The Mixture-of-Experts (MoE) architecture has emerged as a key enabler for scaling large language models (LLMs), empowering increased model capacity with minimal computational overhead through gating-based dynamic expert activation. However, due to the memory demands introduced by expert modules, MoE inference on resource-constrained devices is still challenging. Existing methods such as model compression and parameter offloading provide partial alleviation but often lead to reduced accuracy or increased latency. In this paper, we propose CasMoE, a general and efficient cascaded framework for accelerating MoE inference on resource-constrained devices. CasMoE employs a two-stage offline-online approach to facilitate efficient expert prefetching. In the offline stage, a parameterized Expert Activation Predictor (EAP) is introduced to accurately predict the corresponding expert activation from the incoming prompt. In the online stage, a non-parametric Expert Activation Matcher (EAM) supporting fast expert retrieval is then integrated with the EAP to form a cascade planner that operates independently of the MoE architecture, predicting activated experts for all MoE layers in a single pass prior to decoding. A gating mechanism is also incorporated to dynamically adjust the sensitivity of the EAM and EAP, enabling a flexible trade-off between inference efficiency and quality. Extensive experiments on diverse downstream tasks demonstrate CasMoE’s effectiveness in accelerating inference while preserving high accuracy.

Autonomous vehicles face perception challenges due to occlusions, limited sensor ranges, and adverse weather. Vehicle-to-Everything (V2X) cooperative perception mitigates these limitations by enabling vehicles to share sensor data. However, existing methods rely on supervised learning, requiring costly manual 3D annotations, exhibiting limited generalization, and employing static fusion strategies that fail under communication disruptions. We propose V2X-JEPA, a self-supervised framework that extends the joint-embedding predictive architecture (JEPA) to V2X cooperative perception for both Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure scenarios. V2X-JEPA learns semantic representations via latent embedding prediction, eliminating the need for manual annotations during pretraining. We introduce three cooperative masking strategies and grid spatial attention fusion, which adapt to communication quality and agent reliability. Extensive evaluation on OPV2V and DAIR-V2X benchmarks shows that V2X-JEPA reduces annotation requirements by 85% while achieving competitive performance. On OPV2V (LiDAR, V2V), V2X-JEPA achieves 94.5% [email protected] and 89.2% [email protected]. On DAIR-V2X (camera, V2I), it achieves 24.8% [email protected] and 11.2% [email protected]. It outperforms V2X-ViT by 4.7%, CoCa3D by 2.2%, and CooPre by 2.8%. V2X-JEPA is efficient, with 98M parameters and 78-ms inference time, and demonstrates high robustness, degrading only 5.1% under 20% packet loss, supporting practical deployment in bandwidth-constrained environments.

The vast geographic coverage and sparse customer distribution in rural areas lead to inefficiency in traditional last-mile delivery. Truck-drone collaborative delivery systems have emerged as a promising solution to these rural logistics challenges. Accordingly, we introduce a multi-truck multi-drone collaborative delivery framework. Within this framework, we propose a novel graph embedding module—the edge-gated graph attention network (EG-GAT)—which incorporates multi-dimensional edge features into the attention mechanism and introduces a learnable gating module for adaptive multi-head fusion. We further propose a graded flexible time window mechanism, which permits limited service advancement or deferral while applying graded incentive-penalty structures. This approach better captures the temporal flexibility inherent in rural customer service requirements. The resulting multi-objective truck-drone routing problem is modeled as a rewardmaximization task and solved using multi-agent proximal policy optimization (MAPPO) under a centralized-training with decentralized-execution framework. Extensive experimental results demonstrate that the proposed method outperforms other approaches. Furthermore, studies assess the individual effects of graded flexible time window settings and objective function weight coefficients on the optimization performance of collaborative delivery. Finally, we evaluate the practical advantages of our proposed model using real-world rural road cases.

Memristor-based Hopfield neural networks (MHNNs) exhibit rich chaotic dynamics and bear closer hardware resemblance to the biological brain, making them well suited for emulating neural dynamical behaviors. However, most existing MHNNs are constructed with first-order memristors. This paper proposes a novel second-order memristor (SOM) approach for constructing MHNNs with enriched chaotic dynamics. Specifically, a second-order memristor is incorporated into a three-neuron Hopfield neural network to emulate the magnetic coupling mechanism between neurons, thereby forming a second-order memristor-based neural network (SOM-HNN). Comprehensive dynamical analyses, including bifurcation diagrams, Lyapunov exponent spectra, and numerical simulations, confirm that the proposed SOM-HNN exhibits richer and more intricate chaos behaviors than its first-order counterparts. Remarkably, the proposed SOM-HNN can simultaneously generate butterfly and scroll attractors, multi-butterfly and multi-scroll attractors, as well as initial-boosed coexisting multi-butterfly and multi-scroll attractors, thereby substantially enhancing its dynamical diversity. To the best of our knowledge, this is the first report of both multi-butterfly and multi-scroll dynamics in a neural network. Furthermore, the SOM-HNN is implemented in hardware using analog circuits and a digital field-programmable gate array (FPGA) platform. Experimental results demonstrate the network’s abundant dynamical features and its feasibility for efficient hardware realization in neuromorphic engineering applications.

