Accurate emotion recognition of Intelligent Connected Vehicles (ICV) drivers plays a crucial role in mitigating driving risks caused by emotional fluctuations, thereby enhancing road safety and improving driving experiences. Current approaches predominantly suffer from two critical limitations, reliance on single-modality emotional data analysis and neglect of individual personality differences that significantly influence emotional manifestations. To address these challenges, this paper proposes a Personality-aware Multimodal Emotion Recognition Network (PMERNet) that synergistically integrates psychological theory with multimodal learning. Specifically, we first design an end-edge collaborative architecture that optimizes resource allocation between vehicle terminals and roadside units (RSUs), enabling efficient multimodal data collection (end-side) and collaborative feature processing (edge-side). Second, we develop a Weighted Temporal Background Attention module (WTBA-VExt) for robust facial expression analysis and implement a cross-modal self-attention Transformer for explicit multimodal feature fusion. Third, incorporating the psychological Big Five personality theory, we propose a Multimodal Big Five Personality Extractor (Multi-BFPExt) to capture latent personality traits and establish a bidirectional cross-modal fusion mechanism for personality-enhanced emotion recognition. Comprehensive experiments demonstrate that PMERNet achieves statistically significant improvements over existing state-of-the-art methods, reaching superior performance in both accuracy and weighted F1-score. Notably, the weighted F1-score is enhanced by 1.16%.

While multi-device cooperative task-oriented semantic communication (TOSC) enhances task performance through comprehensive information representation, it inevitably introduces redundancy, thereby increasing communication overhead. Existing redundancy elimination methods suffer from limitations in interpretability and coarse granularity, hindering the optimal utilization of communication resources. To this end, we propose a disentangled information bottleneck guided TOSC framework (DisenIB-TOSC). The framework first employs the basic IB for initial feature compression, then formulates a novel DisenIB specifically designed for multi-device cooperation inference, which enhances task performance and achieves interpretable feature disentanglement by separating features into common and private components, thereby establishing a theoretical foundation for redundancy identification. Subsequently, we derive differentiable, computationally tractable forms for both IB objectives by combining variational approximation, consistency constraints, and density ratio trick. Leveraging the disentangled features, we further design a feature importance-aware selective transmission strategy, DisenIB-TOSC-ST, which quantifies feature importance via mutual information estimation to dynamically discriminate and control redundant feature transmission. Experimental results on several tasks demonstrate that our method outperforms baselines in task performance while reducing communication costs, verifying the effectiveness and interpretability of feature disentanglement.

There exists a tremendous amount of multimodal data in the Internet of Medical Things (IoMT), including medical texts and corresponding images. Retrieval technology can extract target data on demand from the extensive multimodal medical data space, which is crucial for aiding diagnosis and medical informatization. However, existing methods only focus on single-modal data such as medical texts, without considering the privacy protection and retrieval needs of users' multimodal data in the IoMT. Furthermore, these existing methods only match keywords and fail to effectively mine the semantic features of multimodal data, thereby limiting the performance of retrieval systems. To address these issues, this paper proposes a multimodal encrypted retrieval method for the IoMT based on semantic feature fusion and designs a multimodal semantic feature extraction model based on searchable encryption technology to enable encrypted retrieval of multimodal data. Specifically, an edge-cloud collaboration concept is introduced to underpin a secure semantic search architecture tailored for multimodal data, which ensures low-latency encrypted retrieval while safeguarding user privacy. Besides, a semantic-aware multimodal feature extraction method is designed, enhancing the capability of mining semantic features and replacing the traditional keyword retrieval mode with semantic feature retrieval. Moreover, a multimodal data encrypted retrieval method is proposed, employing a block idea and parallel search tree structure, which achieves rapid retrieval of semantic similarity with low-cost and privacy-preserving. Simulation results demonstrate that the proposed method significantly outperforms the latest research regarding precision, search delay, and storage overhead.

