevation angle-based scheme. Next, we propose the SPP-DSN algorithm by combining the DSN model and the designed weighting scheme to improve positioning precision in urban areas. Finally, we collected real-world data to conduct experiments to investigate the performance of our proposed method. The experimental results show that our proposed DSN model can effectively improve NLOS recognition accuracy across multiple locations. Compared to the regular SPP algorithm, our proposed SPP-DSN method can enhance positioning precision by over 29% in urban canyons and more than 10% under overpasses.

Group vehicle trajectory prediction (GVTP) is important for analyzing the traffic states and optimizing the traffic management. However, existing studies have performance bottlenecks in the prediction accuracy and inference latency. To tackle the problems, we propose a linear UNet-enhanced fully connected spatial–temporal GNN (LUFC-STGNN) for GVTP. First, a spatial graph is constructed by integrating prior-based and data-driven methods to capture both explicit and implicit spatial interactions between the vehicles. After that, a comprehensive temporal graph is created to capture the varying strengths of temporal interactions between all vehicles throughout historical timestamps. Furthermore, a fully connected spatial–temporal graph combining the spatial and temporal graphs is introduced to extract the effective spatial–temporal interaction features of the vehicles through the graph convolution operation. Finally, a linear UNet-based temporal dependency encoder (LU-TDE) is designed to further enhance the model’s ability of capturing the potential temporal patterns in the vehicle interactions. The encoder with linear complexity explores the multiscale temporal dependencies from the spatial–temporal interaction features but also reducing the inference latency. Experiments results based on real-world datasets show that compared to state-of-the-art models, our model reduces the average root mean square error over the 5-s prediction horizon by 31% and 10% on the NGSIM and HighD datasets, while reducing the inference latency by at least 1.26 times.

Hashing is essential for approximate nearest neighbor search by mapping high-dimensional data to compact binary codes. The balance between similarity preservation and code diversity is a key challenge. Existing projection-based methods often struggle with fitting binary codes to continuous space due to space heterogeneity. To address this, we propose a novel Cluster Guided Truncated Hashing (CGTH) method that uses latent cluster information to guide the binary learning process. By leveraging data clusters as anchor points and applying a truncated coding strategy, our method effectively maintains local similarity and code diversity. Experiments on benchmark datasets demonstrate that CGTH outperforms existing methods, achieving superior search performance.

Trajectory planning with a learning-based approach has emerged as a crucial element in autonomous unmanned systems and has attracted substantial interest from both academia and industry. However, unresolved issues persist concerning data efficiency, safety, convergence, and generalization within the control pipeline. To address this gap, this work presents a trajectory planning method that combines the differential flatness of wheeled vehicle with global convergence property. Our proposed framework transforms the trajectory planning problem, integrating kinematic constraints into a motion planning paradigm. This transformation significantly reduces the state space associated with trajectory planning. Initially, Gaussian mixture regression (GMR) is employed to learn the nonlinear mapping from flat input, leveraging a limited number of demonstrations solved by the optimal control method. Subsequently, we design an asymmetric quadratic Lyapunov function that incorporates both random barrier information and the potential convergence property of the demonstration trajectories. Based on the optimized parameterized Lyapunov function incorporating the convergence and safety criteria, the analytical supplementary control is subsequently obtained by solving a quadratic programming problem to compensate for the prediction errors of GMR, which make the framework complete. Both numerical and real-world experiments are performed to validate the effectiveness of our framework.Note to Practitioners—This work is motivated by the concept of robot motion primitives. While direct segmented planning based on dynamical system movement is feasible for robots with multiple degrees of freedom, it cannot be directly applied to wheeled vehicles with non-holonomic constraints. In this paper, we propose a method that utilizes the differential flatness properties of wheeled vehicles to bridge the gap between these two application objects. By converting the trajectory planning problem of the mobile vehicles into an optimal control problem, we can obtain a satisfactory optimal trajectory. Solving the optimal control problem involves an iterative process due to its nature as an initial value problem. While some learning-based method offer end-to-end learning capabilities and can perform real-time optimal control, they requires a substantial number of training dataset (different optimal trajectories) and lack convergence validation. The foundation of this work is the imitation learning paradigm. Although learning-based approaches are also capable of directly learning from demonstrations, our approach realizes a combination of Lyapunov theory, which allows us to extract the planning task’s potential properties from a limited number of demonstrations, and the vehicle’s differential flat properties to construct a framework with analytical solution. The framework can effectively re-plan obstacle-free trajectories, even in scenarios with obstacles not given in learning phase. This effectively compensates for the shortcomings of learning-based methods in terms of data reliance, convergence, and interpretability.

In this paper, the model-free dynamic event-driven safe (MFDEDS) control of unknown nonaffine systems with state and input constraints is investigated via adaptive dynamic programming. To begin with, by introducing a dynamic compensator and performing system transformation, the safe control problem with state and input constraints is transformed into an optimal regulation problem of an unconstrained system. Afterwards, an integral reinforcement learning algorithm is applied to the unconstrained system to derive an optimal safe control policy independent of the original system model, which achieves model-free approximate optimal control for the original system. To conserve computing and communication resources, a novel game-based dynamic event-driven mechanism is established, which models the control policy and the event-driven error as players in a zero-sum game, with the aim of obtaining the worst event-driven error to maximize the triggering interval. Furthermore, an approximate solution to the Hamilton-Jacobi-Bellman equation is derived by constructing a single-critic learning structure, which results in an approximate optimal safe control policy. Theoretical analysis demonstrates that the proposed MFDEDS control scheme ensures the closed-loop system is asymptotically stable. Ultimately, the efficacy of the developed approach is corroborated through two simulation examples.

Due to the characteristics of low storage requirement and high retrieval efficiency, hashing-based retrieval has shown its great potential and has been widely applied for information retrieval. However, retrieval tasks in real-world applications are usually required to handle the data from various domains, leading to the unsatisfactory performances of existing hashing-based methods, as most of them assuming that the retrieval pool and the querying set are similar. Most of the existing works overlooked the self-representation that containing the modality-specific semantic information, in the cross-modal data. To cope with the challenges mentioned above, this paper proposes an asymmetric and discrete self-representation enhancement hashing (ADSEH) for cross-domain retrieval. Specifically, ADSEH aligns the mathematical distribution with domain adaptation for cross-domain data, by exploiting the correlation of minimizing the distribution mismatch to reduce the heterogeneous semantic gaps. Then, ADSEH learns the self-representation which is embedded into the generated hash codes, for enhancing the semantic relevance, improving the quality of hash codes, and boosting the generalization ability of ADSEH. Finally, the heterogeneous semantic gaps are further reduced by the log-likelihood similarity preserving for the cross-domain data. Experimental results demonstrate that ADSEH can outperform some SOTA baseline methods on four widely used datasets.

Point cloud completion concerns the inference of the completed geometries for real-scanned point clouds that are sparse and incomplete due to occlusion, noise, and viewpoint. Previous methods usually learn a one-shot partial-to-complete mapping, which is incapable of generating fine structure details for the complex point cloud distributions. In this paper, a Hierarchical Geometry Generation point completion Network (HGG-Net) is proposed to hierarchically generate the fine-grained completed point cloud with a skeleton-to-details strategy, which consists of three fundamental modules, namely Transformer-enhanced Feature Encoder (TFE), Multi-level Geometry Representation Decoder (MGRD), and Hierarchical Dynamic Geometry Generator (HDG). Specifically, TFE first extracts geometry features of the incomplete input and obtains a coarse prediction via self-attention mechanism and edge convolution. Second, MGRD obtains the multi-level decoded geometry representations by Geometric Interactive Transformer (GIT) and Channel-Attention-based Geometry Features Fusion (CAGF), where GIT is proposed to decode the complete prompt by capturing the semantic relationship between geometry features of the incomplete and the decoded complete objects, and CAGF aims to fuse them for the high-quality representation. Third, HDG generates the complete points hierarchically from skeleton to details based on the Dynamic Graph Attention mechanism. Qualitative and quantitative experiments demonstrate that the proposed HGG-Net outperforms state-of-the-art methods on several point cloud completion datasets. Our code is available at https://github.com/haalexx/HGGNet.

In this paper, the event-triggered robust hierarchical synchronization (ETRHS) control of unmanned surface vehicles (USVs) is investigated via reinforcement learning. In the ETRHS control problem, there exists one dominant USV and many following USVs. The dominant USV chooses a motion control policy based on the responses of all following USVs, and then each following USV takes corresponding optimal responses to the dominant USV’s policy. This paper converts the ETRHS control problem to an event-triggered optimal synchronization control problem by designing novel value functions for the dominant and following USVs. Subsequently, critic-only structures are established and the ETRHS control laws of all USVs are obtained to form the Stackelberg equilibrium. In order to reduce the computing and communication burden, a novel event-triggering condition is designed for each USV, and the corresponding control law is updated when the condition is triggered. Theoretical analysis demonstrates that the developed reinforcement learning-based ETRHS controllers guarantee all following USVs synchronize with the dominant USV even when dynamic uncertainties exist. Finally, simulation results verify the effectiveness of the developed reinforcement learning-based ETRHS control scheme.

Vehicle-road collaboration is an effective means of improving perception capacities and enhancing safety of intelligent connected vehicles (ICVs). A larger volume of perception data increases the accuracy and robustness of environmental understanding, but it also introduces heavier computation loads. Aiming to reduce data size while meeting perception requirements, this paper studies joint data preprocessing and offloading in vehicle-road collaboration. In the preprocessing stage, we assign different priorities to the detected objects based on their types and distances from the perceiving vehicles. We allow discarding some low-priority objects that may not need immediate attention to reduce computation loads in subsequent data processing. After object selection and downsampling on video frames, the downsized perception data is offloaded and processed collectively by ICVs and roadside units (RSUs). A nonconvex mixed-integer problem is formulated, maximizing the sum of priorities of the selected objects while satisfying constraints of time delay, bandwidth, and computing resources. A fast heuristic based on the penalty alternating direction method (PADM) and modified annealed feasibility pump (MAFP) is developed to solve the problem. Results show that the proposed method is more computationally efficient than the commercial solver in solving the priority maximization problem. Also, it can significantly reduce perception data size, enabling efficient use of the limited communication and computing resources to timely complete more high-priority tasks.

Cross-modal retrieval is a promising technique nowadays to find semantically similar instances in other modalities while a query instance is given from one modality. However, there still exists many challenges for reducing heterogeneous modality gap by embedding label information to discrete hash codes effectively, solving the binary optimization when generating unified hash codes and reducing the discrepancy of data distribution efficiently during common space learning. In order to overcome the above-mentioned challenges, we propose a Collaboratively Semantic alignment and Metric learning for cross-modal Hashing (CSMH) in this paper. Specifically, by a kernelization operation, CSMH first extracts the non-linear data features for each modality, which are projected into a latent subspace to align both marginal and conditional distributions simultaneously. Then, a maximum mean discrepancy-based metric strategy is customized to mitigate the distribution discrepancies among features from different modalities. Finally, semantic information obtained from the label similarity matrix, is further incorporated to embed the latent semantic structure into the discriminant subspace. Experimental results of CSMH and baseline methods on four widely-used datasets show that CSMH outperforms some state-of-the-art hashing baseline methods for cross-modal retrieval on efficiency and precision.

Embodied Artificial Intelligence (AI) bridges the cyberspace and the physical space, driving advancements in autonomous systems like theVehicularEmbodiedAINETwork (VEANET). VEANET integrates advanced AI capabilities into vehicular systems to enhance autonomous operations and decision-making. Embodied agents, such as Autonomous Vehicles (AVs), are autonomous entities that can perceive their environment and take actions to achieve specific goals, actively interacting with the physical world. Embodied Agent Twins (EATs) are digital models of these embodied agents, with various Embodied Agent AI Twins (EAATs) for intelligent applications in cyberspace. In VEANETs, EAATs act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving using generative AI models. Due to limited onboard computational resources, AVs offload EAATs to nearby RoadSide Units (RSUs). However, the mobility of AVs and limited RSU coverage necessitates dynamic migrations of EAATs, posing challenges in selecting suitable RSUs under information asymmetry. To address this, we construct a multi-dimensional contract theoretical model between AVs and alternative RSUs. Considering that AVs may exhibit irrational behavior, we utilize prospect theory instead of expected utility theory to model the actual utilities of AVs. Finally, we employ a Generative Diffusion Model (GDM)-based algorithm to identify the optimal contract designs, thus enhancing the efficiency of EAAT migrations. Numerical results demonstrate the superior efficiency of the proposed GDM-based scheme in facilitating EAAT migrations compared with traditional deep reinforcement learning methods.

Deep learning-based AI models typically require a large amount of high-quality annotated data to achieve optimal performance. However, thelabel distribution shiftcaused by noisy annotations can lead to perturbations in the classification boundary, reducing the robustness and generalization capabilities of deep learning models. To mitigate this issue, we transform the problem of learning from noisy labels into a semi-supervised learning problem, and propose a novel Semi-Supervised Distribution Alignment (SSDA) framework that strategically integrates noise-robust distribution alignment within a unified semi-supervised learning paradigm for combating noisy labels. By leveraging the similarity distribution between historical predictions, the proposed SSDA approach benefits from a flexible multi-historical regression modeling strategy, which aims to identify high-confidence samples/pairs and recalibrate the label shift through pseudo-labels. Furthermore, our approach employs a comprehensive multi-granularity distribution adaptation strategy, incorporating both instance-wise and class-aware distribution alignment to quantitatively minimize semantic discrepancies across different mixed feature domains. In this way, our SSDA approach ultimately achieves more resilient and generalizable performance against label noise, even in the presence of substantial noise. Extensive experiments conducted on multiple simulated and real-world noisy benchmark datasets consistently demonstrate the superiority and effectiveness of our SSDA method compared to existing state-of-the-art baselines.

In the past decades, supervised cross-modal hashing methods have attracted considerable attentions due to their high searching efficiency on large-scale multimedia databases. Many of these methods leverage semantic correlations among heterogeneous modalities by constructing a similarity matrix or building a common semantic space with the collective matrix factorization method. However, the similarity matrix may sacrifice the scalability and cannot preserve more semantic information into hash codes in the existing methods. Meanwhile, the matrix factorization methods cannot embed the main modality-specific information into hash codes. To address these issues, we propose a novel supervised cross-modal hashing method called random online hashing (ROH) in this article. ROH proposes a linear bridging strategy to simplify the pair-wise similarities factorization problem into a linear optimization one. Specifically, a bridging matrix is introduced to establish a bidirectional linear relation between hash codes and labels, which preserves more semantic similarities into hash codes and significantly reduces the semantic distances between hash codes of samples with similar labels. Additionally, a novel maximum eigenvalue direction (MED) embedding method is proposed to identify the direction of maximum eigenvalue for the original features and preserve critical information into modality-specific hash codes. Eventually, to handle real-time data dynamically, an online structure is adopted to solve the problem of dealing with new arrival data chunks without considering pairwise constraints. Extensive experimental results on three benchmark datasets demonstrate that the proposed ROH outperforms several state-of-the-art cross-modal hashing methods.

3-D lane detection is a challenging task due to the diversity of lanes, occlusion, dazzle light, and so on. Traditional methods usually use highly specialized handcrafted features and carefully designed postprocessing to detect them. However, these methods are based on strong assumptions and single modal so that they are easily scalable and have poor performance. In this article, a multimodal fusion network (MFNet) is proposed through using multihead nonlocal attention and feature pyramid for 3-D lane detection. It includes three parts: multihead deformable transformation (MDT) module, multidirectional attention feature pyramid fusion (MA-FPF) module, and top-view lane prediction (TLP) ones. First, MDT is presented to learn and mine multimodal features from RGB images, depth maps, and point cloud data (PCD) for achieving optimal lane feature extraction. Then, MA-FPF is designed to fuse multiscale features for presenting the vanish of lane features as the network deepens. Finally, TLP is developed to estimate 3-D lanes and predict their position. Experimental results on the 3-D lane synthetic and ONCE-3DLanes datasets demonstrate that the performance of the proposed MFNet outperforms the state-of-the-art methods in both qualitative and quantitative analyses and visual comparisons.

The recently proposed tensor tubal rank has been witnessed to obtain extraordinary success in real-world tensor data completion. However, existing works usually fix the transform orientation along the third mode and may fail to turn multidimensional low-tubal-rank structure into account. To alleviate these bottlenecks, we introduce two unfolding induced tensor nuclear norms (TNNs) for the tensor completion (TC) problem, which naturally extends tensor tubal rank to high-order data. Specifically, we show how multidimensional low-tubal-rank structure can be captured by utilizing a novel balanced unfolding strategy, upon which two TNNs, namely, overlapped TNN (OTNN) and latent TNN (LTNN), are developed. We also show the immediate relationship between the tubal rank of unfolding tensor and the existing tensor network (TN) rank, e.g., CANDECOMP/PARAFAC (CP) rank, Tucker rank, and tensor ring (TR) rank, to demonstrate its efficiency and practicality. Two efficient TC models are then proposed with theoretical guarantees by analyzing a unified nonasymptotic upper bound. To solve optimization problems, we develop two alternating direction methods of multipliers (ADMM) based algorithms. The proposed models have been demonstrated to exhibit superior performance based on experimental findings involving synthetic and real-world tensors, including facial images, light field images, and video sequences.

This article presents a novel theoretical framework for the finite-time synchronization (FTS) of complex dynamic networks (CDNs) under stochastic disturbances. Few studies have explored the combination of pinning impulsive control and pinning finite-time feedback control, with most finite-time feedback controls being designed globally rather than locally. Our approach integrates both pinning impulsive and pinning finite-time feedback strategies to achieve FTS of CDNs. We introduce a new impulse-type stochastic finite-time stability theory to demonstrate FTS in the presence of disturbances. Additionally, we propose criteria to ensure FTS and provide an explicit expression for the settling time, which is shown to be shorter than those in previous works. A numerical simulation is presented to validate the proposed methodology.

Generative Artificial Intelligence (GAI) shows remarkable productivity and creativity in Mobile Edge Networks, such as the metaverse and the Industrial Internet of Things. Federated learning is a promising technique for effectively training GAI models in mobile edge networks due to its data distribution. However, there is a notable issue with communication consumption when training large GAI models like generative diffusion models in mobile edge networks. Additionally, the substantial energy consumption associated with training diffusion-based models, along with the limited resources of edge devices and complexities of network environments, pose challenges for improving the training efficiency of GAI models. To address this challenge, we propose an on-demand quantized energy-efficient federated diffusion approach for mobile edge networks. Specifically, we first design a dynamic quantized federated diffusion training scheme considering various demands from the edge devices. Then, we study an energy efficiency problem based on specific quantization requirements. Numerical results show that our proposed method significantly reduces system energy consumption and transmitted model size compared to both baseline federated diffusion and fixed quantized federated diffusion methods while effectively maintaining reasonable quality and diversity of generated data.