The intelligent development of high-speed railways (HSRs) necessitates support for various services to ensure safe and reliable train operations while providing high-quality travel experiences for passengers. Network slicing presents a promising solution via isolated and service-specific radio resource management. However, meeting heterogeneous quality of service (QoS) requirements in HSR communications is particularly challenging due to imperfect channel state information (CSI) caused by high-speed mobility. In this work, we investigate a slicing puncture strategy in a moving network with an imperfect train-to-ground downlink, supporting passenger entertainment and safety-related services. The system includes two transmission links: outboard and inboard. Given the impact of high-speed mobility, we characterize the statistical probability distribution of the actual CSI and model the average transmission rates in the outboard link. We aim to minimize the system Resource Block (RB) and power in the above two links while satisfying the diverse QoS requirements of services. Since the resource minimization problem is a mixed-integer nonlinear programming, we decompose it into three subproblems: RB allocation, power allocation, and slicing puncture optimization. A Speed-Aware Resource allocation and Slicing puncture (SA-RS) algorithm is proposed. Specifically, analytical expressions are derived for RB allocation, and a bisection-based algorithm is designed for power allocation. Moreover, the slicing puncture strategy is obtained using a genetic-based algorithm. Simulation results demonstrate that the proposed strategy can improve the system performance compared with other baseline schemes under imperfect CSI.

Collaborative content dissemination enables vehicles to directly access content from surrounding nodes through Vehicle-to-Everything (V2X) technologies, such as Vehicle-to-Vehicle (V2V) or Vehicle-to-Infrastructure (V2I) communication. This approach significantly alleviates the downlink traffic burden on cellular network base stations caused by repeated downloading of popular content while addressing security challenges in electric vehicle (EV) charging operations, such as payment fraud and data tampering. A key yet unresolved challenge in content dissemination and EV charging is incentivizing vehicles to participate in collaborative processes voluntarily. Existing incentive mechanisms mainly rely on centralized architectures, which are vulnerable to single-point attacks and trust issues in third-party platforms. To overcome these limitations, we propose the PCD-DB (Popular Content Dissemination using DAG-based Blockchain) scheme, which uses a Directed Acyclic Graph (DAG)-based blockchain to incentivize V2X collaboration for dual applications: improving content dissemination efficiency and ensuring secure EV charging transactions. Our novel framework establishes a decentralized incentive system where vehicles act as content propagators or charging service providers, depending on their service capabilities. We define the propagation and charging capabilities of vehicles and use contract theory to design hierarchical contracts tailored to heterogeneous vehicle roles. Numerical results show that our decentralized incentive mechanism significantly improves the efficiency and profitability of vehicle content dissemination while ensuring the security of electric vehicle charging transactions, outperforming existing benchmark methods.

The inevitable trade-off between perceptual performance and communication bandwidth in collaborative perception poses a significant challenge. To mitigate this constraint, we introduceHAFNet, a hybrid-stage collaborative perception method designed for multi-agent collaborative 3D object detection. This method initially generates dense proposal, serving as the Region of Interest (RoI). Next, all proposals are aggregated through the proposed Agent-Foreground List via RoI association. Moreover, secondary sampling is performed according to those foreground regions. Furthermore, we achieve superior feature extraction through geometric and offset encoding. Concurrently, the setting of proxy points effectively reduces the size of the collective perception messages. In the end, those features are fused and interacted to get the detection. Extensive experiments on existing DAIR-V2X and V2V4Real datasets illustrate thatHAFNetalmost keeps a minimum communication bandwidth, while it surpasses existing state-of-the-art methods in 3D object detection tasks.

Deep learning-based joint source-channel coding (DeepJSCC) has shown significant benefits in emerging semantic and task-oriented communications, providing a promising solution for reducing latency and bandwidth requirements in next-generation mobile networks. However, its deployment on resource-constrained devices is limited by model complexity. Devices with varying computational capacities require models of distinct architectures and complexity levels, motivating the design of a cross-architecture model compression scheme for DeepJSCC. In this paper, we propose a cross-architecture knowledge distillation framework called CAKDJSCC for heterogeneous DeepJSCC models. Specifically, we design a teaching assistant network with feature fusion modules (FFMs) that dynamically perceive architecture gaps between teacher and student models, thereby generating student-adaptive feature representations to alleviate feature space misalignment caused by architectural inconsistencies. In addition, we introduce a conditional information bottleneck (CIB) loss to optimize the distillation process, which prevents students from overfitting to teacher-specific inductive biases while enhancing knowledge transfer efficiency in cross-architecture scenarios. Extensive experiments demonstrate that our approach significantly improves the student model's reconstruction accuracy and perceptual quality without increasing the inference latency while minimizing the performance degradation during model compression.

Mobile Crowdsensing (MCS) is a new data acquisition method that has emerged with the proliferation of smart mobile devices. With the expanding scale of urban sensing, the locations of tasks and users become critical information, which plays a significant role in crowd-sensing and task scheduling areas. Tasks in areas with a high concentration of users can be completed quickly, whereas tasks in sparsely populated areas are challenging to accomplish. To address this issue, existing research has primarily focused on task assignment to designated users, assuming that users' motivations are rational, while neglecting the impact of psychological factors on their motivations. Therefore, we propose an incentive mechanism based on prospect theory, analyzing the decisions users might make under irrationality and then adjusting corresponding rewards to influence user decisions. This paper transforms the problem of maximizing the data value in crowdsensing into an ordered submodular function model. Our proposed incentive mechanism consists of three components: User Decision-Making, User Selection, and Payment Determination. In the User Decision-Making phase, users calculate the prospect value based on the auction results from the previous round to make decisions. In the User Selection phase, users are chosen based on marginal value. In the Payment Determination phase, rewards for winning users are designed based on the ordered submodular model. The platform provides auction results as a reference for the next round. In the experimental section, we demonstrate that the incentive mechanism can enhance the platform's value.