Intelligent search enables users to access information from the Internet quickly, but existing schemes fail to achieve accurate semantic awareness and reliable information transmission, especially in constrained communication conditions, which degrade search accuracy and personalized user experience. To address these challenges, we propose a multiuser semantic communication system to perform personalized search (PS) tasks, named MU-SemCom-PS. In particular, the system introduces a novel semantic encoder at the transmitter to deeply extract user-specific search semantics by analyzing search history from multiple perspectives, and designs a semantic decoder at the receiver to recover and enhance search semantics by leveraging implicit correlations among users, thus the PS tasks are performed based on the recovered search semantics. To optimize the PS tasks for all users, the federated learning (FL) framework is leveraged to jointly train the MU-SemCom-PS system through knowledge collaboration and sharing. Experimental results show that the proposed scheme significantly improves search accuracy and robustness under constrained communication conditions.

High mobility and nonindependent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle’s data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms.

Aspect-Based Multimodal Sentiment Analysis (ABMSA) aims to infer the users’ sentiment polarities over individual aspects using visual, textual, and acoustic signals. Although psychological studies have shown that personality has a direct impact on people's sentiment orientations, most existing methods disregard the potential personality character while executing ABMSA tasks. To tackle this issue, a novel psychological perspective, the people's personalities are introduced. To the best of our knowledge, this paper is the very first study in this field. Different from current pipelined multi-task sentiment analysis methods, an end-to-end ABMSA method called Personality-coupled mUlti-task leaRning framEwork (PURE) is proposed, which strongly couples personality mining and ABMSA tasks in a unified architecture to avoid error propagation and enhance the overall system robustness. Specifically, an adaptive personality feature extraction method is designed to accurately model the first impression of different people's personalities. Then, a multi-task ABMSA framework is designed to strongly couple the multimodal features of aspects extracted by the interactive attention fusion network with people's personalities. Subsequently, the proposed framework optimizes them parallel via extended Bayesian meta-learning. Finally, compared to the current optimal model, the classification accuracy and macro F1 score of the proposed model have both shown significant improvements on public datasets. In addition, PURE is transferable and can effectively couple personality modeling tasks with any other sentiment analysis methods.

Low earth orbit satellite Internet of Things (LEO-SIoT) can provide services such as remote control for IoT devices in mountainous regions and oceans. In LEO-SIoT, time-sensitive applications such as natural disaster warnings and wildlife tracking often require the remote control center to receive the latest status updates from IoT devices in real-time. However, due to the long signal propagation distance and severe constraints on satellite computing resources, LEO-SIoT fails to meet the high information freshness requirements of time-sensitive applications. It is crucial to efficiently allocate resources in LEO-SIoT to improve its information freshness. To address this issue, firstly, a LEO-SIoT architecture for cloud-edge-end collaborative task processing is proposed by employing edge intelligence (EI) technology. Then, the introduction of peak age of information (PAoI) as the metric for the information freshness in the LEO-SIoT is followed by the proposal of a freshness-fairness-aware scheduling strategy. Moreover, an optimization model is developed under the terminal energy constraint with the objective of minimizing the average PAoI. A information freshness optimal resource allocation algorithm, utilizing convex optimization and search algorithm, is proposed to minimize the average PAoI in the LEO-SIoT. Experiments and results demonstrate that the proposed resource allocation algorithm and task scheduling strategy effectively improve information freshness and freshness fairness.

Targeted sentiment analysis aims to identify the sentiment polarity of specific target mentions in a sentence. Existing methods employ neural networks to extract the relations between target mentions and their contexts. Recent approaches based on graph convolutional networks can model the syntactic relations extracted by an external parser into adjacency matrices. However, online reviews are informal and complex, the syntactic structures provided by the parser can be incorrect in these syntax-insensitive scenarios. To remedy this defect, we design a novel integrated syntactic and semantic tree (IS2tree) by labeling semantic relations between the target mention and contexts in a syntactic dependency tree. Furthermore, a dual-channel graph convolutional network (DCGCN) is proposed to encode the contextual information associated with the target mention by dynamic semantic pruning mechanisms and to also retain the syntactic relations. Experimental results demonstrate that the IS2tree has a favorable generalization capability comparing to the state-of-the-art baselines on four public datasets.