Avatars, as promising digital assistants in Vehicular Metaverses, can enable drivers and passengers to immerse in 3-D virtual spaces, serving as a practical emerging example of Artificial Intelligence of Things (AIoT) in intelligent vehicular environments. The immersive experience is achieved through seamless human–avatar interaction, e.g., augmented reality navigation, which requires intensive resources that are inefficient and impractical to process on intelligent vehicles locally. Fortunately, offloading avatar tasks to roadside units (RSUs) or cloud servers for remote execution can effectively reduce resource consumption. However, the high mobility of vehicles, the dynamic workload of RSUs, and the heterogeneity of RSUs pose novel challenges to making avatar migration decisions. To address these challenges, in this article, we propose a dynamic migration framework for avatar tasks based on real-time trajectory prediction and multiagent deep reinforcement learning (MADRL). Specifically, we propose a model to predict the future trajectories of intelligent vehicles based on their historical data, indicating the future workloads of RSUs. Based on the expected workloads of RSUs, we formulate the avatar task migration problem as a long-term mixed-integer programming problem. To tackle this problem efficiently, the problem is transformed into a partially observable Markov decision process (POMDP) and solved by multiple DRL agents with hybrid continuous and discrete actions in decentralized. Numerical results demonstrate that our proposed algorithm can effectively reduce the latency of executing avatar tasks by around 25% without prediction and 30% with prediction and enhance user immersive experiences in the AIoT-enabled Vehicular Metaverse (AeVeM).

The development of industry 4.0 relies on emerging technologies of digital twin, machine learning, blockchain and Internet of Things (IoT) to build autonomous self-configuring systems that maximize manufactory efficiency, precision and accuracy. In this paper, we propose a new distributed and secure digital twin driven IIoT framework that integrates federated learning and Directed Acyclic Graph (DAG) blockchain with sharding. The proposed framework includes three planes: the data plane, the blockchain plane and the digital twin plane. Specifically, the data plane performs federated learning through a set of cluster heads to train models at network edges for twin model construction. The blockchain plane, which supports sharding, utilizes a hierarchical consensus scheme based on DAG blockchain to verify both local model updates and global model updates. The digital twin plane is responsible for constructing and maintaining twin model. Then, an efficient resource scheduling scheme is designed by considering performance of both federated learning and DAG blockchain with sharding. Accordingly, an optimization problem is formulated to maximize long-term utility of the digital twin driven IIoT. To cope with mapping error in the digital twin plane, a multi-agent Proximal Policy Optimization (MAPPO) approach is developed to solve the optimization problem. Numerical results illustrate that comparing with traditional approach, the proposed MAPPO improves utility by about 37 %, and reduces time latency by about 14%. Moreover, it also can well adapt to the mapping error.

Driven by the great advances in metaverse and edge computing technologies, vehicular edge metaverses are expected to disrupt the current paradigm of intelligent transportation systems. As highly computerized avatars of Vehicular Metaverse Users (VMUs), the Vehicle Twins (VTs) deployed in edge servers can provide valuable metaverse services to improve driving safety and on-board satisfaction for their VMUs throughout journeys. To maintain uninterrupted metaverse experiences, VTs must be migrated among edge servers following the movements of vehicles. This can raise concerns about privacy breaches during the dynamic communications among vehicular edge metaverses. To address these concerns and safeguard location privacy, pseudonyms as temporary identifiers can be leveraged by both VMUs and VTs to realize anonymous communications in the physical space and virtual spaces. However, existing pseudonym management methods fall short in meeting the extensive pseudonym demands in vehicular edge metaverses, thus dramatically diminishing the performance of privacy preservation. To this end, we present a cross-metaverse empowered dual pseudonym management framework. We utilize cross-chain technology to enhance management efficiency and data security for pseudonyms. Furthermore, we propose a metric to assess the privacy level and employ a Multi-Agent Deep Reinforcement Learning (MADRL) approach to obtain an optimal pseudonym generating strategy. Numerical results demonstrate that our proposed schemes are high-efficiency and cost-effective, showcasing their promising applications in vehicular edge metaverses.

The synergy between Unmanned Aerial Vehicles (UAVs) and metaverses is giving rise to an emerging paradigm named UAV metaverses, which create a unified ecosystem that blends physical and virtual spaces, transforming drone interaction and virtual exploration. UAV Twins (UTs), as the digital twins of UAVs that revolutionize UAV applications by making them more immersive, realistic, and informative, are deployed and updated on ground base stations, e.g., RoadSide Units (RSUs), to offer metaverse services for UAV Metaverse Users (UMUs). Due to the dynamic mobility of UAVs and limited communication coverages of RSUs, it is essential to perform real-time UT migration to ensure seamless immersive experiences for UMUs. However, selecting appropriate RSUs and optimizing the required bandwidth is challenging for achieving reliable and efficient UT migration. To address the challenges, we propose a tiny machine learning-based Stackelberg game framework based on pruning techniques for efficient UT migration in UAV metaverses. Specifically, we formulate a multi-leader multifollower Stackelberg model considering a new immersion metric of UMUs in the utilities of UAVs. Then, we design a Tiny Multi-Agent Deep Reinforcement Learning (Tiny MADRL) algorithm to obtain the tiny networks representing the optimal game solution. Specifically, the actor-critic network leverages the pruning techniques to reduce the number of network parameters and achieve model size and computation reduction, allowing for efficient implementation of Tiny MADRL. Numerical results demonstrate that our proposed schemes have better performance than traditional schemes.

Long-term and mobile healthcare applications have increased the use of single-channel electroencephalogram (EEG) systems. However, electromyography (EMG) artifacts often disturb EEGs. The lack of spatial correlation, diversity of waveforms, and time-varying overlap make eliminating EMG interference from a single-channel EEG difficult. To overcome these challenges, we create DSATCN, a dual-stream learning model that makes use of multi-level and multi-scale temporal dependencies in different frequency bands to perform robust EEG reconstruction. The first DSATCN stream extracts low-frequency band EEG features with reduced EMG interference. The second stream selectively combines the high-level features of the first stream with its own low-level features to refine the EEG reconstruction across the entire frequency band, lowering the risk of overfitting. Both streams employ a novel attention-based temporal convolution network (ATCN) to adaptively separate the overlapping features of EEGs and EMGs. The ATCN has multiple stages to represent various temporal dependencies at different levels. Each stage consists of multi-scale dilated convolutions and fast Fourier transform modulations, which efficiently enrich the receptive fields and establish global self-attention mechanisms. The stages’ outputs are merged by relaxed attentional feature fusion modules, which bridge semantic gaps between features at various levels. Extensive experimental results on three semi-simulated datasets containing 318,700 samples show that the proposed model significantly outperforms the existing methods in EEG reconstruction accuracy. And its computational cost meets the criteria for real-time processing. Our code is available at https://github.com/BaenRH/DSATCN.

With the advancement in battery technology and the rise of on-board computing capabilities, electric vehicles (EVs) can serve as both energy prosumers and computing nodes. The mobility of EVs allows them to perform wide-area multi-resource exchange in both electricity networks and edge computing networks. We call such a paradigm an Electric Vehicle Charging and Computing Network (EVCCN). It is considered that the EVCCN is composed of multiple charging and computing stations (CCSs) in different locations. Each CCS integrates EV chargers and an edge server, offering the interfaces for EVs to bidirectionally trade both energy and computing resources. We propose a customized model jointly optimizing the path selection, charging/discharging, and task offloading in different CCSs to minimize an EV’s travel cost (i.e., the money spent on the EV’s trip). In the proposed model, the EV consumes energy and generates data on its way to the destination, subject to travel time, energy, and data constraints. The cost minimization problem is formulated as a nonconvex mixed-integer problem from a user-centric perspective. To solve it fast in practice, we construct a new action-expanded network to simply the model and develop a heuristic based on piecewise McCormick to quickly obtain a near-optimal solution. Simulation results show that our heuristic is computationally efficient for large traffic networks compared with global solvers. We also present results in a traffic network based on Guangzhou city, which shows that our model can save 33.99% in the travel cost compared with a baseline model.

In dynamic and complex environments, the positioning accuracy of global navigation satellite system (GNSS) will be seriously reduced. Deep reinforcement learning (DRL) has been found to give effective dynamic policy learning for complex GNSS positioning correction tasks. However, catastrophic interference in DRL models caused by the high correlation between successive positioning states, together with instability in gradient backpropagation in deep neural networks (DNNs), produces inaccurate DRL value approximation thereby degrades GNSS positioning performance. In this article, we develop a dictionary learning-based reinforcement learning (RL) algorithm with the nonconvex log regularizer for GNSS positioning correction. To avoid DNN instability problems, a dictionary learning-structured RL model is proposed. It has a feed-forward learning architecture obviating the need for gradient backpropagation. The nonconvex log regularizer for dictionary learning reduces the correlation between states and thereby alleviates interference in RL. This provides sparse representations, which can more effectively capture features and produce representations with lower biases than convex regularizers. Furthermore, the nonconvex optimization is made efficient through a decomposition scheme that generates an explicit closed-form solution using the proximal operator. Finally, based on the proposed dictionary learning-structured RL model, a novel positioning correction method is developed to enhance GNSS positioning accuracy. The experimental results indicate that the proposed method outperforms state-of-the-art sparse coding-based RL methods in benchmark environments. Moreover, the proposed method effectively improves GNSS positioning accuracy relative to the glsms Kalman filter acrlong KF method and the glsms weighted least squares acrlong WLS method.

Global navigation satellite systems (GNSSs) provide efficient positioning services for location-aware Internet of Things (IoT) devices. However, GNSS non-line-of-sight (NLOS) signals can result in severe positioning errors in urban canyon areas. Existing deep-learning-based NLOS signal classification methods cannot appropriately model the spatiotemporal information of NLOS interference, resulting in limited accuracy across multiple locations. This study presents a spatiotemporal information-driven model that can capture environmental characteristics and signal temporal information simultaneously to improve NLOS classification accuracy across multiple locations. First, a visualization analysis of the signal distribution across multiple locations demonstrates the impact of environmental characteristics. In addition, the significance of both the spatial environmental features and the signal temporal features for NLOS classification is clarified by constructing a tree diagram of the data set. Second, we propose an airspace attention mechanism module and a long short-term memory (LSTM)-based temporal feature extraction module to model both types of features, respectively. Third, the learnable sparse regularizer is utilized to reduce feature redundancy and thereby realize a sparse representation, which improves model generalization performance. Finally, the spatiotemporal information-driven cross-attention model is developed to perform NLOS classification, which uses a cross-attention fusion strategy to integrate the two modules. We use real-world data sets collected across multiple urban canyon locations to test our model. Experiments show that the proposed model can achieve 98% classification accuracy across multiple locations. Generalization performance in unknown environments can be improved over 7% compared to several state-of-the-art models.

Accurate object detection in remote sensing images (RSIs) is of great significance for various applications such as environmental monitoring and agricultural production. However, it is a challenging task mainly due to the complex backgrounds and scale diversity of geospatial objects. In this letter, a Cross-Scale Hybrid Gaussian Attention Network (CSHGANet) is proposed for accurate object detection in RSIs, and it consists of two main components as follows. First, hybrid Gaussian attention is designed to learn the interrelationships between channels and spatial locations of features, which can focus on geospatial objects and reduce the interference of complex backgrounds in RSIs. Then, a cross-scale feature aggregation module is developed to adaptively fuse multi-scale attention feature maps to capture more rich and discriminative feature representations, so as to better handle scale variations of remote sensing objects. Extensive experiments on two public datasets (i.e., NWPU VHR-10 and RSOD) show that the proposed CSHGANet outperforms state-of-the-art object detection methods, achieving mean average precision (mAP) scores of 95.53% and 98.61%, respectively.

Existing studies have shown that the abnormal expression of microRNAs (miRNAs) usually leads to the occurrence and development of human diseases. Identifying disease-related miRNAs contributes to studying the pathogenesis of diseases at the molecular level. As traditional biological experiments are time-consuming and expensive, computational methods have been used as an effective complement to infer the potential associations between miRNAs and diseases. However, most of the existing computational methods still face three main challenges: (i) learning of high-order relations; (ii) insufficient representation learning ability; (iii) importance learning and integration of multi-view embedding representation. To this end, we developed a HyperGraph Contrastive Learning with view-aware Attention Mechanism and Integrated multi-view Representation (HGCLAMIR) model to discover potential miRNA-disease associations. First, hypergraph convolutional network (HGCN) was utilized to capture high-order complex relations from hypergraphs related to miRNAs and diseases. Then, we combined HGCN with contrastive learning to improve and enhance the embedded representation learning ability of HGCN. Moreover, we introduced view-aware attention mechanism to adaptively weight the embedded representations of different views, thereby obtaining the importance of multi-view latent representations. Next, we innovatively proposed integrated representation learning to integrate the embedded representation information of multiple views for obtaining more reasonable embedding information. Finally, the integrated representation information was fed into a neural network-based matrix completion method to perform miRNA-disease association prediction. Experimental results on the cross-validation set and independent test set indicated that HGCLAMIR can achieve better prediction performance than other baseline models. Furthermore, the results of case studies and enrichment analysis further demonstrated the accuracy of HGCLAMIR and unconfirmed potential associations had biological significance.

Graph-based semi-supervised learning (GSSL) is a quite important technology due to its effectiveness in practice. Existing GSSL works often treat the given labels equally and ignore the unbalance importance of labels. In some inaccurate systems, the collected labels usually contain noise (noisy labels) and the methods treating labels equally suffer from the label noise. In this article, we propose a novel label-weighted learning method on graph for semi-supervised classification under label noise, which allows considering the contribution differences of labels. In particular, the label dependency of data is revealed by graph constraints. With the help of this label dependency, the proposed method develops the strategy of adaptive label weight, where label weights are assigned to labels adaptively. Accordingly, an efficient algorithm is developed to solve the proposed optimization objective, where each subproblem has a closed-form solution. Experimental results on a synthetic dataset and several real-world datasets show the advantage of the proposed method, compared to the state-of-the-art methods.

In this paper, stabilization by aperiodically intermittent sampling stochastic noise is introduced as a new way of solving the consensus problem of a class of homogeneous multi-agent systems. A multiplicative noise is designed as a control input to stabilize the error system of the multi-agents. The average noise control rate (ANCR) is employed to estimate the working time of aperiodically intermittent noise, which reduces the conservativeness caused by the irregular noise working and rest time distribution. A novel piecewise analysis technique (PAT) is adopted to estimate the mean square of the error state, which allows for the larger noise sampling period. Meanwhile, the sufficient criteria to ensure almost sure stability of the error system are obtained, as well as the transcendental equation concerning the noise sampling period$\tau $and the ANCR$\Gamma $. Finally, the numerical simulation demonstrates the efficiency and accuracy of the proposed method.

The sparse collaborative tracking (SCT) method has been developed for object tracking recently, and it is very efficient and robust to various occlusions. In SCT, sparse representation (SR) plays an essential role because it needs to perform several manipulations of sparse matrix representation (SMR) or nonnegative SMR in each iteration. So one of the most challenging problems in SCT is how to efficiently solve the SMR. However, existing SR algorithms are solely developed for the vectors-based SR. They partition SMR into a set of vector-based SR problems and solve them in the level-2 BLAS (Basic Linear Algebra Subprograms) manner, i.e., matrix-vector operations, which is computationally much less efficient than the direct level-3 BLAS (direct matrix-matrix operations). To solve this problem, by extending the standard SR algorithm from the vector version to the matrix for SMR and nonnegative SMR, BLAS3-based Sparse Learning (BLAS3-SpaL) is first developed, and then the corresponding BLAS3-SpaL-based SCT method (FastSCT-BLAS3SpaL) is further developed for fast robust-object-tracking in this paper. The experiments verified that it achieves robust object tracking by reducing accumulation errors and speeds up tracking with more than double speed.

Recently, deep hashing-based cross-modal retrieval has attracted much attention of researchers, due to its advantages of fast retrieval efficiency and low storage overhead, etc. However, the existing deep hashing-based cross-modal retrieval methods typically 1) suffer from inadequately capturing the semantic relevance and coexistent information for cross-modal data, which may result in sub-optimal retrieval performance, 2) require a more comprehensive similarity measurement for cross-modal features to ensure high retrieval accuracy, 3) lack of scalability for lightweight deployment framework. To handle the issues mentioned above, we propose a CLIP-based knowledge distillation hashing (CKDH) for cross-modal retrieval, by referring the research trend of combining traditional methods and modern neural architecture to design lightweight networks based on large language models. Specifically, to effectively help capture the semantic relevance and coexistent information, CLIP is fine-tuned to extract visual features, while a graph attention network is used to enhance textual features extracted by bag-of-words model in the teacher model. Then, for better supervising the training of student model, a more comprehensive similarity measurement is introduced to represent distilled knowledge by jointly preserving the log-likelihood, intra and inter modality similarities. Finally, the student model extracts deep features by a lightweight networks, and generates the hash codes under the supervision of the similarity matrix produced by the teacher model. Experimental results on three widely used datasets demonstrate that CKDH can outperform some state-of-the-art methods, by delivering the best result consistently.

Accurate segmentation of 3D dental models derived from intra-oral scanners (IOS) is one of the key steps in many digital dental applications such as orthodontics and implants. However, it is difficult to accurately segment individual teeth and gums in 3D dental models due to the following problems: 1) the shape and appearance of adjacent teeth are very similar, which is easy to be misidentified; 2) the boundary between teeth and gums is often indistinct, especially in orthodontic patients with abnormalities such as missing and crowded teeth. To solve such problems, a Dual-Branch Geometric Attention Network (DBGANet) for 3D tooth segmentation is proposed, which can capture tooth geometric structure and detailed boundary information from multi-view geometric features encoded by 3D coordinates and normal vectors. The framework contains two branches, i.e., C-branch and N-branch. First, centroid-guided separable attention is designed in the C-branch to learn global context information by modeling the spatial dependencies of tooth point clouds, which can capture the overall geometric structure of teeth to better distinguish adjacent teeth with similar appearance. Then, Gaussian neighbor attention is designed in the N-branch to encode normal vectors to highlight detailed differences between geometric features at different points, which helps to refine the boundaries of teeth and gingiva for more accurate and smooth tooth segmentation. Extensive experiments on the real-patient datasets of 3D dental models demonstrate that the proposed DBGANet significantly outperforms state-of-the-art methods.

Despite various measures across different engineering and social systems, network robustness remains crucial for resisting random faults and malicious attacks. In this study, robustness refers to the ability of a network to maintain its functionality after a part of the network has failed. Existing methods assess network robustness using attack simulations, spectral measures, or deep neural networks (DNNs), which return a single metric as a result. Evaluating network robustness is technically challenging, while evaluating a single metric is practically insufficient. This article proposes a multitask analysis system based on the graph isomorphism network (GIN) model, abbreviated as GIN-MAS. First, a destruction-based robustness metric is formulated using the destruction threshold of the examined network. A multitask learning approach is taken to learn the network robustness metrics, including connectivity robustness, controllability robustness, destruction threshold, and the maximum number of connected components. Then, a five-layer GIN is constructed for evaluating the aforementioned four robustness metrics simultaneously. Finally, extensive experimental studies reveal that 1) GIN-MAS outperforms nine other methods, including three state-of-the-art convolutional neural network (CNN)-based robustness evaluators, with lower prediction errors for both known and unknown datasets from various directed and undirected, synthetic, and real-world networks; 2) the multitask learning scheme is not only capable of handling multiple tasks simultaneously but more importantly it enables the parameter and knowledge sharing across tasks, thus preventing overfitting and enhancing the performances; and 3) GIN-MAS performs multitasks significantly faster than other single-task evaluators. The excellent performance of GIN-MAS suggests that more powerful DNNs have great potentials for analyzing more complicated and comprehensive robustness evaluation tasks.