In recent years, Deep Joint Source-Channel Coding (DeepJSCC) has demonstrated superior performance over traditional digital schemes in wireless image transmission tasks. However, existing DeepJSCC approaches often overlook three critical challenges in broadcast communication scenarios: bandwidth heterogeneity among users, dynamic bandwidth variations experienced by individual users, and users diverse requirements. To address these issues, we propose a scalable DeepJSCC framework tailored for broadcast communications. This framework enables users to adaptively intercept an appropriate amount of encoded data according to their bandwidth conditions or specific requirements, thereby reconstructing images with corresponding quality. Specifically, the transmitter generates a multi-layered codestream, consisting of multiple base layers for image reconstruction at different resolutions, as well as enhancement layers built upon each base layer to improve visual quality. At the receiver, users can selectively intercept the base layer stream corresponding to their desired resolution, and further receive parts of the associated enhancement layer stream. This design allows for flexible and quality-adaptive image reconstruction based on the amount of data received. Extensive experiments demonstrate that the proposed scheme consistently achieves high-quality reconstruction across various resolutions and under diverse interception conditions.

The intelligent development of high-speed railways (HSRs) necessitates the support of multiple services to ensure the safe and reliable operations of trains, and high-quality travel experiences for passengers. Network slicing offers a promising solution through isolated and service-specific radio resource management. However, meeting heterogeneous quality of service (QoS) requirements in HSR communications with imperfect channel state information (CSI) presents a great challenge. In this paper, we propose a bandwidth allocation and slicing puncture strategy in a train-to-ground moving network to support safetyrelated driver assistance services (DAS) and high-throughput video-on-demand services (VDS) for passengers. We formulate the resource slicing problem to minimize system resource block allocation, considering the throughput constraint of VDS and the latency and jitter constraints of VDS. The original problem is divided into two subproblems: VDS RB allocation and DAS puncturing. For VDS RB allocation, we transform the subproblem into a convex form and derive a closed-form expression. For DAS puncturing, a Genetic-based mini-slots puncturing (GMP) algorithm is proposed to address the non-convexity. Simulation results demonstrate the effectiveness of the proposed block coordinate descent-based RB allocation and puncturing (BCDAP) algorithm under imperfect CSI conditions, outperforming the baseline schemes.

With growing interest in secure storage, decentralized storage systems (DSSs) have attracted attention due to their strong data integrity but remain limited by restricted capacity, low efficiency, and weak security guarantees. These shortcomings make existing DSSs unsuitable as practical file storage platforms, particularly in private cloud scenarios where performance bottlenecks are easily exposed. To address this, we present Haina Storage (HNS), a decentralized storage system redesigned for scalability, efficiency, and security in private clouds. HNS introduces a bi-directional circular linked chain structure in which each file forms an independent chain, eliminating inter-file dependencies and enabling parallel retrieval. We further propose a lightweight consensus mechanism, Proof of Resources, that accounts for both storage capacity and network conditions, ensuring fair and timely data placement. Security is strengthened through dynamic access control, confidential block distribution, and decentralized key protection without trusted third parties. Extensive experiments on both public cloud servers and local clusters demonstrate that HNS achieves performance comparable to IPFS while offering significantly stronger security, theoretical scalability advantages, and an efficient and fair resource-based consensus mechanism. All prototype code11https://github.com/Zijian-Zhou/Haina_Storage and experimental modules22https://github.com/Zijian-Zhou/Haina_Storage_Exp are open-sourced, and a demonstration video33https://youtu.be/2b8JMqvZV60 is available online.

Cooperative perception in autonomous driving enhances situational awareness by leveraging Vehicle-to-Everything (V2X) communication to share multi-modal sensor data. Despite its potential, challenges such as bandwidth limitations, computational constraints, and data heterogeneity hinder its adoption. This paper introduces Omni-V2X, a vision-language framework that provides real-time, actionable scene descriptions by integrating multi-view images and driving context. Omni-V2X employs spatially-aware cross-view attention and parameter-efficient processing, enabling practical deployment on in-vehicle edge computing units. The framework generates concise insights for navigation and decision-making, such as object detection and obstacle awareness, while addressing resource constraints. Experimental evaluations on the DAIR-V2X-C dataset highlight its capability, achieving ROUGE 55.3, BLEU 42.8, and Average Precision 72.4 with low latency. The modular architecture promotes scalability and future compatibility with LiDAR and additional modalities, contributing to robust and context-aware cooperative perception in dynamic driving scenarios.

Dynamic novel view synthesis (NVS) aims to render time-varying scenes from arbitrary viewpoints, balancing rendering quality and computational efficiency. While recent 4D Gaussian Splatting approaches offer promising real-time performance, they fundamentally overlook critical interdependence between Gaussians by modeling deformations independently. Our information-theoretic analysis reveals substantial mutual information across the Gaussian field, manifesting as appearance-preserving radiance coherence and motion-consistent deformation propagation. This finding establishes that rendering quality emerges from coordinated transformation rather than independent processing. We propose Correlation-aware Dynamic Gaussian Splatting (CaDGS) with our novel Gaussian Correlation Tensor Projection (GCTP) method, which efficiently transforms the complex O(n3) mutual information tensor into a dual-channel O(n2) spatial matrix, preserving the critical topological structure of Gaussian interactions. Combined with our Spatio-Temporal Deformation Consistency (STDC) learning, which enforces volumetric coherence through tensor-guided regularization across multiple scales, CaDGS prevents geometric distortions and texture inconsistencies common in previous approaches. Experimental results demonstrate state-of-the-art performance, achieving 32.4 PSNR on the Neu3D dataset with fewer Gaussians while maintaining rendering speeds of 323 FPS at 1353 × 1014 resolution.