The significant heterogeneity of data resources in Internet of Medical Things (IoM$T$) devices profoundly affects the efficacy of federated learning (FL) when training medical models. Personalized Federated Learning (pFL) not only facilitates the extraction of shared priors from a vast array of distributed data in medical diagnostics but also underpins the development of bespoke models for heterogeneous medical devices. However, existing personalized federated learning methods have problems with insufficient personalization and poor convergence in medical data.To address this issue, we propose an Enhanced Personalized Federated Learning (EPFL) method, designed specifically for heterogeneous IoMT federated learning. Considering the diverse knowledge characteristics of model parameters, we introduce the concept of frequency domain analysis to deeply scrutinize the composition of model parameters. This approach enables us to accurately distinguish between shared and personalized features within the medical model. Moreover, we leverage the principles of knowledge transfer and cooperative gaming to achieve person-alized effects in medical models. We have conducted extensive experiments using various datasets in medical scenarios charac-terized by heterogeneous data. The results clearly demonstrate that, in comparison to current state-of-the-art benchmarks, EPFL achieves superior personalized accuracy for each medical device.

The sharing of medical data nowadays plays a pivotal role in advancing medical research, fostering innovation, enhancing clinical decision-making, improving healthcare quality, and propelling public health monitoring and personalized medicine development. Its significance in the field of medicine cannot be overstated. However, medical data encompasses a wealth of sensitive information pertaining to patients, possessing highly pronounced privacy characteristics. Consequently, while promoting the sharing of medical data, privacy protection must be accorded paramount importance. Existing approaches pre-dominantly focus on hierarchical categorization from the user side, aiming to achieve user-level differentiation, yet disregarding the diversity inherent in data sources. Moreover, these approaches suffer from excessive computational complexity. To address these issues, this paper presents a lightweight bidirectional differential privacy protection method tailored for privacy-sensitive data in Medical Internet of Things (MIoT). It encompasses the design of a protection architecture that combines symmetric encryption and attribute fusion, incorporating the principles of differential privacy protection. A lightweight attribute-based encryption scheme is devised to cater to differentiated user requirements, ensuring data encryption while simultaneously reducing computational overhead and storage space consumption. Additionally, a fine grained privacy protection method, targeting the distinctive characteristics of differentiated data, is introduced to facilitate granular privacy protection for individual sensitive data, ensuring that only authorized personnel can access, utilize, and process the corresponding data. Simulation experiments validate that this proposed approach significantly mitigates computational complexity and communication overhead while demonstrating enhanced data availability.

Demand-oriented data service can provide the physical entity information for Internet of Things (IoT) users conveniently and quickly. The traditional cloud-oriented data service architecture has been inapplicable to the state time-varying and privacy-sensitive entity data in IoT due to long response delay and the risk of privacy leakage for the entities and users, respectively. The edge-based architecture lacks global service function although it can alleviate problems with cloud services. Moreover, existing demand-oriented data service ignores the characteristics of “thousands of people have thousands of faces” and the implicit intents of users, which results in limited service quality and weak user experience. To solve the above problems, a personalized secure demand-oriented data service scheme is proposed. Specifically, an edge-cloud collaborative architecture is designed to realize privacy-preserving, timely response, and personalized search combining the advantages of edge and cloud. To achieve the personalized service for IoT users, a time span fused personalized ranking method (TSFPR) is proposed to deeply perceive individual demands via mining user preferences with temporal evolution characteristics. Finally, an edge-cloud collaborative personalized secure data service approach (ECPSS) oriented different search modes is presented to achieve encryption data matching and personalized reranking, thereby improving the service quality of the IoT system synthetically. Security analysis and simulation demonstrate the effectiveness of the proposed method in terms of privacy preserving, data service time, and personalized performance.