Policy iteration (PI), an iterative method in reinforcement learning, has the merit of interactions with a little-known environment to learn a decision law through policy evaluation and improvement. However, the existing PI-based results for output-feedback (OPFB) continuous-time systems relied heavily on an initial stabilizing full state-feedback (FSFB) policy. It thus raises the question of violating the OPFB principle. This article addresses such a question and establishes the PI under an initial stabilizing OPFB policy. We prove that an off-policy Bellman equation can transform any OPFB policy into an FSFB policy. Based on this transformation property, we revise the traditional PI by appending an additional iteration, which turns out to be efficient in approximating the optimal control under the initial OPFB policy. We show the effectiveness of the proposed learning methods through theoretical analysis and a case study.

The deep-learning-based detection of planetary craters provides significant assistance for in-orbit vehicles in space exploration. However, most object detection researches to date tended to focus on the single-source data collected by mono-type sensors, and their performances were severely hindered by the disability of using diverse source data from various sensors. For effectually using distinct sources in resource-limited vehicles, we present a compact framework to learn unified representation from elevation and visual sources basing on tensor decomposition. In particular, the vital elevation is extracted to obtain the deficient information in visuals. Furthermore, for accommodating limited computing resource, a compound tensor decomposition layer is proposed based on the special structure of decomposition, which extracts the source-specific and source-independent information, and at the same time crafts unified representation for terrains. Comprehensive comparisons with recent methods demonstrate the effective representation learning of the proposed method on different planetary terrains and in insufficient data learning setting, revealing its potential for real-world applications.

An unmanned aerial vehicle (UAV)-enabled intelligent transportation system utilizes a set of UAVs to collect and process surveillance data for transportation management. Subsequently, the processing results of the UAVs are transmitted to a control center that makes a centralized transportation management decision based on the fusion of all processing results. When performing the monitoring tasks, the UAVs can access to an edge server for offloading. To reduce the energy consumption and improve the fusion performance, the control center schedules the UAVs to perform the tasks in an energy-efficient manner while synchronizing the completion time of the UAVs. As a result, the control center studies a constrained multi-objective optimization problem (CMOP), in which two objectives, i.e., the total energy consumption of the UAVs and total completion time difference among the UAVs, are simultaneously considered. To tackle the CMOP, we develop an improved constrained multi-objective evolutionary algorithm. Particularly, we design an improved genetic operator and repairing constraint-handling technique to improve the overall performance of the proposed algorithm in seeking Pareto optimal solutions for the CMOP. Numerical results demonstrate that compared with the baseline algorithms, the proposed algorithm has great advantages in finding better solutions with the enhanced diversity and convergence for the CMOP.

Conventional hash-based retrieval method rely on the assumption that the query and database are of the identical domain. However, cross-domain problem often occurs in real-world applications, leading to the unsatisfactory performance of existing hashing methods. Recently, some researchers have put forward domain adaptation retrieval (DAR) under the perspective of domain adaptation (DA) and achieved promising results. But the following limitations still exist: 1) a single function is used to handle two challenges, i.e., domain adaptation and hashing, which is not flexible to explore enough underlying information for simultaneously accomplishing these challenges well; 2) non-dominant features in the sample are ignored; 3) the dissimilarity structure of dissimilar samples is not taken into account. To address the above problems, we propose a novel framework named two-step strategy (TSS) for domain adaptation retrieval, which advocates dividing DAR into two steps: DA step and hashing step. A DA function and a hash function are learned to handle the above two challenges, respectively, making the process more reasonable. Additionally, a discriminant semantic fusion loss is proposed to improve the discriminative ability among classes. Unlike other works that focus on discovering dominant features, we exploit the neglected non-dominant features and assign them attention with sinusoidal semantic embedding, actively creating a clear separation between classes. At last, we present an adaptive similarity preserving loss to preserve the similarity structure of the original data in all intra-domain and inter-domain hash codes. Extensive experiments on various datasets demonstrate that the proposed TSS achieves state-of-the-art performance.

Partial multi-label learning (PML) needs to address the problem of multi-label learning when the dataset contains redundant information. PML is more challenging compared to traditional multi-label learning, because PML needs not only to perform the multi classification task, but also to reduce the impact of noise information on the model. Existing PML methods suffer from the following problems. (1) Only single source of noise is considered. (2) Some methods ignore the label correlations. To solve the above problems, we proposes a new dual noise elimination and dynamic label correlation guided partial multi-label learning (PML-DNDC). Specifically, the hidden ground-truth label matrix is decomposed into two compressed matrices of instance and classifier, which are used to approximate the candidate label matrix, to eliminate the negative effects of label noise on the model. On one hand, the compressed instance matrix maintains local structural consistency with the original instances, eliminating noise in the feature. On the other hand, dynamic label correlation guidance is designed to help classifier training by dynamically exploring the potential label correlations, which encourages relevant labels to obtain similar classifiers. After extensive experiments and analyses, we conclude that the proposed PML-DNDC is superior to the state-of-the-art methods.

Learning a comprehensive representation from multiview data is crucial in many real-world applications. Multiview representation learning (MRL) based on nonnegative matrix factorization (NMF) has been widely adopted by projecting high-dimensional space into a lower order dimensional space with great interpretability. However, most prior NMF-based MRL techniques are shallow models that ignore hierarchical information. Although deep matrix factorization (DMF)-based methods have been proposed recently, most of them only focus on the consistency of multiple views and have cumbersome clustering steps. To address the above issues, in this article, we propose a novel model termed deep autoencoder-like NMF for MRL (DANMF-MRL), which obtains the representation matrix through the deep encoding stage and decodes it back to the original data. In this way, through a DANMF-based framework, we can simultaneously consider the multiview consistency and complementarity, allowing for a more comprehensive representation. We further propose a one-step DANMF-MRL, which learns the latent representation and final clustering labels matrix in a unified framework. In this approach, the two steps can negotiate with each other to fully exploit the latent clustering structure, avoid previous tedious clustering steps, and achieve optimal clustering performance. Furthermore, two efficient iterative optimization algorithms are developed to solve the proposed models both with theoretical convergence analysis. Extensive experiments on five benchmark datasets demonstrate the superiority of our approaches against other state-of-the-art MRL methods.

Surface defect detection plays an essential role in industry, and it is challenging due to the following problems: 1) the similarity between defect and nondefect texture is very high, which eventually leads to recognition or classification errors and 2) the size of defects is tiny, which are much more difficult to be detected than larger ones. To address such problems, this article proposes an adaptive image segmentation network (AIS-Net) for pixelwise segmentation of surface defects. It consists of three main parts: multishuffle-block dilated convolution (MSDC), dual attention context guidance (DACG), and adaptive category prediction (ACP) modules, where MSDC is designed to merge the multiscale defect features for avoiding the loss of tiny defect feature caused by model depth, DACG is designed to capture more contextual information from the defect feature map for locating defect regions and obtaining clear segmentation boundaries, and ACP is used to make classification and regression for predicting defect categories. Experimental results show that the proposed AIS-Net is superior to the state-of-the-art approaches on four actual surface defect datasets (NEU-DET: 98.38% ± 0.03%, DAGM: 99.25% ± 0.02%, Magnetic-tile: 98.73% ± 0.13%, and MVTec: 99.72% ± 0.02%).

Tensor completion is a fundamental tool for incomplete data analysis, where the goal is to predict missing entries from partial observations. However, existing methods often make the explicit or implicit assumption that the observed entries are noise-free to provide a theoretical guarantee of exact recovery of missing entries, which is quite restrictive in practice. To remedy such drawback, this article proposes a novel noisy tensor completion model, which complements the incompetence of existing works in handling the degeneration of high-order and noisy observations. Specifically, the tensor ring nuclear norm (TRNN) and least-squares estimator are adopted to regularize the underlying tensor and the observed entries, respectively. In addition, a nonasymptotic upper bound of estimation error is provided to depict the statistical performance of the proposed estimator. Two efficient algorithms are developed to solve the optimization problem with convergence guarantee, one of which is specially tailored to handle large-scale tensors by replacing the minimization of TRNN of the original tensor equivalently with that of a much smaller one in a heterogeneous tensor decomposition framework. Experimental results on both synthetic and real-world data demonstrate the effectiveness and efficiency of the proposed model in recovering noisy incomplete tensor data compared with state-of-the-art tensor completion models.

In this article, an optimal output synchronization solution to the$H_{\infty}$optimization of linear discrete-time (DT) multiagent systems is investigated. Compared with current approaches, the issue of designated convergence rate is handled with system optimality, while less computation cost is required. Specifically, the internal model principle is employed to derive a cooperative regulation problem of DT systems, wherein no explicit solution to output regulation equations is needed for learning. Then, we introduce a convergence rate parameter to construct a group of auxiliary cooperative systems, based on which the zero-sum game in$H_{\infty}$optimization is formulated. The data-efficient off-policy reinforcement learning and output-feedback technique are applied to solve the enhanced Bellman equations with a designated convergence rate. This results in an online optimal synchronization solution learning from only the input–output data along the system trajectories. It is shown that the proposed optimal synchronization protocol achieves asymptotic synchronization for the original systems with the consensus error converging to zero at a designated rate. The effectiveness of the proposed approach is verified by the simulation results.

Hashing techniques have been extensively studied in cross-modal retrieval due to their advantages in high computational efficiency and low storage cost. However, existing methods unconsciously ignore the complementary information of multimodal data, thus failing to consider learning discriminative hash codes from the perspective of information complementarity while often involving time-consuming training overhead. To tackle the above issues, we propose an efficient discriminative hashing (EDH) with information complementarity consideration. Specifically, we reckon that multimodal features and their corresponding semantic labels describe heterogeneous data viewed from low-and high-level structures, which owns complementarity. To this end, low-level latent representation and high-level semantics representation are simply derived. Then, a joint learning strategy is formulated to simultaneously exploit the above two representations for generating discriminative hash codes, which is quite computationally efficient. Besides, EDH decomposes hash learning into two steps. To obtain powerful hash functions which are conductive to retrieval, a regularization term considering pairwise semantic similarity is introduced into hash functions learning. In addition, an efficient optimization algorithm is designed to solve the optimization problem in EDH. Extensive experiments conducted on benchmark datasets demonstrate the superiority of our EDH in terms of retrieval performance and training efficiency. The source code is available at https://github.com/hjf-hjf/EDH.

Space–air–ground integrated edge computing is expecting to provide pervasive computation services for Internet of Things (IoT), especially in remote areas. However, the offloading process of power-limited IoT devices is a challenge issue due to unreliable communications in an aerial environment. In this article, we propose an energy-efficient space–air–ground integrated edge computing network architecture, in which the IoT devices choose the most appropriate LEO satellites or unmanned aerial vehicles (UAVs) for task offloading according to their energy level, communication conditions and computing capabilities. In order to providing efficient task offloading and energy-saving policy under an uncertainty aerial environment, a constrained Markov decision process is employed to formulate the task offloading decision problem and a deep reinforcement learning (DRL)-based algorithm is devised to solve the proposed problem. An adaptive federated DRL-based offloading method is further proposed to find suboptimal offloading decisions by considering the privacy protection and communication failure in the proposed network. Numerical results confirm the effectiveness of the proposed schemes on energy saving and computation efficiency.

Drug repositioning (DR) is a strategy to find new targets for existing drugs, which plays an important role in reducing the costs, time, and risk of traditional drug development. Recently, the matrix factorization approach has been widely used in the field of DR prediction. Nevertheless, there are still two challenges: 1) Learning ability deficiencies, the model cannot accurately predict more potential associations. 2) Easy to fall into a bad local optimal solution, the model tends to get a suboptimal result. In this study, we propose a self-paced non-negative matrix tri-factorization (SPLNMTF) model, which integrates three types of different biological data from patients, genes, and drugs into a heterogeneous network through non-negative matrix tri-factorization, thereby learning more information to improve the learning ability of the model. In the meantime, the SPLNMTF model sequentially includes samples into training from easy (high-quality) to complex (low-quality) in the soft weighting way, which effectively alleviates falling into a bad local optimal solution to improve the prediction performance of the model. The experimental results on two real datasets of ovarian cancer and acute myeloid leukemia (AML) show that SPLNMTF outperforms the other eight state-of-the-art models and gets better prediction performance in drug repositioning. The data and source code are available at: https://github.com/qi0906/SPLNMTF.

This article presents a robust${H_{\infty }}$feedback compensator design approach for semilinear parabolic distributed parameter systems (DPSs) with external disturbances via mobile actuators and sensors. An${H_{\infty }}$performance constraint is introduced to deal with the external disturbances from the model and measurement noise. Two types of feedback compensators are designed in terms of the collocated and noncollocated mobile actuators and sensors. By the Lyapunov direct technique, some sufficient conditions based on LMI constraints are proposed for the exponential stability under${H_{\infty }}$performance constraints in the$\mathcal {L}^{2}$-norm. Moreover, the open-loop and closed-loop well-posedness of the semilinear DPSs with external disturbances are analyzed via the${C_{0}}$-semigroup theory approach. Finally, extensive numerical simulation results for semilinear DPSs with external disturbances via collocated and noncollocated mobile actuators and sensors are shown to verify the effectiveness of the proposed method.

Tensor-ring (TR) decomposition is a powerful tool for exploiting the low-rank property of multiway data and has been demonstrated great potential in a variety of important applications. In this article, non-negative TR (NTR) decomposition and graph-regularized NTR (GNTR) decomposition are proposed. The former equips TR decomposition with the ability to learn the parts-based representation by imposing non-negativity on the core tensors, and the latter additionally introduces a graph regularization to the NTR model to capture manifold geometry information from tensor data. Both of the proposed models extend TR decomposition and can be served as powerful representation learning tools for non-negative multiway data. The optimization algorithms based on an accelerated proximal gradient are derived for NTR and GNTR. We also empirically justified that the proposed methods can provide more interpretable and physically meaningful representations. For example, they are able to extract parts-based components with meaningful color and line patterns from objects. Extensive experimental results demonstrated that the proposed methods have better performance than state-of-the-art tensor-based methods in clustering and classification tasks.

This article investigates a class of switched nonlinear systems with output hysteresis, where the switching signal is arbitrary. The considered output hysteresis nonlinearity is captured by the Bouc-Wen model, which causes an uncertain gain that imposes a significant challenge on our control design. To overcome this problem, we propose an adaptive fuzzy optimal control scheme. In our scheme, the Nussbaum gain technique is used to compensate for output hysteresis, and, at each iteration, the actor-critic structure is progressively feedback and adjusted to design the optimal controller. Finally, our proposed design scheme can guarantee the stability of the nonlinear switched systems, which is demonstrated in the simulation results.

This paper studies optimal day-ahead scheduling of a battery swapping and charging system (BSCS) for electric vehicles (EVs) from a new perspective of multiple decision makers. It is considered that the BSCS locally incorporates the battery swapping and charging processes, and the two processes are managed by two operators, called a battery swapping operator (BSO) and a battery charging operator (BCO), respectively. Our main contribution is to propose a bilevel model where the BSO acts as the leader to receive and serve the battery swapping requests from EV users, and the BCO acts as the follower to interact with the grid and control battery charging and discharging power. We reformulate the bilevel optimization problem into an equivalent single-level problem that is a nonconvex mixed-integer nonlinear program (MINLP), and its size can easily become very large. To solve the problem efficiently, we develop a new heuristic composed of two parts, i.e., an estimation of the integer solution and an algorithm based on the alternating direction method (ADM). The results show that the proposed heuristic performs well in solving large-scale problems, providing close-to-optimal solutions quickly. In addition, compared to a social welfare maximization model that follows most existing related works, the proposed bilevel model can increase the number of swapped-out batteries by 35% and the batteries’ average energy state by 6%, improving the quality of battery swapping services.

Incomplete multi-view clustering (IMC) has received considerable attention due to its flexibility in fusing the multi-view information when the view samples are partly missing. However, existing methods seldom consider the affection of the missing samples to the contributions of the views. In this paper, we propose a novel graph fusion based IMC model (SAGF_IMC) to handle this problem. Instead of directly weighting the whole view, SAGF_IMC learns the sample-level auto weight, which allows considering both the contributions of different views and the affection of the missing samples. An effective iterative algorithm is developed, together with its convergence analysis. Experiments are provided to demonstrate that SAGF_IMC is superior to the related state-of-the-art methods by using several real-world datasets.

Direct-optimization-based dictionary learning has attracted increasing attention for improving computational efficiency. However, the existing direct optimization scheme can only be applied to limited dictionary learning problems, and it remains an open problem to prove that the whole sequence obtained by the algorithm converges to a critical point of the objective function. In this article, we propose a novel direct-optimization-based dictionary learning algorithm using the minimax concave penalty (MCP) as a sparsity regularizer that can enforce strong sparsity and obtain accurate estimation. For solving the corresponding optimization problem, we first decompose the nonconvex MCP into two convex components. Then, we employ the difference of the convex functions algorithm and the nonconvex proximal-splitting algorithm to process the resulting subproblems. Thus, the direct optimization approach can be extended to a broader class of dictionary learning problems, even if the sparsity regularizer is nonconvex. In addition, the convergence guarantee for the proposed algorithm can be theoretically proven. Our numerical simulations demonstrate that the proposed algorithm has good convergence performances in different cases and robust dictionary-recovery capabilities. When applied to sparse approximations, the proposed approach can obtain sparser and less error estimation than the different sparsity regularizers in existing methods. In addition, the proposed algorithm has robustness in image denoising and key-frame extraction.

Tensor-ring (TR) decomposition was recently studied and applied for low-rank tensor completion due to its powerful representation ability of high-order tensors. However, most of the existing TR-based methods tend to suffer from deterioration when the selected rank is larger than the true one. To address this issue, this article proposes a new low-rank sparse TR completion method by imposing the Frobenius norm regularization on its latent space. Specifically, we theoretically establish that the proposed method is capable of exploiting the low rankness and Kronecker-basis-representation (KBR)-based sparsity of the target tensor using the Frobenius norm of latent TR-cores. We optimize the proposed TR completion by block coordinate descent (BCD) algorithm and design a modified TR decomposition for the initialization of this algorithm. Extensive experimental results on synthetic data and visual data have demonstrated that the proposed method is able to achieve better results compared to the conventional TR-based completion methods and other state-of-the-art methods and, meanwhile, is quite robust even if the selected TR-rank increases.