ABSTRACT Recent 3D point cloud classification has predominantly focused on local spatial attention, neglecting distant contextual relationships due to the inherent sparsity of LiDAR‐generated data over longer distances. Existing 3D object detection methods prioritize local features, hindering the extraction of semantic information. Despite attempts with transformers, methods often reduce computations through local spatial attention, neglecting content class and scarcely establishing connections among distant global points. Our proposed point class‐adaptive transformer (PCaT) addresses these limitations by establishing long‐range feature dependencies while significantly reducing computations. PCaT includes three key modules: the class‐adaptive transformer (CaT), which utilizes local self‐attention and global self‐attention based on class similarity to facilitate an efficient trade‐off between capturing extended‐global dependencies and managing computational challenges; nested binary clustering (NbC), which dynamically partitions queries into multiple clusters based on content features in each Transformer block; and the AfA, which aggregates high‐dimensional features using max‐pooling alongside a residual MLP component and low‐dimensional features using average pooling and a CaT block. Additionally, PCaT incorporates point cloud segmentation via local–global feature aggregation (PcSeg) to facilitate effective point cloud segmentation. Extensive experimentation on the ModelNet40, ScanObjectNN, and S3DIS datasets demonstrates the superior performance and reasonable stability of PCaT compared with existing methods. PCaT achieves 94.2% overall accuracy (OA) and mIoU scores of 89.2% and 86.2% for the ScanObjectNN and S3DIS datasets, respectively.

Copyright protection of depth image-based rendering (DIBR) videos has raised significant concerns due to their increasing popularity. Zero-watermarking, emerging as a powerful tool to protect the copyright of DIBR 3D videos, mainly relies on traditional feature extraction methods, thus necessitating improvements in robustness against complex geometric attacks and its ability to strike a balance between robustness and distinguishability. This paper presents a novel zero-watermarking scheme based on cross-modality feature fusion within a contrastive learning framework. Our approach integrates complementary information from 2D frames and depth maps using a cross-modality attention feature fusion mechanism to obtain discriminative features. Moreover, our features achieve a better trade-off between robustness and distinguishability by leveraging a designed contrastive learning strategy with an adversarial distortion simulator. Experimental results demonstrate our remarkable performance by reducing the false negative rates to around 0.2% when the false positive rate is equal to 0.5%, which is superior to the state-of-the-art zero-watermarking methods. • Use contrastive learning to balance watermarking robustness and distinguishability. • Employ an adversarial distortion simulator to enhance robustness against various attacks. • Design cross-modality fusion mechanism to achieve better feature representation.

Recently, federated learning (FL) has attracted much attention as a promising decentralized machine learning method that provides privacy and low latency. However, the communication bottleneck is still a problem that needs to be solved to effectively deploy FL on wireless networks. In this article, we aim to minimize the total convergence time of FL by sparsifying and quantizing local model parameters before uplink transmission. More specifically, we first present the convergence analysis of the FL algorithm with random sparsification and quantization, revealing the impact of compression error on the convergence speed. Then, we jointly optimize the computation, communication resources and the number of quantization bits, sparsity to minimize the total convergence time, subject to the energy and compression error requirements derived from the convergence analysis. By simulating the impact of different compression errors on model accuracy, we reveal that the low-precision updates do not inherently yield a better balance between efficiency and accuracy than the high-precision updates. Furthermore, compared with the equal resource allocation schemes and the unilateral compression optimization schemes on four different data distributions, the proposed scheme has faster convergence speed and less total convergence time.

The deployment of Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surfaces (STAR-RIS) has proven to be an effective means to extend coverage and improve wireless signal quality. STAR-RIS in wireless networks for aided Unmanned Aerial Vehicle (UAV) communications enables a significant boost in network capacity and the provision of virtual line-of-sight links to efficiently meet the quality-of-service (QoS) requirements of user equipment (UE). Accordingly, this paper proposes a novel STAR-RIS-aided multi-UAV communication framework to exploit energy efficiency and total throughput maximally. We formulate the long-term optimization problem as a decentralized, partially observed Markov decision process (DEC-POMDP). Then, we formulate the discrete association scheduling problem as a non-cooperative theoretical game and propose the UA-CFG algorithm to realize the UE association scheme that converges to a Nash equilibrium (NE). Then, a multi-agent reinforcement learning (MARL) method with well-established robustness is devised to continuously optimize the trajectories and energetic consumption of UAVs through centralized training and distributed implementation. Experimental results reveal that the performance of the proposed algorithm is considerable compared to other traditional schemes.

Through Internet of Things (IoT) communication technology, collaborative perception enhances a vehicle’s capacity to discern its surroundings while driving by integrating and synchronizing sensor data from multiple agents. With the advancement of cooperative perception techniques in single-modality methods, there has been a growing trend toward integrating multimodal data from heterogeneous sensors in recent years. However, due to the data heterogeneity inherent in diverse sensors, Bird’s Eye View (BEV) maps generated from different types of sensors may exhibit local discrepancies in the spatial representation of entity positions. Furthermore, individual agents may produce uncertain and flawed feature representations in real noisy environments. The influence of this indeterminacy exacerbates the issue of local inconsistency, leading to misalignment of the detected target during BEV alignment and fusion, thereby reducing detection accuracy. To address these problems, we propose a modal decision-making spatial alignment cooperative perception network (MDNet). First, the network generates BEV feature maps through dense depth image supervision for voxel feature extraction and model-guided selective feature fusion. Subsequently, we achieve enhanced accuracy in object detection by performing spatial alignment of BEV representations generated from two distinct sensors, both globally and locally within the spatial domain. Besides, we employ a cascaded centralized pyramid strategy during the message fusion stage, facilitating flexible sampling across horizontal and vertical spatial dimensions, promoting deep interaction among multiple agents. We conduct quantitative and qualitative experiments on the public OPV2V and DAIR-V2X-C benchmarks, and our proposed MDNet exhibits superior performance and stronger robustness in the 3-D object detection task, providing more precise target detection results.