The metaverse aims to build an immersive virtual reality world to support the daily life, work, and recreation of people. In this survey, the status quo of the metaverse is investigated, and the technical framework of the metaverse is introduced from three aspects: 1) the generation of virtual worlds; 2) the connection of virtual and real objects; and 3) the transmission of data. Specifically, this survey first discusses the development and challenges of the related technologies for virtual world generation methods from three aspects: 1) the 3-D world generation; 2) immersive human–computer interaction experience; and 3) ecosystem. Second, we investigate the status quo of extended reality (XR), motion capture, and brain–computer interface technologies and evaluate the potential and research directions of these entrance technologies for the metaverse. Finally, network and data transmission technologies for the metaverse are reviewed from the Internet of Things (IoT), 5G/6G wireless, and edge computing aspects, the demand side of the metaverse in virtual-reality interpromotion, big data processing, and low-latency networking is discussed, and promising research hotspots are identified.

The high-speed movement of nodes and the burstiness of interactions in the Internet of Vehicles pose huge challenges to the trusted vehicle collaboration and data sharing. Aiming at the disadvantages of existing authentication mechanisms and trust management models for connected vehicles, this article proposes a trust management model enabled by blockchain to ensure the traceability, nontampering, unforgeability, and transparency of vehicular interactions. The proposed trust management model leverages Dirichlet distribution, reputation regression, and revocation punishment to objectively and accurately reflect the trust status of vehicles. Simulation results on real-world data sets show that the proposed trust management model advantageously improves the accuracy of malicious vehicle detection and the attack resistance of connected vehicles.

Federated learning (FL) is a distributed machine learning paradigm that ensures data do not leave local devices. Data sharing problems can be addressed by FL in untrusted environments, e.g., the Internet of Vehicles (IoV). However, FL needs to frequently exchange massive parameters to achieve preset model goals. In addition, the change in bandwidths and the delay of data communications due to user mobility challenge the synchronization of model parameters. In this article, an efficient hierarchical asynchronous FL (EHAFL) algorithm is proposed to adjust the encoding length dynamically according to the bandwidth and reduce the communication cost substantially. A dynamic hierarchical asynchronous aggregation mechanism is proposed leveraging gradient sparsification and asynchronous aggregation techniques to further reduce the communication costs and improve the aggregation efficiency of the global model. Simulation results on MNIST and real-world data sets show that our proposed solution can reduce the communication costs by 98% while only compromising the model accuracy by 1%.

Limited by the storage and computing capacity of Internet of Things (IoT) devices, outsourcing encrypted entity data has become a prevalent trend. The existing IoT entity search methods lack the integration and utilization of both edge and cloud resources and the protection of user privacy. Besides, the traditional searchable encryption mode is inapplicable to state-time-varying entities in IoT. Therefore, in this article, an edge–cloud collaborative entity search method with privacy protection in IoT is proposed, fusing the advantages of edge and cloud resources to fulfill users’ needs for real-time search and privacy protection. Specifically, a secure search architecture and search method for edge–cloud collaboration is designed to support various needs of users, such as real-time search and global search. Then, an adaptive discrimination method for similar interested entities through attribute analysis and feature extraction is proposed to construct attribute-distinguished encrypted index and query vector groups, enabling efficient entity search meanwhile ensuring fast index update. Simulation results demonstrate that the proposed method with privacy protection can effectively improve the efficiency of entity search in IoT while safeguarding user privacy.