Multiview dictionary learning (DL) is attracting attention in multiview clustering due to the efficient feature learning ability. However, most existing multiview DL algorithms are facing problems in fully utilizing consistent and complementary information simultaneously in the multiview data and learning the most precise representation for multiview clustering because of gaps between views. This article proposes an efficient multiview DL algorithm for multiview clustering, which uses the partially shared DL model with a flexible ratio of shared sparse coefficients to excavate both consistency and complementarity in the multiview data. In particular, a differentiable scale-invariant function is used as the sparsity regularizer, which considers the absolute sparsity of coefficients as the$\ell _{0}$norm regularizer but is continuous and differentiable almost everywhere. The corresponding optimization problem is solved by the proximal splitting method with extrapolation technology; moreover, the proximal operator of the differentiable scale-invariant regularizer can be derived. The synthetic experiment results demonstrate that the proposed algorithm can recover the synthetic dictionary well with reasonable convergence time costs. Multiview clustering experiments include six real-world multiview datasets, and the performances show that the proposed algorithm is not sensitive to the regularizer parameter as the other algorithms. Furthermore, an appropriate coefficient sharing ratio can help to exploit consistent information while keeping complementary information from multiview data and thus enhance performances in multiview clustering. In addition, the convergence performances show that the proposed algorithm can obtain the best performances in multiview clustering among compared algorithms and can converge faster than compared multiview algorithms mostly.

More and more evidence indicates that the dysregulations of microRNAs (miRNAs) lead to diseases through various kinds of underlying mechanisms. Identifying the multiple types of disease-related miRNAs plays an important role in studying the molecular mechanism of miRNAs in diseases. Moreover, compared with traditional biological experiments, computational models are time-saving and cost-minimized. However, most tensor-based computational models still face three main challenges: (i) easy to fall into bad local minima; (ii) preservation of high-order relations; (iii) false-negative samples. To this end, we propose a novel tensor completion framework integrating self-paced learning, hypergraph regularization and adaptive weight tensor into nonnegative tensor factorization, called SPLDHyperAWNTF, for the discovery of potential multiple types of miRNA-disease associations. We first combine self-paced learning with nonnegative tensor factorization to effectively alleviate the model from falling into bad local minima. Then, hypergraphs for miRNAs and diseases are constructed, and hypergraph regularization is used to preserve the high-order complex relations of these hypergraphs. Finally, we innovatively introduce adaptive weight tensor, which can effectively alleviate the impact of false-negative samples on the prediction performance. The average results of 5-fold and 10-fold cross-validation on four datasets show that SPLDHyperAWNTF can achieve better prediction performance than baseline models in terms of Top-1 precision, Top-1 recall and Top-1 F1. Furthermore, we implement case studies to further evaluate the accuracy of SPLDHyperAWNTF. As a result, 98 (MDAv2.0) and 98 (MDAv2.0-2) of top-100 are confirmed by HMDDv3.2 dataset. Moreover, the results of enrichment analysis illustrate that unconfirmed potential associations have biological significance.

With the rapid development of Internet of Things (IoT), the digital twin is emerging as one of the most promising technologies to connect physical components with digital space for better optimization of physical systems. However, the limited wireless resource and security concerns impede the deployment of the digital twin in IoT. In this article, we exploit blockchain to propose a new digital twin edge networks framework for enabling flexible and secure digital twin construction. We first develop cooperative federated learning through an access point (AP) to help resource-limited smart devices in constructing digital twin at the network edges belonging to different mobile network operators (MNOs). Then, we propose a model update chain by leveraging directed acyclic graph (DAG) blockchain to secure both local model updates and global model updates. In order to incentivize the APs to help in local models training for resource-limited smart devices and also encourage the APs to contribute resource in local model update verification, we design an iterative double auction-based joint cooperative federated learning and local model update verification scheme. The optimal unified time for cooperative federated learning and local model update verification is solved to maximize social welfare. Numerical results illustrate that the proposed scheme is efficient in digital twin construction.

Dynamic off-chain routing in payment channel network (PCN)-based Internet of Things (IoT) is attracting increasing research attention. However, there are two major issues in dynamic routing in PCN-based IoT with resource-limited devices. The first issue is how to achieve high long-term transaction efficiency in PCN with dynamic channel capacities. The second issue is how to achieve a lightweight routing algorithm deployed on IoT devices while achieving high transaction efficiency, i.e., successful payment amount and success ratio. Therefore, in this paper, we propose a compact deep reinforcement learning (DRL) algorithm to learn the joint dynamic and lightweight routing policy for maximizing long-term transaction efficiency. To obtain optimal performance in dynamic routing problems for off-chain systems, a proximal policy optimization algorithm is employed to create an actor–critic learning structure for training the teacher DRL model. To obtain a compact and efficient student DRL model, an adaptive pruning technique is utilized for pruning unnecessary parameters of networks in the teacher model adaptively without affecting its learning ability. Furthermore, knowledge distillation is leveraged to improve the performance of the student network. Thus, a compact and efficient student DRL model can be developed and implemented to maximize the long-term transaction efficiency in off-chain systems on resource-limited IoT devices. The simulation results demonstrate that the proposed DRL algorithm outperforms the other baseline algorithms in PCN transaction efficiency while requiring only 10% of the computation and storage resources compared with that of the original teacher model.

Tensor robust principal component analysis (TRPCA) is a fundamental model in machine learning and computer vision. Recently, tensor train (TT) decomposition has been verified effective to capture the global low-rank correlation for tensor recovery tasks. However, due to the large-scale tensor data in real-world applications, existing TRPCA models often suffer from high computational complexity. In this letter, we propose an efficient TRPCA under hybrid model of Tucker and TT. Specifically, in theory we reveal that TT nuclear norm (TTNN) of the original big tensor can be equivalently converted to that of a much smaller tensor via a Tucker compression format, thereby significantly reducing the computational cost of singular value decomposition (SVD). Numerical experiments on both synthetic and real-world tensor data verify the superiority of the proposed model.

Deep multitask learning (MTL) shares beneficial knowledge across participating tasks, alleviating the impacts of extreme learning conditions on their performances such as the data scarcity problem. In practice, participators stemming from different domain sources often have varied complexities and input sizes, for example, in the joint learning of computer vision tasks with RGB and grayscale images. For adapting to these differences, it is appropriate to design networks with proper representational capacities and construct neural layers with corresponding widths. Nevertheless, most of the state-of-the-art methods pay little attention to such situations, and actually fail to handle the disparities. To work with the dissimilitude of tasks' network designs, this article presents a distributed knowledge-sharing framework called tensor ring multitask learning (TRMTL), in which the relationship between knowledge sharing and original weight matrices is cut up. The framework of TRMTL is flexible, which is not only capable of sharing knowledge across heterogenous networks but also able to jointly learn tasks with varied input sizes, significantly improving performances of data-insufficient tasks. Comprehensive experiments on challenging datasets are conducted to empirically validate the effectiveness, efficiency, and flexibility of TRMTL in dealing with the disparities in MTL.

In general, existing cross-domain recognition methods mainly focus on changing the feature representation of data or modifying the classifier parameter and their efficiencies are indicated by the better performance. However, most existing methods do not simultaneously integrate them into a unified optimization objective for further improving the learning efficiency. In this article, we propose a novel cross-domain recognition algorithm framework by integrating both of them. Specifically, we reduce the discrepancies in both the conditional distribution and marginal distribution between different domains in order to learn a new feature representation which pulls the data from different domains closer on the whole. However, the data from different domains but the same class cannot interlace together enough and thus it is not reasonable to mix them for training a single classifier. To this end, we further propose to learn double classifiers on the respective domain and require that they dynamically approximate to each other during learning. This guarantees that we finally learn a suitable classifier from the double classifiers by using the strategy of classifier fusion. The experiments show that the proposed method outperforms over the state-of-the-art methods.

Cross-modal retrieval has attracted considerable attention for searching in large-scale multimedia databases because of its efficiency and effectiveness. As a powerful tool of data analysis, matrix factorization is commonly used to learn hash codes for cross-modal retrieval, but there are still many shortcomings. First, most of these methods only focus on preserving locality of data but they ignore other factors such as preserving reconstruction residual of data during matrix factorization. Second, the energy loss of data is not considered when the data of cross-modal are projected into a common semantic space. Third, the data of cross-modal are directly projected into a unified semantic space which is not reasonable since the data from different modalities have different properties. This article proposes a novel method called average approximate hashing (AAH) to address these problems by: 1) integrating the locality and residual preservation into a graph embedding framework by using the label information; 2) projecting data from different modalities into different semantic spaces and then making the two spaces approximate to each other so that a unified hash code can be obtained; and 3) introducing a principal component analysis (PCA)-like projection matrix into the graph embedding framework to guarantee that the projected data can preserve the main energy of data. AAH obtains the final hash codes by using an average approximate strategy, that is, using the mean of projected data of different modalities as the hash codes. Experiments on standard databases show that the proposed AAH outperforms several state-of-the-art cross-modal hashing methods.

Convolutional transform learning (CTL), learning filters by minimizing the data fidelity loss function in an unsupervised way, is becoming very pervasive, resulting from keeping the best of both worlds: the benefit of unsupervised learning and the success of the convolutional neural network. There have been growing interests in developing efficient CTL algorithms. However, developing a convergent and accelerated CTL algorithm with accurate representations simultaneously with proper sparsity is an open problem. This article presents a new CTL framework with a log regularizer that can not only obtain accurate representations but also yield strong sparsity. To efficiently address our nonconvex composite optimization, we propose to employ the proximal difference of the convex algorithm (PDCA) which relies on decomposing the nonconvex regularizer into the difference of two convex parts and then optimizes the convex subproblems. Furthermore, we introduce the extrapolation technology to accelerate the algorithm, leading to a fast and efficient CTL algorithm. In particular, we provide a rigorous convergence analysis for the proposed algorithm under the accelerated PDCA. The experimental results demonstrate that the proposed algorithm can converge more stably to desirable solutions with lower approximation error and simultaneously with stronger sparsity and, thus, learn filters efficiently. Meanwhile, the convergence speed is faster than the existing CTL algorithms.

Non-negative Tucker decomposition (NTD) is one of the most popular techniques for tensor data representation. To enhance the representation ability of NTD by multiple intrinsic cues, that is, manifold structure and supervisory information, in this article, we propose a generalized graph regularized NTD (GNTD) framework for tensor data representation. We first develop the unsupervised GNTD (UGNTD) method by constructing the nearest neighbor graph to maintain the intrinsic manifold structure of tensor data. Then, when limited must-link and cannot-link constraints are given, unlike most existing semisupervised learning methods that only use the pregiven supervisory information, we propagate the constraints through the entire dataset and then build a semisupervised graph weight matrix by which we can formulate the semisupervised GNTD (SGNTD). Moreover, we develop a fast and efficient alternating proximal gradient-based algorithm to solve the optimization problem and show its convergence and correctness. The experimental results on unsupervised and semisupervised clustering tasks using four image datasets demonstrate the effectiveness and high efficiency of the proposed methods.

Rank minimization is widely used to extract low-dimensional subspaces. As a convex relaxation of the rank minimization, the problem of nuclear norm minimization has been attracting widespread attention. However, the standard nuclear norm minimization usually results in overcompression of data in all subspaces and eliminates the discrimination information between different categories of data. To overcome these drawbacks, in this article, we introduce the label information into the nuclear norm minimization problem and propose a labeled-robust principal component analysis (L-RPCA) to realize nuclear norm minimization on multisubspace data. Compared with the standard nuclear norm minimization, our method can effectively utilize the discriminant information in multisubspace rank minimization and avoid excessive elimination of local information and multisubspace characteristics of the data. Then, an effective labeled-robust regression (L-RR) method is proposed to simultaneously recover the data and labels of the observed data. Experiments on real datasets show that our proposed methods are superior to other state-of-the-art methods.

A spatial-construction-based fault diagnosis method is proposed to detect and locate the abnormality for unknown distributed parameter systems (DPSs). To accurately locate the abnormality, the continuous spatial basis functions (SBFs) are derived by the proposed spatial construction method from empirical data. Theoretical analysis proves that the B-spline curve is a proper solution to the spatial construction problem. Two new statistics are constructed based on the derived continuous SBFs and the improved independent component analysis algorithm. The abnormality can be timely detected according to the reference signals derived by the central limit theorem and hypothesis testing. With the continuous SBFs, the probability distribution of statistic contribution can be constructed to reveal the actual position of the abnormality. The proposed method can timely detect and locate the abnormality under fewer sensors without the knowledge of PDE and boundary conditions. The internal short circuit experiment on a lithium-ion battery demonstrates the effectiveness and superiority of the proposed method.

The thermal effect has a significant impact on the performance and durability of lithium-ion batteries. This article proposes a systematic approach for fast modeling of the distributed battery thermal process. In this method, the time/space (T/S) separation is adopted to decompose the spatio-temporal thermal dynamics. Under the T/S separation, an incremental-learning-based regulator is first employed for the recursive update of spatial basis functions, which can represent the most recent spatial complexity. Then, a corresponding temporal model with incremental adaptive characteristics is developed to capture the temporal nonlinearity. Under such a fully adaptive modeling pattern, the desired temperature distribution can be reconstructed with high efficiency and flexibility. Experimental studies indicate that the proposed method can achieve satisfactory modeling performance while its computational efficiency is outstanding compared to peer methods.

This article proposes a novel data reconstruction method, called projective cross-reconstruction (PCR) for cross-domain recognition. The intrinsic philosophy behind PCR is that the data from different domains but with the same label have a strong correlation and thus they can be reconstructed with each other. To this end, we first rearrange the data of source and target domains to form two new cross-data matrices, and the data with the same label but from different domains can be arranged together. Then, we use two different projection matrices to project the new cross-data into two approximate subspaces and perform the cross-reconstruction without introducing any extra matrix as the reconstruction coefficient matrix. This guarantees that the data from different domains can be interlaced well and the data from different domains but sharing the same label can be aligned together. In doing so, the problem of cross-domain distribution mismatch is solved and a discriminative and transferrable feature representation can be obtained. Moreover, PCR integrates the classifier learning and feature representation learning into a unified framework so that these two tasks can be iteratively improved until the termination condition is met. Extensive experiments on six datasets validate the effectiveness of our proposed PCR, compared with the state-of-the-art methods.

Blockchain technologies allow the Internet of Things (IoT) to build trust among various interest parties. For the resource-limited IoT devices, offloading computation-intensive tasks (blockchain verification and mining tasks, and data process tasks) to edge servers for execution is considered as a promising solution in mobile-edge computing. However, conventional methods (such as linear programming or game theory) for the computation offloading problem cannot achieve long-term performance while the existing deep reinforcement learning (DRL)-based algorithms suffer from slow convergence, lack of robustness, and unstable performance. In this article, we propose a multiagent DRL framework to achieve long-term performance for cooperative computation offloading, in which a scatter network is adopted to improve its stability and league learning is introduced for agents to explore the environment collaboratively for fast convergence and robustness. First, we study the nonorthogonal multiple access-enabled cooperative computation offloading problem and formulate the joint problem as a Markov decision process by considering both the blockchain mining tasks and data processing tasks. Second, to avoid useless exploration and unstable performance, we initially train an intelligent agent represented by scatter networks using conventional expert strategies. Third, in order to enhance the performance, we subsequently establish a hierarchical league where agents collaborate with others to explore the environment. Finally, our experimental results demonstrate that our algorithm could perform better in terms of reducing energy cost and delay cost, and shortening almost 60% of the training time compared with the state-of-the-art approaches.

A common approach for synchronizing the agents in a Wireless Sensor Network (WSN) is two-way timing stamps exchange mechanism. In this letter, by analyzing the change of accumulated clock offset within each communication cycle, an improved two-state discrete-time state model is proposed. A step further, two Kalman-filter-based estimators are proposed, by which the clock parameters and propagation delays can be estimated. The simulation results show that the proposed estimators outperform the conventional Kalman Filter (KF), especially with respect to the accumulated clock offset.

Multiview data processing has attracted sustained attention as it can provide more information for clustering. To integrate this information, one often utilizes the non-negative matrix factorization (NMF) scheme which can reduce the data from different views into the subspace with the same dimension. Motivated by the clustering performance being affected by the distribution of the data in the learned subspace, a tri-factorization-based NMF model with an embedding matrix is proposed in this article. This model tends to generate decompositions with uniform distribution, such that the learned representations are more discriminative. As a result, the obtained consensus matrix can be a better representative of the multiview data in the subspace, leading to higher clustering performance. Also, a new lemma is proposed to provide the formulas about the partial derivation of the trace function with respect to an inner matrix, together with its theoretical proof. Based on this lemma, a gradient-based algorithm is developed to solve the proposed model, and its convergence and computational complexity are analyzed. Experiments on six real-world datasets are performed to show the advantages of the proposed algorithm, with comparison to the existing baseline methods.

In recent years, numerous many-objective evolutionary algorithms (MaOEAs) have been developed to search for well-diversified and well-converged Pareto optimal solutions for high-dimensional many-objective optimization problems (MaOPs). However, existing MaOEAs have to tackle some daunting challenges, including the emergence of dominance resistance solutions, effective diversity preservation scheme, management of a large population size, extremely high computational complexity, sensitivity to the shape of Pareto front (PF), and overly relying on high-quality reference points. In this article, we present an evolution strategy (ES) for solving MaOPs, called MaOES, which can solve these challenges efficiently and effectively. Inspired by the Vector Equilibrium phenomenon in magnetic fields, isotropic magnetic particles would automatically repel from each other, keep the uniform distance from the nearest neighbors, and extend the entire magnetic fields as far as possible, all at the same time. In the proposed algorithm, an efficient self-adaptive Precision-Controllable Mutation operator is designed for individuals to explore and exploit the decision space. In addition, the Maximum Extension Distance strategy, which emulates the isotropic magnetic particle behavior in a magnetic field, is developed to guide individuals to keep uniform distance and extension to approximate the entire PF. As a result, the MaOES can obtain a well-converged and well-diversified PF with much less population size and far lower computational complexity. The larger the number of individuals, the sharper the contour the resulting approximate PF will be. Finally, the proposed algorithm is evaluated by the scalable MaOPs test suites on DTLZ and WFG. The experimental results have been demonstrated to provide a competitive and oftentimes better performance when compared against some chosen state-of-the-art MaOEAs.

This article proposes distributed demand response (DR) approaches for a multienergy residential community, which is equipped with various energy conversion and storage devices to serve multiple residential loads (e.g., electricity, natural gas, and heating loads). In the proposed DR approaches, each of the energy devices and loads is an individual decision-maker and also a node in a randomly connected communication network. The DR approaches are tolerant to incomplete information which is caused by random inaction of nodes and links in the network. At first, in order to coordinate nodes' behaviors in distributed DR, different information transmission mechanisms among nodes are employed. Particularly, Steiner tree broadcast, in which nodes are networked according to their energy types, is proposed to lower the nodes' computational complexity and the network's communication overhead. Based on the information transmission mechanisms, the initial DR problem is transformed into network problems that are solvable in a random network. Then, based on the randomized alternating direction method of multipliers, distributed algorithms are designed to optimally solve the network problems in the presence of incomplete information. In simulation, real-world datasets of multiple energy loads and prices are used, and three proposed DR approaches are compared in terms of convergence performance and communication overhead.