Networks in the 5G and beyond era can use software-defined networks (SDN) to achieve network slicing (NS), so as to meet the extremely diverse service requirements of diverse applications in the Internet of Vehicles (IoV). However, the flow fluctuations in the highly dynamic IoV make it difficult to provide reliable, flexible, and scalable services for the IoV by the SDN control plane. Careful SDN controller placement can be a feasible solution to achieve its robustness and flexibility to deal with the changes in network status. Thus, this paper studies a dynamic controller placement problem to improve the performance of IoV services. To be specific, a hierarchical SDN control plane for the IoV is considered with the SDN controllers placed at the edge of networks. Under this architecture, we model the dynamic controller placement by Markov Decision Process (MDP). To efficiently solve the formulated NP-hard problems, we develop an algorithm based on Deep Deterministic Policy Gradient (DDPG) because of its advantages in solving the problem with multi-dimensional action and large solution space. Further, we incorporate a random process into the action selection strategy of DDPG to prevent it from getting trapped in local optimum. Simulation results show that the proposed DDPG-based controller placement approach can adapt to a highly dynamic IoV environment with outstanding performance.

Mobile Edge Computing (MEC) can accelerate computation-intensive applications and emerge as a promising technology for enabling Internet of Things (IoT). MEC improves the processing performance of tasks by assigning them to the edge nodes. However, with massive terminals contending for computation and communication resources simultaneously, how to develop a flexible computational offloading mechanism becomes the fundamental issue of MEC-enabled IoT systems. This paper aims to develop an effective computational offloading decision scheme by jointly considering the computational resource and diverse user demands with two goals, i.e., minimizing both the latency and the energy consumption. Specifically, we develop a two-stage computational offloading mechanism, where the computational resources and offloading decisions can be allocated and coordinated with the variation of computation requirements. To achieve the two goals, this work introduces an edge node recommendation model within the cloud-edge-end architecture to reduce the offloading optimization search space. Furthermore, we propose a new computational offloading (CROCA) algorithm based on Chemical Reaction Optimization (CRO) for optimizing offloading utility, which thoroughly considers the competition between mobile device requests and computational resources. Extensive evaluation results demonstrate that the proposed CROCA scheme can effectively improve the computational offloading performance.

The rapid proliferation of IoT technologies intensifies network anomaly detection challenges because of high-dimensional and redundant data. To address this issue, we propose causal gray wolf optimization (CGWO), a framework that integrates the global search capabilities of gray wolf optimization (GWO) with causal inference to distinguish causal features from spurious correlations. CGWO employs a four-stage process: (1) data preprocessing with causal weight transformation, (2) causal analysis via potential outcome models (POMs), (3) feature subset optimization using a fitness function balancing accuracy and dimensionality, and (4) anomaly detection with an enhanced convolutional autoencoder (ECAE). By prioritizing causal relationships over statistical correlations, CGWO minimizes redundant features while increasing model interpretability. When evaluated with benchmark datasets (NSL-KDD and UNSW-NB15), CGWO achieves 99.8% accuracy (14 features) for 5-class classification with NSL-KDD and 94.2% accuracy (10 features) for 10-class classification with UNSW-NB15, outperforming conventional methods by more than 6%. The framework reduces feature dimensions by 65–80% without performance loss, demonstrating robustness, computational efficiency (120–150 s per dataset), and scalability for edge computing. These results validate the effectiveness of CGWO in balancing dimensionality reduction and interpretable model design for complex network environments.

It is difficult for existing Internet of Things (IoT) intrusion detection systems to simultaneously identify and classify network anomalies, especially when the classification of unknown attacks is required, which brings great risks to the use of IoT devices. This article applies transformers to decouple false associations by causal reasoning to obtain an intelligent interpretable IoT detection system that can classify known attacks and identify unknown attacks. To achieve these goals, a causal transformer-based intelligent detection system for IoT devices is proposed. The system is divided into three main modules. First, training is conducted based on known traffic types with prior knowledge, and then the detection samples containing unknown attack types are classified into known traffic types. Second, the causal feature distribution of known traffic types is learned based on causal attention, and the causal feature distribution differences between normal and abnormal traffic samples are amplified with the minimax strategy to distinguish their types. Then, all traffic samples different from the known types are integrated into unknown types for causal transformer classification until there is only one type. Validation is performed on three broad and representative IoT datasets, and the results show that the causal transformer detection system can not only correctly classify known attacks but also achieve a 100% success rate in identifying cyberattacks on IoT datasets. In addition, more than 99% of unknown attack types can be effectively identified and classified, providing timely and effective guidance for cybersecurity defense.

With the continuous development of Internet of Things (IoT) technology, an increasing number of devices are connected to the internet, generating large amounts of highdimensional redundant information. Moreover, significant environmental and device heterogeneity leads to nonindependent and identically distributed (N-IID) samples. These challenges compromise the stability and causal interpretability of existing IoT detection methods, limiting their effectiveness in providing actionable insights for network security defense. To address these limitations, we propose a causal interpretabilitydriven IoT abnormal traffic detection approach. Central to this method is the adoption of structural causal models (SCMs), which are chosen for their ability to explicitly model direct causal linkages, suppress confounding effects, ensure robust cross-deployment detection, and enable counterfactual reasoning for precise attack attribution. The approach first eliminates spurious feature associations via Fourier transformation, then constructs and prunes SCMs using causal effect analysis, KNN, and counterfactual diagnosis to restore genuine causal relationships between anomalies and traffic features. Experiments on CI-CIDS2019, ToNIoT, and NSL-KDD datasets demonstrate effective noise reduction, redundancy elimination, and causal relationship recovery. Notably, detection accuracy improves by >19% on NSL-KDD data under polluted conditions, while maintaining stability and providing clear causal explanations for IoT network anomalies.