Caching AI of Things (AIoT) data at the edge can reduce the load on cloud centers while providing real-time services for AIoT users. Existing static caching strategies based on popularity prediction fail to meet users’ demands for time-varying entity data, while dynamic caching strategies focus only on evaluating the time-varying state characteristics of entity data, but ignore the differences in popularity among entities, resulting in poor service experience. To this end, a device–edge collaborative differentiated data caching strategy considering static entity popularity as well as dynamic system state is proposed. First, a hot entity recognition method centered on user interests is designed to achieve individual preference estimation by mining users’ long short-term interests, and then achieve group interest prediction based on social computing. Based on this, a dynamic caching optimization method is designed, which considers the timeliness of entity data and communication cost of the system to design the objective function of optimal cache decision and then solve it based on reinforcement learning. Simulation results demonstrate that the proposed caching strategy achieves better performance than other benchmark strategies in terms of cache hit rate and search cost.

Wearing masks can effectively inhibit the spread and damage of COVID-19. A device-edge-cloud collaborative recognition architecture is designed in this paper, and our proposed device-edge-cloud collaborative recognition acceleration method can make full use of the geographically widespread computing resources of devices, edge servers, and cloud clusters. First, we establish a hierarchical collaborative occluded face recognition model, including a lightweight occluded face detection module and a feature-enhanced elastic margin face recognition module, to achieve the accurate localization and precise recognition of occluded faces. Second, considering the responsiveness of occluded face detection services, a context-aware acceleration method is devised for collaborative occluded face recognition to minimize the service delay. Experimental results show that compared with state-of-the-art recognition models, the proposed acceleration method leveraging device-edge-cloud collaborations can effectively reduce the recognition delay by 16% while retaining the equivalent recognition accuracy.

In Industrial Internet application scenarios, due to the ubiquitous connection requirements of the massive Internet of Things (IoT) devices in the edge layer. The data transmission rate is reduced, and the transmission delay increases, increasing the transmission energy consumption per bit. So a low-energy transmission strategy based on real-time edge layer traffic sensing is proposed. First, a mixed-integer modeling method for low-energy transmission of the IoT is proposed. This method aims to optimize the overall energy consumption of the system. The low-energy transmission task of the IoT is modeled as a mixed-integer linear programming problem. Second, a traffic prediction method for the estimation of the number of access packets is designed. Solve the problem of fog access point (F-AP) state change caused by the real-time change of network load. Finally, an energy-driven mapping strategy is designed. The transmission task can be dynamically mapped to the appropriate F-AP. The simulation results show that the strategy proposed in this article can effectively reduce the transmission energy consumption of IoT devices and the overall energy consumption of the system in the massive device access scenario.

Targeted sentiment analysis aims to predict the sentiment polarity of the target in a sentence. Most traditional Graph Neural Network-based methods have focused only on the syntactic dependency information of sentences. However, they ignore the position information of words in the linear form of sentences, which leads the model to paying attention to the irrelevant syntactic dependency information to the target. To attenuate the irrelevant information, a novel model called Position-aware Dual Relational Graph Attention Network (PDRGAT) is proposed. Firstly, introducing the position-aware weight window of the syntactic dependency information to make the model pay more attention to the local syntactic information of words that neighbor the target. Secondly, a dual relational attention mechanism combining syntactic and position information is proposed. Experiments show that our model can effectively attenuate the irrelevant syntactic information and outperform state-of-the-art baselines on Accuracy and Macro-F1.

The flexible combination of pervasive portable smart devices and omnipresent high-speed access infrastructures has revolutionized the data sensing and knowledge acquisition in mobile crowdsensing (MCS), underpinning fine-grained city management and highly customizable Internet service applications. However, MCS applications are still confronted with unsolved challenges, such as task assignment, privacy risks, and misbehavior detection. In light of this, this article proposes PETA, a privacy-preserving edge task assignment framework for MCS, leveraging the powerful edge servers deployed between users and the platform to cluster and manage users according to user attributes. Furthermore, group signature is employed by PETA to anonymize and verify user identities for privacy-preserving task assignments. The theoretical analysis and simulation results validate the performance of PETA on identity anonymity, malicious user detection, and task completion rate.