Parked Vehicle (PV) assistance in vehicular edge computing and networks is proposed to exploit underutilized computing resources from PVs for enhancing the resource capacity at the edge vehicular network. Containerization is used to improve task execution of PVs with fast start-up time, less hardware overheads and safe resource isolation. To this end, we introduce a task-container matching market to provide on-demand offloading services. For network implementation, the related entities including requesters, PVs with containers as performers and a service provider are described. Considering parking behaviors and resource availability, we measure the serviceabilities of PVs to select appropriate PVs for reliable and efficient task processing. According to utility functions, preference profiles of requesters and performers in the task-container matching market are modeled through the best response analysis. Finally, we apply matching game approach to cope with associations between tasks and containers deployed inside PVs. Numerical results demonstrate that compared with baseline schemes, our scheme accomplishes more tasks and acquires a higher overall utility in computation offloading.

Accurate and rapid diagnosis of COVID-19 using chest X-ray (CXR) plays an important role in large-scale screening and epidemic prevention. Unfortunately, identifying COVID-19 from the CXR images is challenging as its radiographic features have a variety of complex appearances, such as widespread ground-glass opacities and diffuse reticular-nodular opacities. To solve this problem, we propose an adaptive attention network (AANet), which can adaptively extract the characteristic radiographic findings of COVID-19 from the infected regions with various scales and appearances. It contains two main components: an adaptive deformable ResNet and an attention-based encoder. First, the adaptive deformable ResNet, which adaptively adjusts the receptive fields to learn feature representations according to the shape and scale of infected regions, is designed to handle the diversity of COVID-19 radiographic features. Then, the attention-based encoder is developed to model nonlocal interactions by self-attention mechanism, which learns rich context information to detect the lesion regions with complex shapes. Extensive experiments on several public datasets show that the proposed AANet outperforms state-of-the-art methods.

Tensor-ring (TR) decomposition has recently attracted considerable attention in solving the low-rank tensor completion (LRTC) problem. However, due to an unbalanced unfolding scheme used during the update of core tensors, the conventional TR-based completion methods usually require a large TR rank to achieve the optimal performance, which leads to high computational cost in practical applications. To overcome this drawback, we propose a new method to exploit the low TR-rank structure in this article. Specifically, we first introduce a balanced unfolding operation called tensor circular unfolding, by which the relationship between TR rank and the ranks of tensor unfoldings is theoretically established. Using this new unfolding operation, we further propose an algorithm to exploit the low TR-rank structure by performing parallel low-rank matrix factorizations to all circularly unfolded matrices. To tackle the problem of nonuniform missing patterns, we apply a row weighting trick to each circularly unfolded matrix, which significantly improves the adaptive ability to various types of missing patterns. The extensive experiments have demonstrated that the proposed algorithm can achieve outstanding performance using a much smaller TR rank compared with the conventional TR-based completion algorithms; meanwhile, the computational cost is reduced substantially.

Learning a good graph similarity matrix in data clustering is very crucial. The goal of clustering is to construct a good graph similarity matrix such that the similarity of points between the same classes is largest, and the similarity of points between different classes is smallest. In this paper, a more efficient subspace segmentation approach to learn a similarity matrix with large spectral gap is proposed. In our model, a robust self-representation coefficient matrix is learned by utilizing the Schatten-p norm instead of the conventional rank function. Besides, the fast block-diagonal structure of the coefficient representation matrix is enhanced by learning and optimizing the co-association matrix with the soft label of clustering results simultaneously in a unified framework. The affinity graphs constructed in this paper can clearly reveal the intrinsic structures of the data sets. Extensive experiments on the real data sets demonstrate that our proposed method can perform better than the state-of-the-art methods.

Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis. The numerical defects of TD methods, however, limit their practical applications on real-world data. As an alternative, convex tensor decomposition (CTD) was proposed to alleviate these problems, but its exact-recovery property is not properly addressed so far. To this end, we focus on latent convex tensor decomposition (LCTD), a practically widely-used CTD model, and rigorously prove a sufficient condition for its exact-recovery property. Furthermore, we show that such property can be also achieved by a more general model than LCTD. In the new model, we generalize the classic tensor (un-)folding into reshuffling operation, a more flexible mapping to relocate the entries of the matrix into a tensor. Armed with the reshuffling operations and exact-recovery property, we explore a totally novel application for (generalized) LCTD, i.e., image steganography. Experimental results on synthetic data validate our theory, and results on image steganography show that our method outperforms the state-of-the-art methods.

Dictionary learning plays a significant role in the field of machine learning. Existing works mainly focus on learning dictionary from a single domain. In this paper, we propose a novel projective double reconstructions (PDR) based dictionary learning algorithm for cross-domain recognition. Owing the distribution discrepancy between different domains, the label information is hard utilized for improving discriminability of dictionary fully. Thus, we propose a more flexible label consistent term and associate it with each dictionary item, which makes the reconstruction coefficients have more discriminability as much as possible. Due to the intrinsic correlation between cross-domain data, the data should be reconstructed with each other. Based on this consideration, we further propose a projective double reconstructions scheme to guarantee that the learned dictionary has the abilities of data itself reconstruction and data crossreconstruction. This also guarantees that the data from different domains can be boosted mutually for obtaining a good data alignment, making the learned dictionary have more transferability. We integrate the double reconstructions, label consistency constraint and classifier learning into a unified objective and its solution can be obtained by proposed optimization algorithm that is more efficient than the conventional l1 optimization based dictionary learning methods. The experiments show that the proposed PDR not only greatly reduces the time complexity for both training and testing, but also outperforms over the stateof- the-art methods.

Subspace learning based transfer learning methods commonly find a common subspace where the discrepancy of the source and target domains is reduced. The final classification is also performed in such subspace. However, the minimum discrepancy does not guarantee the best classification performance and thus the common subspace may be not the best discriminative. In this paper, we propose a latent elastic-net transfer learning (LET) method by simultaneously learning a latent subspace and a discriminative subspace. Specifically, the data from different domains can be well interlaced in the latent subspace by minimizing Maximum Mean Discrepancy (MMD). Since the latent subspace decouples inputs and outputs and, thus a more compact data representation is obtained for discriminative subspace learning. Based on the latent subspace, we further propose a low-rank constraint based matrix elastic-net regression to learn another subspace in which the intrinsic intra-class structure correlations of data from different domains is well captured. In doing so, a better discriminative alignment is guaranteed and thus LET finally learns another discriminative subspace for classification. Experiments on visual domains adaptation tasks show the superiority of the proposed LET method.

Linear discriminant analysis (LDA) has been widely used as the technique of feature exaction. However, LDA may be invalid to address the data from different domains. The reasons are as follows: 1) the distribution discrepancy of data may disturb the linear transformation matrix so that it cannot extract the most discriminative feature and 2) the original design of LDA does not consider the unlabeled data so that the unlabeled data cannot take part in the training process for further improving the performance of LDA. To address these problems, in this brief, we propose a novel transferable LDA (TLDA) method to extend LDA into the scenario in which the data have different probability distributions. The whole learning process of TLDA is driven by the philosophy that the data from the same subspace have a low-rank structure. The matrix rank in TLDA is the key learning criterion to conduct local and global linear transformations for restoring the low-rank structure of data from different distributions and enlarging the distances among different subspaces. In doing so, the variations of distribution discrepancy within the same subspace can be reduced, i.e., data can be aligned well and the maximally separated structure can be achieved for the data from different subspaces. A simple projected subgradient-based method is proposed to optimize the objective of TLDA, and a strict theory proof is provided to guarantee a quick convergence. The experimental evaluation on public data sets demonstrates that our TLDA can achieve better classification performance and outperform the state-of-the-art methods.

Blind source separation (BSS) is a typical unsupervised learning method that extracts latent components from their observations. In the meanwhile, convolutive BSS (CBSS) is particularly challenging as the observations are the mixtures of latent components as well as their delayed versions. CBSS is usually solved in frequency domain since convolutive mixtures in time domain is just instantaneous mixtures in frequency domain, which allows to recover source frequency components independently of each frequency bin by running ordinary BSS, and then concatenate them to form the Fourier transformation of source signals. Because BSS has inherent permutation ambiguity, this category of CBSS methods suffers from a common drawback: it is very difficult to choose the frequency components belonging to a specific source as they are estimated from different frequency bins using BSS. This paper presents a tensor framework that can completely eliminate the permutation ambiguity. By combining each frequency bin with an anchor frequency bin that is chosen arbitrarily in advance, we establish a new virtual BSS model where the corresponding correlation matrices comply with a block tensor decomposition (BTD) model. The essential uniqueness of BTD and the sparse structure of coupled mixing parameters allow the estimation of the mixing matrices free of permutation ambiguity. Extensive simulation results confirmed that the proposed algorithm could achieve higher separation accuracy compared with the state-of-the-art methods.

How to learn dimension-reduced representations of image data for clustering has been attracting much attention. Motivated by that the clustering accuracy is affected by both the prior-known label information of some of the images and the sparsity feature of the representations, we propose a non-negative matrix factorization (NMF) method with dual constraints in this paper. In our model, one constraint is used to keep the label feature and the other constraint is utilized to enhance the sparsity of the representations. Notably that these two constraints are embedded naturally into the traditional NMF model, refraining from the usage of the balance parameters which are hard to choose. Meantime, for solving the proposed model, the alternative iteration scheme is employed, and an efficient algorithm based on convex optimization is designed to conduct each iteration operation. It is proved that this algorithm achieves a nonlinear convergence rate, much faster than existing methods with linear rate. Simulation results demonstrate the advantages of the proposed method.

Data rewarding is a novel business model leading a new economic trend in mobile networks, in which the operators stimulate mobile users to watch ads with data rewards and ask for corresponding payments from advertisers. Yet, due to the uncertain nature of users' preferences, it is always challenging for the advertiser to find the best choice of data rewards to attain an optimum balance between ad revenue and rewards spent. In this paper, we build a general contract-theoretic framework to address the problem of data rewards design in a realistic asymmetric information scenario, where each user is associated with multi-dimensional private information, i.e., data valuation, ad valuation, and ad sensitivity. In particular, we model the interplay between the advertiser and users by using a multi-dimensional contract approach, and theoretically analyze optimal data rewarding schemes. To ensure global incentive compatibility, we utilize the structural properties of our contract problem and convert the multi-dimensional contract into an equivalent one-dimensional contract. Necessary and sufficient conditions for an optimal and feasible contract are then derived to provide incentives for engagement of users in data rewarding scheme. Extensive numerical evaluations validate the efficiency of the designed multi-dimensional contract for data rewarding compared to other benchmark schemes.

Nonnegative Tucker Decomposition (NTD) is one of the most popular technique for feature extraction and representation from nonnegative tensor data with preserving internal structure information. From the perspective of geometry, highdimensional data are usually drawn in low-dimensional submanifold of the ambient space. In this paper, we propose a novel Graph reguralized Nonnegative Tucker Decomposition (GNTD) method which is able to extract the low-dimensional parts-based representation and preserve the geometrical information simultaneously from high-dimensional tensor data. We also present an effictive algorithm to solve the proposed GNTD model. Experimental results demonstrate the effectiveness and high efficiency of the proposed GNTD method.

By providing computation and storage resources at the edge of the wireless access networks, edge computing(EC) has been regarded as a provisioning solution to enable the efficient, reliable and cost-effective two-way energy and information flows in smart grids. In this paper, we propose the framework of EC-based smart grid networks, in which EC servers are deployed at the gateways between the remote cloud center and the terminal smart meters. The EC servers perform energy scheduling and renewable energy generation(RG) output forecasting, based on the collected power demand data of terminal devices and monitoring data of RG equipments. According to the inherent collaboration features of the monitoring data offloading, that the outputs of the same size/type RG equipments in a limited area are the same in a short time, we consider an efficient cooperative task offloading and resource allocation scheme. Not all of the monitoring data should be offloaded. Then, an optimal problem is formulated, the transmission powers and channels, computation resource allocation and task offloading fraction of devices are jointly optimized. Numerical results show that our proposed schemes reduce the system cost efficiently, while the latency constraints are ensured.

This paper studies a new model of energy storage (ES) sharing in a residential community in which some homes have physical ESs (PESs) but some do not. The non-PES homes can buy ES capacity from PES homes, creating virtual ESs (VESs). Based on the transaction results between PESs and VESs, an online algorithm is developed for real-time energy management of ES sharing among the homes. During online control, non-negative long-term utilities of homes and practical charging/discharging constraints of PESs and VESs are considered. The advantage of the proposed algorithm is that system state forecasting, such as home load, renewable generation, and grid price, is not required. The algorithm only needs current system states to make a control decision. Theoretic analysis shows that the worst-case system cost under the algorithm is upper bounded, guaranteeing the online solution is near-optimal. In the simulation, real-time data of grid price and home power use is employed, and the proposed algorithm is benchmarked against a greedy algorithm and a theoretic lower bound.

Federated learning is an emerging machine learning technique that enables distributed model training using local datasets from large-scale nodes, e.g., mobile devices, but shares only model updates without uploading the raw training data. This technique provides a promising privacy preservation for mobile devices while simultaneously ensuring high learning performance. The majority of existing work has focused on designing advanced learning algorithms with an aim to achieve better learning performance. However, the challenges, such as incentive mechanisms for participating in training and worker (i.e., mobile devices) selection schemes for reliable federated learning, have not been explored yet. These challenges have hindered the widespread adoption of federated learning. To address the above challenges, in this article, we first introduce reputation as the metric to measure the reliability and trustworthiness of the mobile devices. We then design a reputation-based worker selection scheme for reliable federated learning by using a multiweight subjective logic model. We also leverage the blockchain to achieve secure reputation management for workers with nonrepudiation and tamper-resistance properties in a decentralized manner. Moreover, we propose an effective incentive mechanism combining reputation with contract theory to motivate high-reputation mobile devices with high-quality data to participate in model learning. Numerical results clearly indicate that the proposed schemes are efficient for reliable federated learning in terms of significantly improving the learning accuracy.

The drastically increasing volume and the growing trend on the types of data have brought in the possibility of realizing advanced applications such as enhanced driving safety, and have enriched existing vehicular services through data sharing among vehicles and data analysis. Due to limited resources with vehicles, vehicular edge computing and networks (VECONs) i.e., the integration of mobile edge computing and vehicular networks, can provide powerful computing and massive storage resources. However, road side units that primarily presume the role of vehicular edge computing servers cannot be fully trusted, which may lead to serious security and privacy challenges for such integrated platforms despite their promising potential and benefits. We exploit consortium blockchain and smart contract technologies to achieve secure data storage and sharing in vehicular edge networks. These technologies efficiently prevent data sharing without authorization. In addition, we propose a reputation-based data sharing scheme to ensure high-quality data sharing among vehicles. A three-weight subjective logic model is utilized for precisely managing reputation of the vehicles. Numerical results based on a real dataset show that our schemes achieve reasonable efficiency and high-level of security for data sharing in VECONs.

The introduction of edge computing into blockchain-enabled Internet of Things (IoT) for offloading computational tasks is attracting increasing attention. Computing resource trading unavoidably happens in edge-assisted IoT. However, efficient computing resource trading cannot be achieved because of the “cold start” and “long return” problems. To address these challenges, we propose to use a credit-based payment for fast computing resource trading in edge-assisted blockchain-enabled IoT; therefore, the IoT nodes can finish fast payment and frequent trading by borrowing resource coins from other IoT nodes based on their credit values. In our resource-coin loan problem, we propose an iterative double-auction-based algorithm, where a broker is introduced to solve the loan allocation problem and to determine the size of the loan each lender would provide to each borrower. Furthermore, the broker enforces specific loan pricing rules to induce the borrowers and lenders to bid truthfully. Then, the hidden privacy information could be extracted to achieve the optimal resource-coin allocation and loan pricing. The proposed algorithm can maximize the economic benefits while protecting privacy. Simulations showed that the proposed algorithm can maximize social welfare. In addition, we compared the proposed algorithm with the credit-bank-based method in terms of the satisfaction function and payments. The experimental results demonstrated that the proposed algorithm was individually rational, truthful, and budget-balanced.

Subspace clustering aims to separate the data into clusters under the hypothesis that the samples within the same cluster will lie in the same low-dimensional subspace. Due to the tough pairwise constraints, k-subspace clustering is sensitive to outliers and initialization. In this letter, we present a novel deep architecture for k-subspace clustering to address this issue, called as Deep Weighted k-Subspace Clustering (DWSC). Specifically, our framework consists of autoencoder and weighted k-subsapce network. We first use the autoencoder to non-linearly compress the samples into the low-dimensional latent space. In the weighted k-subspace network, we feed the latent representation into the assignment network to output soft assignments which represent the probability of data belonging to the according subspace. Subsequently, the optimal k subspaces are identified by minimizing the projection residuals of the latent representations to all subspaces, using the learned soft assignments as a weighting vector. Finally, we jointly optimize the representation learning and clustering in a unified framework. Experimental results show that our approach outperforms the state-of-the-art subspace clustering methods on two benchmark datasets.

This paper investigates a problem of designing an adaptive asymptotic cooperative control scheme for nonlinear time-varying multiagent systems, which can simultaneously tolerate unknown actuator failures and unknown control directions. To address such the problem, we propose a conditional inequality, which allows multiple piecewise Nussbaum functions to acquire the control robustness. Benefiting from this robustness, a part of failure uncertainties and system errors are compensated for, while the remaining parts are handled by adaptive control technique. Moreover, structural properties of the proposed adaptive laws are utilized so that Barbalat's lemma is applicable to make all the followers asymptotically converge to the leader based on the neighborhood information.

Optimal computing resource allocation for edge-cloud-assisted Internet of things (IoT) in blockchain network is attracting increasing attention. Auction is a classical algorithm which guarantees that the computing resources are allocated to the buyers of the computing resource. However, the traditional auction algorithm only guarantees the revenue gains for the sellers of the computing resource. How to guarantee the seller and the buyer of the computing resource when both are willing to trade and moreover, bid truthfully, is still an open problem in computing resource trading for edge-cloud-assisted IoT. In this paper, we introduce a broker with sparse information to manage and adjust the trading market. We then propose an iterative double-sided auction scheme for computing resource trading, where the broker solves an allocation problem to determine how much computing resource is traded and designs a specific price rule to induce the buyers and sellers of the computing resource to submit bids in a truthful way. Thus, hidden information can be extracted gradually to obtain optimal computing resource allocation and trading prices. Hence, the proposed algorithm can achieve the maximum social welfare meanwhile protecting the privacies of the buyers and the sellers. Our theoretical analysis and simulations demonstrate that the proposed algorithm is efficient, i.e., it achieves the maximum social welfare. In addition, the proposed algorithm can provide effective trading strategies for the buyers and sellers of the computing resource, leading to the proposed algorithm satisfying incentive compatibility, individual rationality, and budget balance.