With the advent of the sixth-generation (6G) wireless communications, transmission speeds are projected to exceed tenfold those of 5G, reaching theoretical peak download speeds of up to 1 Tbps. Data transmission capacity and speed will be significantly enhanced, enabling emerging applications, such as mixed reality, federated learning, and digital twins, driving exponential data traffic growth. To address this, the space-air–ground integrated network (SAGIN) combines satellite, aerial, and ground communication technologies, offering seamless global coverage and high-speed connectivity. In this article, we proposes an SAGIN framework integrated with mobile edge computing (MEC) to jointly optimize system energy consumption and delay costs. Specifically, we decompose the optimization problem into three subproblems: 1) uncrewed aerial vehicle (UAV) computational resource allocation; 2) satellite computational resource allocation; and 3) task offloading and channel allocation. The subproblems are then transformed and addressed using Newton’s interior point method and the deep reinforcement learning DQN algorithm to derive optimal allocation strategies for UAV and satellite computing resources, along with task offloading and channel resources, that our proposed algorithm effectively reduces system energy consumption and delay costs compared to other algorithms.

Memristors are often used to emulate neural synapses or to describe electromagnetic induction effects in neural networks. However, when these two things occur in one neuron concurrently, what dynamical behaviors could be generated in the neural network? Up to now, it has not been comprehensively studied in the literature. To this end, this article constructs a new memristive Hopfield neural network (HNN) by simultaneously introducing two memristors into one Hopfield-type neuron, in which one memristor is employed to mimic an autapse of the neuron and the other memristor is utilized to describe the electromagnetic induction effect. Dynamical behaviors related to the two memristive systems are investigated. Research results show that the constructed memristive HNN can generate the Lorenz-like double-wing and four-wing butterfly attractors by changing the parameters of the first memristive system. Under the simultaneous influence of the two memristive systems, the memristive HNN can generate complex multibutterfly chaotic attractors, including multidouble-wing-butterfly attractors and multifour-wing-butterfly attractors, and the number of butterflies contained in an attractor can be freely controlled by adjusting the control parameter of the second memristive system. Moreover, by switching the initial state of the second memristive system, the multibutterfly memristive HNN exhibits initial-boosted coexisting double-wing and four-wing butterfly attractors. Undoubtedly, such diversified butterfly attractors make the proposed memristive HNN more suitable for the chaos-based engineering applications. Finally, based on the multibutterfly memristive HNN, a novel privacy protection scheme in the Internet of Medical Things is designed. Its effectiveness is demonstrated through the encryption tests and hardware experiments.

Cloud gaming represents a major part of contemporary gaming. To boost the Quality-of-Experience (QoE) of cloud gaming, the integration of Dynamic Adaptive Video Encoding (DAVE) with Multi-access Edge Computing (MEC) has become the natural candidate owing to its flexibility and reliable transmission support for real-time interactions. However, as multiple gamers compete for limited resources to achieve personalized QoE, such as ultra-high video quality and ultra-low latency, how to support efficient edge resource optimization is a fundamental and important problem. Furthermore, determining the optimal game video encoding configuration in real-time poses significant challenges, especially when lacking the information on future video and edge network resources. To address these key issues, we jointly optimize the video encoding as well as computing and communication resource allocation by active mutual adaptation of video coding configurations and physical resources in a Software Defined Networking (SDN)-assisted edge network. This eliminates the performance bottleneck caused by decoupling optimization of coding parameter configuration and physical resource allocation. The SDN-assisted edge network architecture supports efficient on-demand resource management, provides global network information, and meets the stringent time-varying game requests. Due to the significant time scale difference between video chunk and physical resource block, we propose a novel Asynchronous Decision-Making Multi Agent Proximal Policy Optimization algorithm (AD-MAPPO), which can address the credit assignment problem with a single agent. It can also adapt to the highly dynamic cloud gaming environment without prior knowledge and a deterministic environmental model. Extensive experimentation based on real cloud gaming datasets convincingly demonstrates that our approach can significantly enhance the overall QoE of gamers.

With the ever-growing attention on communication security, machine learning-based network intrusion detection system (NIDS) is widely utilized to meet different security requirements. However, most of the existing methods manually extract or learn features from raw traffic, which is usually expensive, complicated, and time-consuming. Moreover, this also brings unprecedented challenges for preserving users’ privacy in the communication process, making it difficult for existing solutions to be deployed in practice due to the privacy requirements from legal policies. This paper proposes a privacy-preserving graph neural network (named NIGNN) for NIDS, which can encode the local structure and traffic features. To address the privacy issues pertaining to the application of graph representation learning, we design a privacy message-passing mechanism with formal privacy guarantees, in which sensitive information potentially contained in graph vertices will be kept private. Specifically, we design a privacy-enhancement graph representation that introduces a degree-sensitive item in vertex-based aggregation to reduce noise. Our theoretical analysis shows that NIGNN can provide a provable privacy guarantee. Extensive experiments demonstrate NIGNN's performance in maintaining a sound privacy-accuracy trade-off.