With the tremendous growth of traffic demand caused by the conventional service and emerging Internet-of-Things (IoT) applications, it is vitally challenging to support seamlessly access for billions of IoT devices along with existing Internet service. Fiber-Wireless (FiWi) access networks is an ideal solution for the next-generation access networks to support both IoT and conventional service. One of the main challenges faced by the design of an FiWi access network is the high energy consumption due to low utilization of optical network units (ONUs) and high control overhead of data transmission. In this article, An adaptive frame aggregation scheme with load transfer is proposed to reduce the energy consumption in FiWi. By evaluating the quality of wireless channel, the proposed scheme adaptively adjusts the length of the aggregated frame to reduce the energy consumption caused by the frequent preemption of wireless channel and the numerous retransmission of data frames resulted by poor channel quality. In the optical backhaul, according to the delay requirements of services with different priorities, the proposed scheme calculates the optimal frame length for each queue and performs load transfer among ONUs to dynamically distribute network load and maximize the sleep rate of ONUs for energy saving. Simulation results and theoretical analysis both unanimously show that the proposed scheme achieves significant amounts of energy saving, while preserving delay performance of various services.

In mobile crowd sensing (MCS), the cloud as a single sensing platform undertakes a large number of communication tasks, leading to the reduction of sensing task execution efficiency and the risk of loss and leakage of users’ private data. In this paper, we propose a spatial ciphertext aggregation scheme with collaborative verification of fog nodes. Firstly, the cloud and fog collaboration architecture is constructed. Fog nodes are introduced for data validation and slices transmission, reducing computing cost on the sensing platform. Secondly, a multipath transmission method of slice data is proposed, in which the user identity and data are transmitted anonymously by the secret sharing method, and the data integrity is guaranteed by hash chain authentication. Finally, a spatial data aggregation method based on privacy protection is presented. The ciphertext aggregation calculation of the sensing platform is realized through Paillier homomorphic encryption, and the problem of insufficient data coverage in the sensing region is solved by the position-based weight interpolation method. The security analysis demonstrates that the scheme can achieve the expected security goal. The simulation results show the feasibility and effectiveness of the proposed scheme.

Caching state data of real-world entities just in the cloud without any distinction will cause search performance degrading, due to the characteristics of uncountable number of entities and time-varying state of entities in cyber-physical systems (CPSs). Considering the diverse time-varying features of CPS entities, an edge-cloud collaborative entity state data caching strategy toward networking search application in CPSs is proposed in this article. Specifically, an entity state feature extraction method is presented to mine underlying changing rules of CPS entities via raw entity state observation sequence. Then, an edge and cloud collaborative entity state data caching strategy is devised to improve the search accuracy of CPSs search service and reduce the search delay and energy consumption, in which entities are clustered first according to the time-varying degree of their state and then these state information are discriminately cached based on their belonging clusters. Simulation results validate the effectiveness of the proposed strategy in terms of real-time and accuracy performances.

Intermittently connected wireless networks (ICWNs) have been studied in recent years to solve the disruption problem in mobile ad hoc networks and improve the utilization of temporary links raised by node movements. In ICWNs, the packet storing-carrying-forwarding principle is adopted through the cooperation between multiple nodes. Therefore, it is critical to include the connection status of nodes in designing efficient packet forwarding mechanism. In this paper, a node service ability aware packet forwarding mechanism is proposed based on the connection status. First, the connection model is established to analyze the transition of connection status; moreover, the service ability can be evaluated according to the connection strength and connection availability. Second, packet forwarding levels are determined based on their transmitting status to exploit the limited buffer resources. Consequently, the efficient packet forwarding mechanism can guarantee the flexibility of packet transmission in both complex and dynamic network scenarios. Numerical results show that about 20% delivery ratio increase can be achieved by the proposed mechanism, while the overheads and latency are reduced.