In this paper, we propose a unified model called flexible affinity matrix learning (FAML) for unsupervised and semisupervised classification by exploiting both the relationship among data and the clustering structure simultaneously. To capture the relationship among data, we exploit the self-expressiveness property of data to learn a structured matrix in which the structures are induced by different norms. A rank constraint is imposed on the Laplacian matrix of the desired affinity matrix, so that the connected components of data are exactly equal to the cluster number. Thus, the clustering structure is explicit in the learned affinity matrix. By making the estimated affinity matrix approximate the structured matrix during the learning procedure, FAML allows the affinity matrix itself to be adaptively adjusted such that the learned affinity matrix can well capture both the relationship among data and the clustering structure. Thus, FAML has the potential to perform better than other related methods. We derive optimization algorithms to solve the corresponding problems. Extensive unsupervised and semisupervised classification experiments on both synthetic data and real-world benchmark data sets show that the proposed FAML consistently outperforms the state-of-the-art methods.

The ubiquitous information from multiple-view data, as well as the complementary information among different views, is usually beneficial for various tasks, for example, clustering, classification, denoising, and so on. Multiview subspace clustering is based on the fact that multiview data are generated from a latent subspace. To recover the underlying subspace structure, a successful approach adopted recently has been sparse and/or low-rank subspace clustering. Despite the fact that existing subspace clustering approaches may numerically handle multiview data, by exploring all possible pairwise correlation within views, high-order statistics that can only be captured by simultaneously utilizing all views are often overlooked. As a consequence, the clustering performance of the multiview data is compromised. To address this issue, in this paper, a novel multiview clustering method is proposed by using t-product in the third-order tensor space. First, we propose a novel tensor construction method to organize multiview tensorial data, to which the tensor-tensor product can be applied. Second, based on the circular convolution operation, multiview data can be effectively represented by a t-linear combination with sparse and low-rank penalty using "self-expressiveness." Our extensive experimental results on face, object, digital image, and text data demonstrate that the proposed method outperforms the state-of-the-art methods for a range of criteria.

This paper considers finite-time distributed state estimation for discrete-time nonlinear systems over sensor networks. The Round-Robin protocol is introduced to overcome the channel capacity constraint among sensor nodes, and the multiplicative noise is employed to model the channel fading. In order to improve the performance of the estimator under the situation, where the transmission resources are limited, fading channels with different stochastic properties are used in each round by allocating the resources. Sufficient conditions of the average stochastic finite-time boundedness and the average stochastic finite-time stability for the estimation error system are derived on the basis of the periodic system analysis method and Lyapunov approach, respectively. According to the linear matrix inequality approach, the estimator gains are designed. Finally, the effectiveness of the developed results are illustrated by a numerical example.

This paper considers the problem of I2- I∞filtering for discrete-time Takagi-Sugeno (T-S) fuzzy systems with multiplicative sensor noises over the channels with limited capacity. A more general multidensity logarithmic quantizer is designed to increase the utilization of the communication resources, and a sojourn-time-dependent Markov chain is used to model the variation of the quantizer density. Then, the fuzzy basis-, quantizer density-, and sojourn-time-dependent filter is designed for T-S fuzzy systems on the basis of the quantized measurements to improve the performance of the filter. Sufficient conditions are proposed to guarantee that the filtering error system is exponentially mean-square stable and achieves a prescribed I2- I∞performance. Finally, three examples are given to illustrate the developed new design techniques.

In green cities, one of the most promising energy system designs is the multi-energy system, which is capable of integrating different energy resources to supply stable energy for users. To schedule diverse energy efficiently, the energy trading among different energy entities is a big issue in multi-energy systems. This paper proposes auction mechanisms for energy trading in a smart multi-energy district, in which the district manager sells electricity, natural gas, and heating energy to users and meanwhile trades with outer energy networks. Two auction mechanisms are designed under the day-ahead and real-time markets, respectively. For each auction, energy allocation is optimized by solving a social welfare maximization problem, which is strictly subject to constraints of physical multi-energy system models. It is theoretically proven that both auctions are able to guarantee the properties of economic efficiency, truthfulness, and individual rationality. With these properties, users are incentivized to participate into the auctions with fairness. Finally, real data are adopted to evaluate the performance of the proposed mechanisms. The theoretic analysis of the properties is verified as well.

By using a sparse representation or low-rank representation of data, the graph-based subspace clustering has recently attracted considerable attention in computer vision, given its capability and efficiency in clustering data. However, the graph weights built using the representation coefficients are not the exact ones as the traditional definition is in a deterministic way. The two steps of representation and clustering are conducted in an independent manner, thus an overall optimal result cannot be guaranteed. Furthermore, it is unclear how the clustering performance will be affected by using this graph. For example, the graph parameters, i.e., the weights on edges, have to be artificially pre-specified while it is very difficult to choose the optimum. To this end, in this paper, a novel subspace clustering via learning an adaptive low-rank graph affinity matrix is proposed, where the affinity matrix and the representation coefficients are learned in a unified framework. As such, the pre-computed graph regularizer is effectively obviated and better performance can be achieved. Experimental results on several famous databases demonstrate that the proposed method performs better against the state-of-the-art approaches, in clustering.

The introduction of wirelessly charged electric buses (WCEBs) into current public transportation system attracts many attentions in recent years. As the wireless charging technology enables energy transfer from power transmitters to electric vehicles (EVs) on road, it provides a promising solution to reduce the huge cost of battery with large size and long charging time, which are two critical impediments for EV applications. However, the system cost of WCEBs is huge. Under the dynamic electricity demands and the fluctuating electricity prices, the system operating electricity cost highly depends on the charging schedule. In this paper, according to the typical day-ahead electricity market, we explore an optimal charging scheduling scheme in a WCEB system to minimize the system operating electricity cost, while the characteristic of WCEBs is considered. The price of electricity fluctuates with the accumulated energy demands in both spatial and temporal domains. We first present a day-ahead reserved wholesale electricity determination algorithm, in which, the average speeds of WCEBs are presumed. Then, we propose an optimal charging scheduling algorithm, in which the WCEB charging schedules in slots are optimized sequentially. Both the reserved electricity and the predicted speeds in the slot are used. Simulation results demonstrate the efficiency of our proposed WCEB charging schedules.

This paper proposes a novel method, called robust latent subspace learning (RLSL), for image classification. We formulate an RLSL problem as a joint optimization problem over both the latent SL and classification model parameter predication, which simultaneously minimizes: 1) the regression loss between the learned data representation and objective outputs and 2) the reconstruction error between the learned data representation and original inputs. The latent subspace can be used as a bridge that is expected to seamlessly connect the origin visual features and their class labels and hence improve the overall prediction performance. RLSL combines feature learning with classification so that the learned data representation in the latent subspace is more discriminative for classification. To learn a robust latent subspace, we use a sparse item to compensate error, which helps suppress the interference of noise via weakening its response during regression. An efficient optimization algorithm is designed to solve the proposed optimization problem. To validate the effectiveness of the proposed RLSL method, we conduct experiments on diverse databases and encouraging recognition results are achieved compared with many state-of-the-arts methods.

In this paper, we propose an adaptive neural-network-based asymptotic control algorithm for a class of nonlinear systems subject to unknown actuator quantization. To this end, we exploit the sector property of the quantization nonlinearity and transform actuator quantization control problem into analyzing its upper bounds, which are then handled by a dynamic loop gain function-based approach. In our adaptive control scheme, there is only one parameter required to be estimated online for updating weights of neural networks. Within the framework of Lyapunov theory, it is shown that the proposed algorithm ensures that all the signals in the closed-loop system are ultimately bounded. Moreover, an asymptotic tracking error is obtained by means of introducing Barbalat's lemma to the proposed adaptive law.

This paper studies the issue of robust state estimation for coupled neural networks with parameter uncertainty and randomly occurring distributed delays, where the polytopic model is employed to describe the parameter uncertainty. A set of Bernoulli processes with different stochastic properties are introduced to model the randomly occurrences of the distributed delays. Novel state estimators based on the local coupling structure are proposed to make full use of the coupling information. The augmented estimation error system is obtained based on the Kronecker product. A new Lyapunov function, which depends both on the polytopic uncertainty and the coupling information, is introduced to reduce the conservatism. Sufficient conditions, which guarantee the stochastic stability and the performance of the augmented estimation error system, are established. Then, the estimator gains are further obtained on the basis of these conditions. Finally, a numerical example is used to prove the effectiveness of the results.

One of the major advantages of smart grid is to allow a large number of electric vehicles (EVs) to participate in energy dispatch as elastic energy storage devices via vehicle-to-grid (V2G) technology. As mechanism design for V2G energy trading can stimulate energy interaction between EVs and grids, it is really significant to V2G systems. This paper focuses on efficient mechanism design for energy trading in a two-layer V2G architecture, which includes a grid-aggregator layer and aggregator-EV layer. We propose two auction mechanisms for the two layers, respectively, and discuss three essential economic properties of the mechanisms, i.e., truthfulness, individual rationality, and efficiency. Then, based on these two mechanisms, we illustrate the detailed operation procedure of the two-layer V2G energy trading architecture. Performance evaluation shows that the proposed auction mechanisms greatly reduce social costs, i.e., enhance efficiency, while guaranteeing truthfulness and individual rationality.

A perfect bidirectional communication network is a common assumption in smart grids. However, it is unrealistic, especially in the neighborhood area network of microgrids. Due to the channel fading, large volumes of transmission data, and considerable communication cost, the imperfect communications affect the system performance directly. In this paper, we consider the uncertainty of imperfect communications in both supply and demand sides, which affects the microgrid system performance in terms of the packet loss ratio of the power demand data transmission and the forecasting accuracy ratio of the renewable energy generation. We analyze the impacts of imperfect communications on the demand response management (DRM) performance under the real-time pricing scheme. An optimization problem is formulated first to maximize the DRM performance of the microgrid system. As these impacts can be mitigated by using sufficient spectrum resources, we then propose a spectrum resource allocation scheme that considers different characteristics of transmission data and system communication cost to balance the tradeoff between the DRM performance and the incurred communication cost. We introduce a joint optimization problem that not only maximizes the DRM performance but also minimizes the communication cost. Simulation results reveal the impacts of imperfect communications on the DRM performance and power price, and the efficiency of the proposed optimization problems.

This paper presents an asymptotic tracking control design method for stochastic strict-feedback systems via fuzzy logic systems. In the existing results, stochastic controls are usually limited to be bounded in probability. However, how to realize the asymptotic tracking control for stochastic strict-feedback systems remains a control dilemma. This paper achieves the asymptotic tracking control by proposing a novel gain suppressing inequality approach. Specifically, the three-part construction is performed to achieve such control objective for stochastic systems. First, the novel gain suppressing inequality technique is developed to lay the foundation for carrying out the Lyapunov stability analysis. Second, the developed inequality technique is integrated with each step of the backstepping-based adaptive control design procedure. Third, analyses are provided to realize the asymptotic tracking control of stochastic strict-feedback systems.

This paper concerns with the problem of adaptive inverse compensation control for a class of uncertain pure-feedback nonlinear systems with asymmetric actuator backlash. By resorting to the mean-value theorem, the considered system can be transformed into the strict-feedback form with unknown state-dependent virtual control coefficients. Then, the most challenging difficulty is how to design the adaptive backlash inverse compensator in face of uncertain control gain function. To overcome this challenge, we first propose a smooth inverse model for asymmetric backlash, and based on it, a new expression of adaptive compensation error is further developed, which also paves the way to the embeddedness of fuzzy logic systems to cancel the unknown gain function. Moreover, two mutually learning mechanisms (one is for predicting unknown backlash parameters, while another is to search for optimal fuzzy weights) are further constructed such that the inverse compensator can be updated online. With the backstepping iteration design of compensator input, an adaptive fuzzy compensation controller (i.e., the compensator output) is developed to ensure the asymptotic stability of the closed-loop system. Finally, comparative simulations are conducted to validate the effectiveness and applicability of the proposed control theory.

This paper solves the problem of adaptive fuzzy inverse compensation control for an uncertain nonlinear system whose actuator is subjected to generalized dead-zone nonlinearity. By defining a continuous connection function and combining with the mean-value theorem, the generalized dead zone is first decomposed into a nominal asymmetric dead zone multiplying an uncertain continuous input function. Afterward, a smooth inversion and its parameterization are further proposed such that a new expression of adaptive asymmetric dead-zone compensation error is established in Theorems 1 and 2. With such an expression, the fuzzy systems can be successfully embedded into a compensation structure to indirectly handle uncertain input dynamics. In addition, a separation scheme is developed to construct two online estimators. Based on the above design procedure, an adaptive inverse compensator for generalized dead zone is built eventually. With the backstepping iteration design of compensator input, an adaptive fuzzy controller is developed to establish the closed-loop system stability. Finally, two simulations are conducted to illustrate the effectiveness and applicability of the proposed control scheme.

This paper mainly aims at the problem of adaptive quantized control for a class of uncertain nonlinear systems preceded by asymmetric actuator backlash. One challenging problem that blocks the construction of our control scheme is that the real control signal is wrapped in the coupling of quantization effect and nonsmooth backlash nonlinearity. To resolve this challenge, this paper presents a two-stage separation approach established on two new technical components, which are the approximate asymmetric backlash model and the nonlinear decomposition of quantizer, respectively. Then the real control is successfully separated from the coupling dynamics. Furthermore, by employing the neural networks and adaptation method in control design, a quantized controller is developed to guarantee the asymptotic convergence of tracking error to an adjustable region of zero and uniform ultimate boundedness of all closed-loop signals. Eventually, simulations are conducted to support our theoretical results.

To achieve satisfying motion/force objectives, it is required for the multiarm robot manipulation to tackle unknown nonlinearities and uncertainties. Existing control schemes have a requirement that the deadzone nonlinearity in the sensor channel could be ignored. However, the sensor deadzone is widely spread in real world applications; and its existence significantly limits the robotic performances. Moreover, the kinematics and dynamics of the manipulated object cannot be accurately known as the prior knowledge. Hence, such robotic systems may not be perfectly controlled by conventional approaches. In this paper, a coordinated motion/force control method is presented to handle unknown sensor deadzone and object's uncertainty. The proposed method ensures the motion and internal force errors be bounded in a small neighborhood around the origin. Finally, comparative studies are presented to show the effectiveness and robustness of the proposed scheme.

Sparse subspace clustering (SSC), as one of the most successful subspace clustering methods, has achieved notable clustering accuracy in computer vision tasks. However, SSC applies only 10 vector data in Euclidean space. Unfortunately there is still no satisfactory approach to solve subspace clustering by self-expressive principle f or symmetric positive definite (SPD) matrices which is very useful, in computer vision. In this paper, by embedding the SPD matrices into a Reproducing Kernel Hilbert Space (RKHS), a kernel subspace clustering method is constructed un the SPD manifold through an appropriate Log-Euclidean kernel, termed as kernel sparse subspace clustering on the SPD Riemannian manifold(KSSCR). By exploiting the intrinsic Riemannian geometry within data, KSSCR can effectively characterize the geodesic distance between SPD matrices to uncover the underlying subspace structure. Experimental results Oft several famous datasets demonstrate that the proposed method achieves better clustering results than the state-of-the-art approaches.

With the increasing availability of various sensor technologies, we now have access to large amounts of multiblock (also called multiset, multirelational, or multiview) data that need to be jointly analyzed to explore their latent connections. Various component analysis methods have played an increasingly important role for the analysis of such coupled data. In this article, we first provide a brief review of existing matrix-based (two-way) component analysis methods for the joint analysis of such data with a focus on biomedical applications. Then, we discuss their important extensions and generalization to multiblock multiway (tensor) data. We show how constrained multiblock tensor decomposition methods are able to extract similar or statistically dependent common features that are shared by all blocks, by incorporating the multiway nature of data. Special emphasis is given to the flexible common and individual feature analysis of multiblock data with the aim to simultaneously extract common and individual latent components with desired properties and types of diversity. Illustrative examples are given to demonstrate their effectiveness for biomedical data analysis.

Spectrum access strategy plays a critical role in multichannel cognitive radio networks (CRNs). However, the CRNs cannot obtain the maximal throughput, when the existing access strategies, including overlay, underlay, and hybrid access strategies, are applied to multichannel CRNs. In this paper, we present a generalized access strategy in a multichannel CRN smart home environment, in which a secondary user (SU) system selects part of channels for sequential spectrum sensing, and accesses these channels based on the sensing results. Moreover, it accesses the remaining channels directly. We then formulate a two-phase optimization framework, which takes the sensing channel selection, sensing time allocation, and the power allocation into consideration, to maximize the gross average throughput of the multichannel CRN. In the sensing phase, a generalized access strategy algorithm (GAS) is first proposed, where we prove that only part of channels needs to be selected for spectrum sensing to achieve the maximum throughput. An optimal stopping rule is proposed to determine the optimal number of selected sensing channels. In addition, a completed hybrid access strategy algorithm is further investigated where the SU system senses all channels. An approximation algorithm is also presented to achieve suboptimal results with low computational complexity. In the transmission phase, the transmission powers of all channels are optimized via convex algorithms. Numerical experiments show that, compared with the existing schemes, the proposed schemes are able to achieve considerable throughput improvement.

This paper presents a saturated Nussbaum function based approach for robotic systems with unknown actuator dynamics. To eliminate the effect of the control shock from the traditional Nussbaum function, a new type of the saturated Nussbaum function is developed with the idea of time-elongation. Moreover, by exploiting properties of the proposed Nussbaum function, a promising theorem is established to deal with unknown multiple actuator nonlinearities. In what follows, the proposed theorem is integrated with the adaptive control technique such that the stability analysis of the robotic system is completed. It thus guarantees that the state of the robotic system asymptotically converges to the desired trajectory. Finally, comparative studies are carried out to validate the effectiveness and the superiority of the proposed approach.

Vehicular social network (VSN) is envisioned to serve as an essential data sensing, exchanging and processing platform for the future Intelligent Transportation Systems. In this paper, we aim to address the location privacy issue in VSNs. In traditional pseudonym-based solutions, the privacy-preserving strength is mainly dependent on the number of vehicles meeting at the same occasion. We notice that an individual vehicle actually has many chances to meet several other vehicles. In most meeting occasions, there are only few vehicles appearing concurrently. Motivated by these observations, we propose a new privacy-preserving scheme, called MixGroup, which is capable of efficiently exploiting the sparse meeting opportunities for pseudonym changing. By integrating the group signature mechanism, MixGroup constructs extended pseudonym-changing regions, in which vehicles are allowed to successively exchange their pseudonyms. As a consequence, for the tracking adversary, the uncertainty of pseudonym mixture is accumulatively enlarged, and therefore location privacy preservation is considerably improved. We carry out simulations to verify the performance of MixGroup. Results indicate that MixGroup significantly outperforms the existing schemes. In addition, MixGroup is able to achieve favorable performance even in low traffic conditions.

Vehicle-to-grid (V2G) technology enables bidirectional energy flow between electric vehicles (EVs) and power grid, which provides flexible demand response management (DRM) for the reliability of smart grid. EV mobility is a unique and inherent feature of the V2G system. However, the inter-relationship between EV mobility and DRM is not obvious. In this paper, we focus on the exploration of EV mobility to impact DRM in V2G systems in smart grid. We first present a dynamic complex network model of V2G mobile energy networks, considering the fact that EVs travel across multiple districts, and hence EVs can be acting as energy transporters among different districts. We formulate the districts' DRM dynamics, which is coupled with each other through EV fleets. In addition, a complex network synchronization method is proposed to analyze the dynamic behavior in V2G mobile energy networks. Numerical results show that EVs mobility of symmetrical EV fleet is able to achieve synchronous stability of network and balance the power demand among different districts. This observation is also validated by simulation with real world data.