3D object detection by autonomous vehicles is integral to intelligent transportation. Existing systems often compromise essential foreground point features and local spatial interactions through random down-sampling, focusing primarily on local feature extraction. However, this neglects interactions among distant yet significant points, limiting semantic information and detection performance due to inherent point cloud data sparsity. Addressing this, our proposed Geometric Feature Aggregation and Self-Attention in a Multi-Head Transformer (GFA-SMT) architecture leverages Graph Convolutional Networks and multi-channel transformers to enhance weak semantic information of distant sparse objects. GFA-SMT comprises three modules: Distance Suppression for Local Receptive Fields (DsLRF), Geometric Feature Aggregator with Multi-head Self Attention (GFaSA), and Predicted Key-point Weighting and Refinement (PKwR). DsLRF preserves foreground features, GFaSA encodes similar features and aggregates edge features, while PKwR focuses on key-points for enhancing geometric knowledge of distant and sparse objects. Extensive experiments on KITTI, DIARV2X-I and NuScenes datasets show significant enhancements in widely used techniques, resulting in notable increases in average precision (AP) for 3D object detection: 4.08%, 5.56%, and 4.62%, respectively, on the KITTI test dataset. GFA-SMT enhances point cloud detection accuracy, particularly at medium and long distances, with minimal impact on run-time performance and model parameters.

The rapid evolution of the Internet-of-Vehicles (IoV) has amplified the need for mobile computing resources, driving the shift toward offloading tasks to edge servers or vehicles with idle resources to optimize computational efficiency. To this end, an approach based on Deep Reinforcement Learning (DRL) is presented in this paper, termed DVTP, which integrates Variational Graph Attention Networks (VGAT) and Transformer models to optimize Directed Acyclic Graph (DAG) task scheduling in vehicular networks. DVTP effectively captures both the spatiotemporal information and task dependencies, enabling more accurate and efficient task offloading decisions. Extensive simulation experiments demonstrate that DVTP outperforms traditional methods in reducing task completion times across various multi-vehicle and multi-edge server scenarios, showcasing its potential for real-world IoV applications.

Network-assisted full-duplex (NAFD) cell-free (CF) massive MIMO systems enable simultaneous uplink and downlink transmissions, where interference suppression and beamforming are critical for improving spectral efficiency and system performance. However, the asymmetric time-varying properties of current network traffic, coupled with the interference problems associated with complex network topologies, make existing resource allocation and interference management strategies difficult to handle, and unable to satisfy the low-latency, high-reliability Quality-of-Service (QoS) requirements of the growing number of terminal devices (TDs). To address these challenges, we propose a novel access method based on decoupled uplink-downlink multi-connectivity transmission to achieve flexible access selection and formulate an optimization problem that maximizes the cumulative fair spectral efficiency by simultaneously optimizing power allocation and link scheduling. To solve this mixed-integer nonlinear programming (MINLP) problem, we propose an optimized transfer scheme that reduces the dimensionality of the action and constraint spaces. Then, we characterize the network states as heterogeneous graph structures and employ node-level and metapath-level attention mechanisms for message passing and aggregation, and obtain graph-level scheduling policy via the heterogeneous graph neural network (HGNN). Finally, in light of the superior performance of Deep Reinforcement Learning (DRL) in exploration-based tasks, we design a holistic updating mechanism using environmental feedback and advantage state-action function, named as HGN-DRL for this end-to-end learning framework. Simulation results demonstrated the effectiveness and scalability of HGN-DRL in large-scale cell-free scenarios.

In Vehicular Edge Computing (VEC), a reasonable and efficient user association and resource allocation approach is a worthwhile research issue. However, most studies in Internet of Vehicles (IoV) only consider vehicle mobility and IoV communication. Therefore, we propose a user association and resource allocation strategy in Integrated Sensing and Communication (ISAC)-aided VEC. Compared with existing solutions, we consider constraints such as sensing and communication interference, vehicle mobility, Road Side Unit (RSU) sensing performance, and vehicle user quality of service (QoS). By quantifying the sensing and communication performance of RSUs, we construct a user association and resource allocation model with the optimisation objective of maximising the average sensing performance and communication performance of the system. Then, combining double dueling deep Q-network (D3QN) algorithm and twin delayed deep deterministic policy gradient (TD3) algorithm, we propose a DRL algorithm based on D3QN-TD3. We represent the user association and resource allocation problem as a Markov Decision Process (MDP) and solve it using the proposed algorithm to obtain the optimal user association, channel allocation, and power allocation strategies. Experimental results show that the proposed algorithm has better performance in terms of downlink transmission rate, radar sensing mutual information, system utility, and task completion rate.

Wireless train communication network (WLTCN) is an emerging technology for enabling intelligent rail vehicles. It is responsible for providing train control services (TCS), passenger information services (PIS), and train sensing services (TSS). These services within WLTCN have notably different quality of service (QoS) requirements from traditional telecommunication services. In this paper, to incorporate multiple services in a single WLTCN, we propose a radio access network (RAN) slicing architecture empowered WLTCN to satisfy the demands of services and save bandwidth resource. In particular, the service and slicing models of TCS, PIS, and TSS are investigated. By analyzing the heterogeneous characteristics and QoS requirements of the above services within WLTCN, we exploit the orthogonal multiple access scheme for TCS and PIS and the non-orthogonal multiple access scheme for TSS, respectively. The system bandwidth minimization problem is formulated with slicing resource allocation for TCS, PIS, and TSS and non-orthogonal access grouping for TSS terminals as a mixed-integer nonlinear programming (MINLP). To solve the intractable MINLP, the original problem is transformed and decoupled into the two subproblems. Then, we propose a joint bandwidth optimization and terminal clustering (JBOTC) algorithm to tackle the bandwidth allocation problem with optimal terminal grouping strategy for TSS effectively. The closed-form expressions of the optimal bandwidth allocation strategy for three services are derived. The simulation results illustrate the performance superiority for saving bandwidth of the JBOTC algorithm to the benchmark schemes. Our proposed slicing strategy enables WLTCN to support heterogeneous services co-existence with minimal bandwidth consumption.