Research on the smart grid is being given enormous supports worldwide due to its great significance in solving environmental and energy crises. Electric vehicles (EVs), which are powered by clean energy, are adopted increasingly year by year. It is predictable that the huge charge load caused by high EV penetration will have a considerable impact on the reliability of the smart grid. Therefore, fair energy scheduling for EV charge and discharge is proposed in this paper. By using the vehicle-to-grid technology, the scheduler controls the electricity loads of EVs considering fairness in the residential distribution network. We propose contribution-based fairness, in which EVs with high contributions have high priorities to obtain charge energy. The contribution value is defined by both the charge/discharge energy and the timing of the action. EVs can achieve higher contribution values when discharging during the load peak hours. However, charging during this time will decrease the contribution values seriously. We formulate the fair energy scheduling problem as an infinite-horizon Markov decision process. The methodology of adaptive dynamic programming is employed to maximize the long-term fairness by processing online network training. The numerical results illustrate that the proposed EV energy scheduling is able to mitigate and flatten the peak load in the distribution network. Furthermore, contribution-based fairness achieves a fast recovery of EV batteries that have deeply discharged and guarantee fairness in the full charge time of all EVs.

As the next-generation power grid, smart grid will be integrated with a variety of novel communication technologies to support the explosive data traffic and the diverse requirements of quality of service (QoS). Cognitive radio (CR), which has the favorable ability to improve the spectrum utilization, provides an efficient and reliable solution for smart grid communications networks. In this paper, we study the QoS differential scheduling problem in the CR-based smart grid communications networks. The scheduler is responsible for managing the spectrum resources and arranging the data transmissions of smart grid users (SGUs). To guarantee the differential QoS, the SGUs are assigned to have different priorities according to their roles and their current situations in the smart grid. Based on the QoS-aware priority policy, the scheduler adjusts the channels allocation to minimize the transmission delay of SGUs. The entire transmission scheduling problem is formulated as a semi-Markov decision process and solved by the methodology of adaptive dynamic programming. A heuristic dynamic programming (HDP) architecture is established for the scheduling problem. By the online network training, the HDP can learn from the activities of primary users and SGUs, and adjust the scheduling decision to achieve the purpose of transmission delay minimization. Simulation results illustrate that the proposed priority policy ensures the low transmission delay of high priority SGUs. In addition, the emergency data transmission delay is also reduced to a significantly low level, guaranteeing the differential QoS in smart grid.

This paper proposes an improved version of the single objective optimization evolutionary algorithm based on Covariance Matrix Learning and Searching Preference (CMLSP), named ICMLSP. ICMLSP uses the same way with CMLSP to generate high quality solutions by sampling a multivariate Gauss distribution, which uses the best solutions found so far as its mean value. However, unlike the previous one, ICMLSP uses different covariance matrix learning philosophy, that is, the principal component analysis (PCA) method is used to estimate the covariance matrix. Furthermore, ICMLSP tends to use smaller population size than CMLSP to achieve a faster search. In order to get enough information for a reliable estimation, a new cumulation strategy is designed in ICMLSP. Solutions are selected from an archive set which stores the best λ individuals in present population and last t(t >= 1) populations to estimate the covariance matrix. A new adaptive rule, which makes use of the history successful information to generate different searching step from two different Cauchy distributions, is designed for ICMLSP to balance global exploration and local exploitation. Finally, the performance of the ICMLSP has been tested on 15 noiseless optimization problems designed for the CEC 2015 Competition on Learning-based Real-Parameter Single Objective Optimization. The results are reported at the end of this paper.

False data injection attacks have serious threat to the smart grid, e.g., may incur power outage or blackout. Normally, an intruder should have priori knowledge of the linear structure matrix and then control all smart meters to perform attacks. State-of-the-art studies have proven in theory that false data injection attacks can be unobservable when an intruder coordinately controls a small number of smart meters. However, there are no practical or implementable unobservable false data injection attacks with low-sparsity yet in the literature. In this paper, we propose a two-stage attacking scheme to demonstrate the practical feasibility of unobservable false data injection attacks in the smart grid. In the first stage, we explore the parallel factor analysis to derive the linear structure matrix of the smart grid using the intercepted data. In the second stage, we construct the sparse attack vector via a linear-based relaxation approach, which is used as the false data. Results indicate that we can realize highly successful attacking performance with a low detection probability.

Vehicle-to-grid (V2G) technology enables bidirectional energy flow between electric vehicles (EVs) and grid, which provides powerful demand response, balancing the electricity demand and supply in smart grid. Mobility is the key feature of EVs, which is also a significant challenge for V2G systems. In order to model the EV mobility in V2G systems, we propose a complex networking modeling for V2G mobile energy network. Each district has a V2G system. EVs travel among different districts. The EV fleets transport energy and impact the V2G systems of districts. The theory of complex network synchronization is employed to analyze the dynamics of the mobile energy network. Numerical results show the energy transportation of EV fleets may achieve synchronous stability of demand level of different districts, balancing the demand response in the mobile energy network.

Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor data while preserving the natural multilinear structure of data. However, as the data tensor often has multiple modes and is large scale, the existing NTD algorithms suffer from a very high computational complexity in terms of both storage and computation time, which has been one major obstacle for practical applications of NTD. To overcome these disadvantages, we show how low (multilinear) rank approximation (LRA) of tensors is able to significantly simplify the computation of the gradients of the cost function, upon which a family of efficient first-order NTD algorithms are developed. Besides dramatically reducing the storage complexity and running time, the new algorithms are quite flexible and robust to noise, because any well-established LRA approaches can be applied. We also show how nonnegativity incorporating sparsity substantially improves the uniqueness property and partially alleviates the curse of dimensionality of the Tucker decompositions. Simulation results on synthetic and real-world data justify the validity and high efficiency of the proposed NTD algorithms.

Abstract In cognitive vehicular networks (CVNs), spectrum sensing and access are introduced as the promising technologies to fully exploit the underutilized licensed spectrum. Because the sensing ability of a single secondary vehicular user (SVU) is affected by high mobility, dynamic topology, and unreliable wireless environment, collaborative sensing is developed to increase the sensing accuracy and efficiency. Generally, the synchronization is required in the collaborative sensing in CVN. However, it is difficult to keep all SVUs synchronized with others for sensing under the high dynamic network topology, and the sensing overhead of the synchronous cooperative action may be significant. In this paper, we first propose an asynchronous cooperative sensing scheme in which each SVU provides an energy information (EI) that is tagged with location and time information. The sensing decision will be made on account of the EI. Considering the temporal and spatial diversities of each SVU, we assign different weights to each EI and formulate the probabilities of detection and false alarm as the optimization problems to find the optimal weight of each EI. Then, based on the asynchronous sensing, the specifications of the opportunistic spectrum access mechanism are elaborated in both centralized and decentralized CVNs for the sake of practical implementation. We analyze the system performance in terms of achievable throughput and transmission delay. Numerical results show that the proposed scheme is able to achieve substantially higher throughput and lower delay, as compared with existing schemes. Copyright © 2014 John Wiley & Sons, Ltd.

In this paper, we propose a single objective optimization evolutionary algorithm (EA) based on Covariance Matrix Learning and Searching Preference (CMLSP) and design a switching method which is used to combine CMLSP and Covariance Matrix Adaptation Evolution Strategy (CMAES). Then we investigate the performance of the switch method on a set of 30 noiseless optimization problems designed for the special session on real-parameter optimization of CEC 2014. The basic idea of the proposed CMLSP is that it is more likely to find a better individual around a good individual. That is to say, the better an individual is, the more resources should be invested to search the region around the individual. To achieve it, we discard the traditional crossover and mutation and design a novel method based on the covariance matrix leaning to generate high quality solutions. The best individual found so far is used as the mean of a Gaussian distribution and the covariance of the best λ individuals in the population are used as the evaluation of its covariance matrix and we sample the next generation individual from the Gaussian distribution other than using crossover and mutation. In the process of generating new individuals, the best individual is changed if ever a better one is found. This search strategy emphasizes the region around the best individual so that a faster convergence can be achieved. The use of switch method is to make best use of the proposed CMLSP and existing CMAES. At last, we report the results.

In active contour models (snakes), various vector force fields replacing the gradient of the original external energy in the equations of motion are a popular way to extract the object boundary. Gradient descent method is usually used to obtain the equations of motion by minimising the energy functional. However, it always suffers from local minimum in extracting complex geometries because of non‐convex functional. Gradient descent method with adaptive momentum term is proposed in this study. First, an acceleration function of evolution is defined. Then, the adaptive momentum term is obtained by calculating the product between the edge stopping function and the defined acceleration function. Finally, adaptive momentum is compatible with the snakes. The edge stopping function is used to decide the influence region of the momentum, whereas the defined acceleration function determines the magnitude of the momentum. It is used to extract the complex geometries (such as deep concavity) when adding the adaptive momentum into some snakes, such as gradient vector field or vector field convolution snakes. On the other hand, the proposed method also accelerates the rate of convergence. It can be applied to extract a single object in real images. The experimental results show that the proposed method is effective and efficient.

Recently, plug-in hybrid electric vehicles (PHEVs) have attracted considerable attention as a sustainable transport system and also an essential component of the smart grid. With the rapid growth of PHEVs penetration, the charging and discharging of PHEVs will pose a significant impact on the residential electricity distribution network. For this reason, the management of PHEV charging and discharging has become one of the key issues in the research of PHEVs. In most existing work, PHEVs are supposed to operate individually for charging and discharging in the grid. However, we argue that, by leveraging the cooperation among PHEVs, the grid will efficiently stimulate PHEV users to charge in load valley and discharge in load peak. As a consequence, the electricity load is well balanced. Meanwhile, the PHEV users also achieve higher profit. The PHEV charging and discharging cooperation is a win-win strategy for both the grid and the PHEV users. We formulate and resolve the PHEV charging and discharging cooperation in the framework of coalition game. The simulation results indicate that the peak-valley difference in electricity load of the grid is significantly reduced. Besides, the PHEV users have better satisfaction in the vehicle battery status and the economic profit.

Discriminatory channel estimation (DCE) is a recently developed strategy to enlarge the performance difference between a legitimate receiver (LR) and an unauthorized receiver (UR) in a multiple-input multiple-output (MIMO) wireless system. Specifically, it makes use of properly designed training signals to degrade channel estimation at the UR, which in turn limits the UR's eavesdropping capability during data transmission. In this paper, we propose a new two-way training scheme for DCE through exploiting a whitening-rotation (WR) based semiblind method. To characterize the performance of DCE, a closed-form expression of the normalized mean squared error (NMSE) of the channel estimation is derived for both the LR and the UR. Furthermore, the developed analytical results on NMSE are utilized to perform optimal power allocation between the training signal and artificial noise (AN). The advantages of our proposed DCE scheme are twofold: Compared with the existing DCE scheme based on the linear minimum mean square error (LMMSE) channel estimator, the proposed scheme adopts a semiblind approach and achieves better DCE performance; and the proposed scheme is robust against active eavesdropping with the pilot contamination attack, whereas the existing scheme fails under such an attack.

This issue marks the first anniversary issue of IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS after it changed its name from IEEE TRANSACTIONS ON NEURAL NETWORKS. I am happy to report that we had a great year! The number of new submissions in a year exceeded 1,000 for the first time in the history of TNN/TNNLS. IEEE TNN had a very successful development for 22 years from 1990 to 2011, and we have good reasons to believe that IEEE TNNLS will have many more years of successful growth.

This paper presents a projection pursuit (PP) based method for blind separation of nonnegative sources. First, the available observation matrix is mapped to construct a new mixing model, in which the inaccessible source matrix is normalized to be column-sum-to-1. Then, the PP method is proposed to solve this new model, where the mixing matrix is estimated column by column through tracing the projections to the mapped observations in specified directions, which leads to the recovery of the sources. The proposed method is much faster than Chan's method, which has similar assumptions to ours, due to the usage of optimal projection. It is also more advantageous in separating cross-correlated sources than the independence- and uncorrelation-based methods, as it does not employ any statistical information of the sources. Furthermore, the new method does not require the mixing matrix to be nonnegative. Simulation results demonstrate the superior performance of our method.

CANonical polyadic DECOMPosition (CANDECOMP, CPD), also known as PARAllel FACtor analysis (PARAFAC) is widely applied to Nth-order (N ≥ 3) tensor analysis. Existing CPD methods mainly use alternating least squares iterations and hence need to unfold tensors to each of their N modes frequently, which is one major performance bottleneck for large-scale data, especially when the order N is large. To overcome this problem, in this paper, we propose a new CPD method in which the CPD of a high-order tensor (i.e., N > 3) is realized by applying CPD to a mode reduced one (typically, third-order tensor) followed by a Khatri-Rao product projection procedure. This way is not only quite efficient as frequently unfolding to N modes is avoided, but also promising to conquer the bottleneck problem caused by high collinearity of components. We show that, under mild conditions, any Nth-order CPD can be converted to an equivalent third-order one but without destroying essential uniqueness, and theoretically they simply give consistent results. Besides, once the CPD of any unfolded lower order tensor is essentially unique, it is also true for the CPD of the original higher order tensor. Error bounds of truncated CPD are also analyzed in the presence of noise. Simulations show that, compared with state-of-the-art CPD methods, the proposed method is more efficient and is able to escape from local solutions more easily.

Previous cooperative sensing schemes require the cooperative Secondary Users (SUs) to behave in a synchronous way. This requires each SU to start cooperations at the same time by stopping their own transmissions. In multi-hop cognitive radio networks, it is very difficult to keep all SUs synchronized with others for sensing. In this paper, we propose an asynchronous cooperative sensing scheme for multi-hop cognitive radio networks in which each SU only provides its energy information in stead of ceasing its own transmission to perform the cooperative sensing. Each energy information is assigned an appropriate weight by considering the temporal and spatial diversities of each SU. We formulate the probabilities of detection and false alarm as optimization problems to find the optimal weight for every energy information. The achievable throughput has been derived. Numerical results show that the proposed scheme is able to achieve substantially higher throughput compared with the existing schemes.

In cognitive radio networks, spectrum sensing and access scheme affects the system performance. In this paper, a new wideband mixed access scheme is proposed, in which the Secondary Users (SUs) sense the channels via wideband spectrum sensing, and access them with a mixed access strategy. In order to maximize the ergodic throughput of SUs, we find optimal sensing time and transmission power of each channel, while protecting the Primary Users (PUs) from interference. It is shown that the optimization problem can be formulated as a convex problem. Moreover, we present a QoS-aware low complexity scheme, in which the SUs select several specific channels to sense. An effective sensing channels selection criterion is proposed. Numerical results show that the proposed schemes can effectively improve the system performance.

Block-sparse reconstruction, which arises from the reconstruction of block-sparse signals in structured compressed sensing, is generally considered difficult to solve due to the mixed-norm structure. In this letter, we propose an algorithm for reconstructing block-sparse signals, that is an extension of fixed point continuation in block-wise case by incorporating block coordinate descent technique. We also apply our algorithm to multiple measurement vector reconstruction, that is a special case of block-sparse reconstruction and can be used in magnetic resonance imaging reconstruction. Numerical results show the validity of our algorithm for both synthetic and real-world data.

Active contour models (ACMs) integrated with various kinds of external force fields to pull the contours to the exact boundaries have shown their powerful abilities in object segmentation. However, local minimum problems still exist within these models, particularly the vector field's "equilibrium issues." Different from traditional ACMs, within this paper, the task of object segmentation is achieved in a novel manner by the Poincaré map method in a defined vector field in view of dynamical systems. An interpolated swirling and attracting flow (ISAF) vector field is first generated for the observed image. Then, the states on the limit cycles of the ISAF are located by the convergence of Newton-Raphson sequences on the given Poincaré sections. Meanwhile, the periods of limit cycles are determined. Consequently, the objects' boundaries are represented by integral equations with the corresponding converged states and periods. Experiments and comparisons with some traditional external force field methods are done to exhibit the superiority of the proposed method in cases of complex concave boundary segmentation, multiple-object segmentation, and initialization flexibility. In addition, it is more computationally efficient than traditional ACMs by solving the problem in some lower dimensional subspace without using level-set methods.

This paper presents a new time-frequency (TF) underdetermined blind source separation approach based on Wigner-Ville distribution (WVD) and Khatri-Rao product to separate N non-stationary sources from M(M <; N) mixtures. First, an improved method is proposed for estimating the mixing matrix, where the negative value of the auto WVD of the sources is fully considered. Then after extracting all the auto-term TF points, the auto WVD value of the sources at every auto-term TF point can be found out exactly with the proposed approach no matter how many active sources there are as long as N ≤ 2M-1. Further discussion about the extraction of auto-term TF points is made and finally the numerical simulation results are presented to show the superiority of the proposed algorithm by comparing it with the existing ones.

The problem of nonnegative blind source separation (NBSS) is addressed in this paper, where both the sources and the mixing matrix are nonnegative. Because many real-world signals are sparse, we deal with NBSS by sparse component analysis. First, a determinant-based sparseness measure, named D-measure, is introduced to gauge the temporal and spatial sparseness of signals. Based on this measure, a new NBSS model is derived, and an iterative sparseness maximization (ISM) approach is proposed to solve this model. In the ISM approach, the NBSS problem can be cast into row-to-row optimizations with respect to the unmixing matrix, and then the quadratic programming (QP) technique is used to optimize each row. Furthermore, we analyze the source identifiability and the computational complexity of the proposed ISM-QP method. The new method requires relatively weak conditions on the sources and the mixing matrix, has high computational efficiency, and is easy to implement. Simulation results demonstrate the effectiveness of our method.

Nonnegative matrix factorization (NMF) is a widely used method for blind spectral unmixing (SU), which aims at obtaining the endmembers and corresponding fractional abundances, knowing only the collected mixing spectral data. It is noted that the abundance may be sparse (i.e., the endmembers may be with sparse distributions) and sparse NMF tends to lead to a unique result, so it is intuitive and meaningful to constrain NMF with sparseness for solving SU. However, due to the abundance sum-to-one constraint in SU, the traditional sparseness measured by L0/L1-norm is not an effective constraint any more. A novel measure (termed as S-measure) of sparseness using higher order norms of the signal vector is proposed in this paper. It features the physical significance. By using the S-measure constraint (SMC), a gradient-based sparse NMF algorithm (termed as NMF-SMC) is proposed for solving the SU problem, where the learning rate is adaptively selected, and the endmembers and abundances are simultaneously estimated. In the proposed NMF-SMC, there is no pure index assumption and no need to know the exact sparseness degree of the abundance in prior. Yet, it does not require the preprocessing of dimension reduction in which some useful information may be lost. Experiments based on synthetic mixtures and real-world images collected by AVIRIS and HYDICE sensors are performed to evaluate the validity of the proposed method.

Nonnegative matrix factorization (NMF) is an unsupervised learning method useful in various applications including image processing and semantic analysis of documents. This paper focuses on symmetric NMF (SNMF), which is a special case of NMF decomposition. Three parallel multiplicative update algorithms using level 3 basic linear algebra subprograms directly are developed for this problem. First, by minimizing the Euclidean distance, a multiplicative update algorithm is proposed, and its convergence under mild conditions is proved. Based on it, we further propose another two fast parallel methods: α-SNMF and β -SNMF algorithms. All of them are easy to implement. These algorithms are applied to probabilistic clustering. We demonstrate their effectiveness for facial image clustering, document categorization, and pattern clustering in gene expression.

Nonnegative matrix factorization (NMF) with minimum-volume-constraint (MVC) is exploited in this paper. Our results show that MVC can actually improve the sparseness of the results of NMF. This sparseness is L(0)-norm oriented and can give desirable results even in very weak sparseness situations, thereby leading to the significantly enhanced ability of learning parts of NMF. The close relation between NMF, sparse NMF, and the MVC_NMF is discussed first. Then two algorithms are proposed to solve the MVC_NMF model. One is called quadratic programming_MVC_NMF (QP_MVC_NMF) which is based on quadratic programming and the other is called negative glow_MVC_NMF (NG_MVC_NMF) because it uses multiplicative updates incorporating natural gradient ingeniously. The QP_MVC_NMF algorithm is quite efficient for small-scale problems and the NG_MVC_NMF algorithm is more suitable for large-scale problems. Simulations show the efficiency and validity of the proposed methods in applications of blind source separation and human face images analysis.

In blind source separation, many methods have been proposed to estimate the mixing matrix by exploiting sparsity. However, they often need to know the source number a priori, which is very inconvenient in practice. In this paper, a new method, namely nonlinear projection and column masking (NPCM), is proposed to estimate the mixing matrix. A major advantage of NPCM is that it does not need any knowledge of the source number. In NPCM, the objective function is based on a nonlinear projection and its maxima just correspond to the columns of the mixing matrix. Thus a column can be estimated first by locating a maximum and then deflated by a masking operation. This procedure is repeated until the evaluation of the objective function decreases to zero dramatically. Thus the mixing matrix and the number of sources are estimated simultaneously. Because the masking procedure may result in some small and useless local maxima, particle swarm optimization (PSO) is introduced to optimize the objective function. Feasibility and efficiency of PSO are also discussed. Comparative experimental results show the efficiency of NPCM, especially in the cases where the number of sources is unknown and the sources are relatively less sparse.

Online blind source separation (BSS) is proposed to overcome the high computational cost problem, which limits the practical applications of traditional batch BSS algorithms. However, the existing online BSS methods are mainly used to separate independent or uncorrelated sources. Recently, nonnegative matrix factorization (NMF) shows great potential to separate the correlative sources, where some constraints are often imposed to overcome the non-uniqueness of the factorization. In this paper, an incremental NMF with volume constraint is derived and utilized for solving online BSS. The volume constraint to the mixing matrix enhances the identifiability of the sources, while the incremental learning mode reduces the computational cost. The proposed method takes advantage of the natural gradient based multiplication updating rule, and it performs especially well in the recovery of dependent sources. Simulations in BSS for dual-energy X-ray images, online encrypted speech signals, and high correlative face images show the validity of the proposed method.

Sensor nodes in Cognitive Sensor Networks (CSNs) can work on different frequency bands (or channels) according to dynamically available wireless resources. This paper proposes a spectrum-aware routing scheme for CSNs, which jointly considers traffic balance, route configuration and power control for reliable end-to-end communications. Bayesian learning method is used to estimate the number of neighboring Primary Users (PUs) and Secondary Users (SUs). The estimated results effectively reflect the spectrum utilization and provide important information for route configuration. Multiple Attribute Decision Making (MADM) method is employed to combine the routing objectives of reliability, energy efficiency and path delay into a single target function. Randomized route selection strategy is adopted for traffic balance. The simulation results demonstrate that the proposed spectrum-aware routing scheme significantly improves the communication reliability, and simultaneously has satisfying performances in energy efficiency and end-to-end delay.

In Cognitive Radio (CR) networks, spectrum sensing is a crucial technique to discover spectrum opportunities for the Secondary Users (SUs). The Quality-of-Service (QoS) of spectrum sensing is characterized by both sensing accuracy and sensing efficiency. Here, sensing accuracy is represented by the false alarm probability and the detection probability while sensing efficiency is represented by the metrics sensing overhead and throughput. The literature has mainly focused on improving sensing accuracy while sensing efficiency has been largely ignored. In this paper, we propose a group-based cooperative Medium Access Control (MAC) protocol, which concentrates on improving sensing efficiency without degrading spectrum sensing accuracy. The MAC protocol is specified and implemented in three phases: reservation, sensing and transmission. The protocol incorporates a group-based cooperative spectrum sensing scheme. In particular, the cooperative SUs are grouped into several teams. During a sensing period, each team senses a different channel. As a consequence, multiple distinct channels can be simultaneously detected within one sensing period. Then, we formulate throughput maximization problems in both time-invariant and time-varying channel scenarios to determine the key design parameters. In addition, an SU-selecting algorithm is presented to selectively choose the cooperative SUs based on the channel dynamics and usage patterns in order to substantially reduce sensing overhead. Numerical results indicate that the proposed strategy is able to significantly decrease sensing overhead and increase throughput with guaranteed sensing accuracy.

Recently, there has been a growing interest in multiway probabilistic clustering. Some efficient algorithms have been developed for this problem. However, not much attention has been paid on how to detect the number of clusters for the general n-way clustering (n ≥ 2). To fill this gap, this problem is investigated based on n-way algebraic theory in this paper. A simple, yet efficient, detection method is proposed by eigenvalue decomposition (EVD), which is easy to implement. We justify this method. In addition, its effectiveness is demonstrated by the experiments on both simulated and real-world data sets.

Blind source separation (BSS) has been widely discussed in many real applications. Recently, under the assumption that both of the sources and the mixing matrix are nonnegative, Wang develop an amazing BSS method by using volume maximization. However, the algorithm that they have proposed can guarantee the nonnegativities of the sources only, but cannot obtain a nonnegative mixing matrix necessarily. In this letter, by introducing additional constraints, a method for fully nonnegative constrained iterative volume maximization (FNCIVM) is proposed. The result is with more interpretation, while the algorithm is based on solving a single linear programming problem. Numerical experiments with synthetic signals and real-world images are performed, which show the effectiveness of the proposed method.

A coarse-to-fine boundary location with a self-organizing map (SOM)-like method is proposed in this paper. Inspired from the conventional SOM and universal gravitation, given a small quantity of supervision seeds from the desired boundaries, neurons are used to evolve to the desired boundaries in a coarse-to-fine framework. The major components of this framework are the designs of union action and evolving rate. In the course of neuron evolution, the union actions acting on these neurons will offer them the evolving directions. Also controlled by the corresponding referenced gradients, the neurons' evolving rates are adaptively adjusted at different positions. With the union actions and evolving rates, the neurons will evolve with appropriate manners to expand the set of feature points on the desired boundaries. The newly expanded feature points will cause the generation updates for feature points and neurons, and offer new information to guide the new generation of neurons to the boundaries. What is more, the proposed multiround evolution is as well a coarse-to-fine way for boundary location. Experiments and comparisons show that the proposed method performs well in complex long concavities, inhomogeneous and weak boundary location with good initialization flexibility.

This letter discusses blind separability based on temporal predictability (Stone, 2001 ; Xie, He, & Fu, 2005 ). Our results show that the sources are separable using the temporal predictability method if and only if they have different temporal structures (i.e., autocorrelations). Consequently, the applicability and limitations of the temporal predictability method are clarified. In addition, instead of using generalized eigendecomposition, we suggest using joint approximate diagonalization algorithms to improve the robustness of the method. A new criterion is presented to evaluate the separation results. Numerical simulations are performed to demonstrate the validity of the theoretical results.

A novel method to reconstruct object boundaries with geodesic circular arc is proposed in this paper. Within this framework, an energy of circular arc spline is utilized to simultaneously arrange and interpolate each member in the set of sparse unorganized feature points from the desired boundaries. A general form for a family of parametric circular arc spline is firstly derived and followed by a novel method of arranging these feature points by minimizing an energy term depending on the circular arc spline configuration defined on these feature points. With regard to the fact that the energy function is usually nonconvex and nondifferentiable at its critical points, an improved scheme of particle swarm optimizer is given to find the minimum for the energy in this paper. With this improved scheme, each pair of neighboring feature points along the boundaries of the desired objects are picked out from the set of sparse unorganized feature points, and the corresponding directional chord tangent angles are computed simultaneously to finish interpolation. We show experimentally and comparatively that the proposed method can perform effectively to restrict leakage on weak boundaries and premature convergence on long concave boundaries. Besides, it has good noise robustness and can as well extract multiple and open boundaries.

To make the results reasonable, existing joint diagonalization algorithms have imposed a variety of constraints on diagonalizers. Actually, those constraints can be imposed uniformly by minimizing the condition number of diagonalizers. Motivated by this, the approximate joint diagonalization problem is reviewed as a multiobjective optimization problem for the first time. Based on this, a new algorithm for nonorthogonal joint diagonalization is developed. The new algorithm yields diagonalizers which not only minimize the diagonalization error but also have as small condition numbers as possible. Meanwhile, degenerate solutions are avoided strictly. Besides, the new algorithm imposes few restrictions on the target set of matrices to be diagonalized, which makes it widely applicable. Primary results on convergence are presented and we also show that, for exactly jointly diagonalizable sets, no local minima exist and the solutions are unique under mild conditions. Extensive numerical simulations illustrate the performance of the algorithm and provide comparison with other leading diagonalization methods. The practical use of our algorithm is shown for blind source separation (BSS) problems, especially when ill-conditioned mixing matrices are involved.

Ant colony optimization (ACO) is an optimization algorithm inspired by the natural behavior of ant species that ants deposit pheromone on the ground for foraging. In this paper, ACO is introduced to tackle the image edge detection problem. The proposed ACO-based edge detection approach is able to establish a pheromone matrix that represents the edge information presented at each pixel position of the image, according to the movements of a number of ants which are dispatched to move on the image. Furthermore, the movements of these ants are driven by the local variation of the image’s intensity values. Experimental results are provided to demonstrate the superior performance of the proposed approach.

This paper discusses the source recovery step in two-stage blind separation algorithm of underdetermined mixtures. A statistically non-sparse decomposition principle of two mixtures (2d-SNSDP), which is an extension of the SSDP algorithm about two mixtures, is proposed. It overcomes the disadvantage of the SSDP algorithm and sparse representation based on l1-norm. Compared with traditional sparse methods, it is non-sparse method, that is, almost all the recovered sources in any instant t are non-zero. Finally, several stereo audio signals experiments demonstrate its performance and practical.

This paper studies the blind identification problem for multiple-input multiple-output (MIMO) FIR channels, in which the source signals are modulated by high order periodic precoders. A set of new design criteria of the periodic precoders is proposed from the channel blind identification viewpoint for multiuser channels. It is shown that, due to the fact that high order periodic precoders are used in the modelling problem, certain simple orthogonality among user’s signals can be introduced by a set of proper designed periodic precoders. This results in a simple blind identification algorithm and the impulse response of every subchannel can also be determined uniquely up to a unitary scalar based on the received signals’ second order statistics (SOS) and a priori information of the periodic precoders. Simulation results illustrate that the developed blind identification algorithm is efficient.

Overcomplete representations have greater robustness in noise environment and also have greater flexibility in matching structure in the data. Lewicki and Sejnowski (2000) proposed an efficient extended natural gradient for learning the overcomplete basis and developed an overcomplete representation approach. However, they derived their gradient by many approximations, and their proof is very complicated. To give a stronger theoretical basis, we provide a brief and more rigorous mathematical proof for this gradient in this note. In addition, we propose a more robust constrained Lewicki-Sejnowski gradient.

This paper discusses the estimation and numerical calculation of the probability that the 0-norm and 1-norm solutions of underdetermined linear equations are equivalent in the case of sparse representation. First, we define the sparsity degree of a signal. Two equivalence probability estimates are obtained when the entries of the 0-norm solution have different sparsity degrees. One is for the case in which the basis matrix is given or estimated, and the other is for the case in which the basis matrix is random. However, the computational burden to calculate these probabilities increases exponentially as the number of columns of the basis matrix increases. This computational complexity problem can be avoided through a sampling method. Next, we analyze the sparsity degree of mixtures and establish the relationship between the equivalence probability and the sparsity degree of the mixtures. This relationship can be used to analyze the performance of blind source separation (BSS). Furthermore, we extend the equivalence probability estimates to the small noise case. Finally, we illustrate how to use these theoretical results to guarantee a satisfactory performance in underdetermined BSS.

Convolutive blind source separation (CBSS) that exploits the sparsity of source signals in the frequency domain is addressed in this paper. We assume the sources follow complex Laplacian-like distribution for complex random variable, in which the real part and imaginary part of complex-valued source signals are not necessarily independent. Based on the maximum a posteriori (MAP) criterion, we propose a novel natural gradient method for complex sparse representation. Moreover, a new CBSS method is further developed based on complex sparse representation. The developed CBSS algorithm works in the frequency domain. Here, we assume that the source signals are sufficiently sparse in the frequency domain. If the sources are sufficiently sparse in the frequency domain and the filter length of mixing channels is relatively small and can be estimated, we can even achieve underdetermined CBSS. We illustrate the validity and performance of the proposed learning algorithm by several simulation examples.

Objective quality assessment has been widely used in image processing for decades and many researchers have been studying the objective quality assessment method based on Human Visual System (HVS). Recently the Structural Similarity (SSIM) is proposed, under the assumption that the HVS is highly adapted for extracting structural information from a scene, and simulation results have proved that it is better than PSNR (or MSE). By deeply studying the SSIM, we find it fails in measuring the badly blurred images. Based on this, we develop an improved method which is called Edge-based Structural Similarity (ESSIM). Experiment results show that ESSIM is more consistent with HVS than SSIM and PSNR especially for the blurred images.

Objective quality assessment has been widely used in image processing for decades and many researchers have been studying the objective quality assessment method based on human visual system (HVS). Recently the structural similarity (SSIM) is proposed, under the assumption that the HVS is highly adapted for extracting structural information from a scene, and simulation results have proved that it is better than PSNR (or MSE), By deeply studying the SSIM, we find it fails in measuring the badly blurred images. Based on this, we develop an improved method which is called gradient-based structural similarity (GSSIM). Experiment results show that GSSIM is more consistent with HVS than SSIM and PSNR especially for blurred images.

Combining the modelling technique for signal with the unscented transform (UT), a new filtering algorithm is realized. It indicates by computer simulation that this new algorithm can effectively reduce noise on chaotic signal no matter how parameter of chaos generator varies with time. In comparison with the EKF algorithm, this algorithm has a better filtering performance in the case of low signal to noise (SNR), and has the similar performance in the case of high SNR. In addition, an application in blind channel equalization is also found.

This article introduces a new image quality assessment: QNIF (quality assessment based on noise influencing force). Considering uneven property of noise distribution, we put forward the concept of noise influencing significance area. Analyzing noise in significance area coverage is to identify the property that noise destructiveness on image structure can approach to human visual system. In addition, in view of human eyes' physiological characteristics of gaze and fast jump, QNIF also includes noise area influencing image quality. Test result shows that QNIF performance is evidently superior to traditional MSE because it can effectively estimate different types of quality reduction.

One of the major drawbacks in block-based discrete cosine transform (BDCT) is the blocking artifacts at low bit rates. In this paper, an adaptive deblocking algorithm based on Markov random field (MRF) is proposed. A visibility function of blocking artifacts is introduced which based on human visual system (HVS), together with edge information to construct a new adaptive potential function of MRF. The experiment results show that the proposed algorithm reduces the blocking artifacts effectively and preserves the original edges faithful

In H.264 I-frame encoder, the best infra prediction modes are chosen by utilizing the rate-distortion (R-D) optimization whose distortion is the sum of the squared differences (SSD, means the same as MSE) between the reconstructed and the original blocks. Recently a new image measurement called structural similarity (SSIM) based on the degradation of structural information was brought forward. It is proved that the SSIM can provide a better approximation to the perceived image distortion than the currently used PSNR (or MSE). In this paper, we propose two improved prediction modes selection methods based on SSIM for H.264 I-frame encoder. The first one is the SSIM-based R-D optimization (SBRDO) method, the other is the fast mode selection method based on SSIM (FMSBS). Experiments show that both the proposed method can improve the coding efficiency while maintaining the same perceptual reconstructed image quality.

Stone's method is one of the novel approaches to the blind source separation (BSS) problem and is based on Stone's conjecture. However, this conjecture has not been proved. We present a simple simulation to demonstrate that Stone's conjecture is incorrect. We then modify Stone's conjecture and prove this modified conjecture as a theorem, which can be used a basis for BSS algorithms.

Through an analysis and comparison of the algorithm proposed by Hyvarinen-Oja (1996), we present an approach of blind separation based on the penalty functions with multipliers. The approach gives the method to select the penalty function and speeds up the convergence of the algorithm. It avoids the ill-posed problem that may be caused by the pure penalty functions. Also, we propose a new simple method of deflation. The simulations show the good effectiveness of our algorithm. The separation time of our algorithm is shorter than the one proposed by Hyvarinen-Oja (1996) by 30%.

This paper discusses adaptive filtering algorithms and proposes a fast algorithm based on vector plots analysis, that is different from the previous adaptive filtering algorithms. By introducing approaches of mathematical geometrical analysis to study adaptive filtering, the paper inquires into vector plots structure of least mean squares (LMS) algorithm and geometrical feature of algorithm convergence and seeks effective fast algorithm on the basis of geometrical analysis. Numerical simulations are given to show the efficiency and superiority of the new algorithm.

In this paper, a new algorithm of iterative learning control with forgetting factor is proposed by using a new norm and a new analysis method. The new method applies the whole information of systems to transfer the iterative learning control problem into a stability problem of a discrete system with parameters. This algorithm improves the shortage appeared in some present learning algorithms with forgetting factors. The simulations show the effectiveness of our new algorithm.

In this paper, a new fuzzy logic-based image quality assessment approach is presented. The proposed method assumes that an image is composed of edge, texture and smooth regions. Then three different quality measures are defined and applied to their respective regions according to several fuzzy inference rules. Experimental results show that the proposed method performs better than some other methods, such as MSE, traditional block distortion measure.

A new error concealment algorithm based on average motion vector (AVMV) method is proposed as a post-processing tool at the decoder side for recovering the lost blocks and their motion vectors as well incurred during the video transmission. In our proposed scheme, LOG operator is used to detect the texture of the blocks around the lost block and find the more precise estimation of the motion vectors, so as to improve the AVMV method. Simulation results show that the proposed method can recover the higher quality image in different rates of lost block, comparing to the existing traditional concealment algorithms.