Deep learning techniques, particularly those based on Wi-Fi fingerprinting, have become increasingly prevalent in the field of indoor localization. These methods typically require specialized training for specific environments and often lack adaptability to changes in indoor settings. In contrast, this study introduces an indoor localization approach based on few-shot regression. The aim is to enable the model to rapidly adapt to new indoor environments using a limited number of labeled Wi-Fi Received Signal Strength Indicator (RSSI) samples. This research treats indoor location prediction as a regression problem, initially pretrain the model on a Wi-Fi dataset from a source domain and establishing a general mapping relationship between Wi-Fi signals and locations using the concept of basis functions. Subsequently, the model is fine-tuned with a small set of Wi-Fi samples from the target domain to learn specific weights. This process of transferring the model from the source to the target domain aids in achieving accurate localization in new and constantly changing environments. Experimental results demonstrate the method’s superior performance in localization accuracy, showing a 57.9% improvement over few-shot classification, a 13% improvement over KNN and a 11.1% improvement over SAE-CNN.

Model stealing (MS) involves querying and observing the output of a machine learning model to steal its capabilities. The quality of queried data is crucial, yet obtaining a large amount of real data for MS is often challenging. Recent works have reduced reliance on real data by using generative models. However, when high-dimensional query data is required, these methods are impractical due to the high costs of querying and the risk of model collapse. In this work, we propose using sample gradients (SG) to enhance the utility of each real sample, as SG provides crucial guidance on the decision boundaries of the victim model. However, utilizing SG in the model stealing scenario faces two challenges: 1. Pixel-level gradient estimation requires ex-tensive query volume and is susceptible to defenses. 2. The estimation of sample gradients has a significant variance. This paper proposes Superpixel Sample Gradient stealing (SPSG) for model stealing under the constraint of limited real samples. With the basic idea of imitating the victim model's low-variance patch-level gradients instead ofpixel-level gradients, SPSG achieves efficient sample gradient es-timation through two steps. First, we perform patch-wise perturbations on query images to estimate the average gradient in different regions of the image. Then, we filter the gradients through a threshold strategy to reduce variance. Exhaustive experiments demonstrate that, with the same number of real samples, SPSG achieves accuracy, agreements, and adversarial success rate significantly surpassing the current state-of-the-art MS methods. Codes are available at https://github.com/zyI123456aBISPSG_attack.

Current 3D object detection methods face limitations in both single-modal and multimodal approaches. Single-modal detectors struggle with inadequate depth perception or difficulty distinguishing semantically similar objects, while multimodal systems, which combine LiDAR and camera data, encounter challenges like integration complexity and inefficient feature fusion. This study presents ROI-based ViT Fusion (RVF3D), a multimodal 3D object detector combining sparse 3D and dense 2D data, outperforming current methods. The RVF3D enhances the understanding of rich LiDAR and camera representations through improved query generation, feature sampling, and multimodality cross-ViT fusion. We propose an ROI-based Query Sampling (RQS) multimodal 3D object identification pipeline, eliminating laborious non-maximum suppression (NMS) postprocessing and complex prior box configurations. The RQS module uses learnable filters to aggregate image and point representations, retaining foreground characteristics for object localization and recognition while removing background noise. Our RVF3D leverages a hierarchical vision transformer-based approach, ViT-Fusion, which includes CameraViT and LidarViT components for embedding representations of input data in each modality. These representations are fused to enable hierarchical learning and deeper feature extraction. Comprehensive tests on the KITTI and nuScenes datasets demonstrate that RVF3D achieves 89.88% mAP in BEV and 75.2% mAP in 3D, respectively.

In computer vision, accurately detecting objects in three-dimensional (3D) scenes is indispensable for intelligent transportation, robotics, vision applications, and augmented reality. While self-attention mechanisms have demonstrated remarkable success in enhancing feature representations and capturing long-range dependencies, their application to 3D object detection remains challenging due to inherent limitations to capturing intricate contextual dependencies among points to refining 3D proposals. This paper proposes a high-quality Chunk-wise Reweighting Transformer for 3D Object Detection (CRT3D) architecture explicitly tailored for 3D object detection tasks. CRT3D comprises three modules: self-attention-based encoder-decoder for effective modelling of spatial context; channel-based Reweighting captures temporal dependencies; and Chunk-wise Reweighting improves computational efficiency to efficiently handle sparse point cloud data, advancing real-time 3D object detection in autonomous vehicles. Our CRT3D model can effectively balance the trade-off between capturing local and global context, leading to more informative and contextually rich representations. Through extensive experiments on the benchmark dataset KITTI [1], we demonstrate the efficacy of CRT3D in achieving better performance by 3.49% and 4.25% in 3D AP with PointPillar and PointRCNN backbone, respectively. CRT3D enhances 3D object detection framework accuracy, particularly at medium range and occlusion cases, while minimally impacting real-time performance and model parameters.

Detecting camouflaged objects is expected to be a challenging task due to the hard-distinguihsed boundaries of targets. Although existing learning-based methods have concentrated on utilizing boundary information to enhance camouflaged object detection, the absence of boundary difficulty estimation causes them to treat all boundary regions as equal, thereby making it more challenging to distinguish high intrinsic similarity boundary regions. To address this issue, by filtering redundant information on easy boundaries, we have proposed Edge Attention Network (EANet) to extract informative boundary knowledge. Specifically, we propose an Edge-attention Guidance module to prevent misleading segmentation by extracting critical boundary features. Then, Progressive Recognition module is proposed to progressively generate boundary-informative. The experimental results on three real-world datasets have demonstrated that our EANet outperforms existing methods across all three mertrics, while maintaining low computation.

The indeterminacy of human motion poses challenges for pedestrian trajectory prediction. Consequently, existing methods adopt multimodal strategy to model pedestrians future trajectories. A significant advancement in this regard is the growing prominence of the diffusion model. However, the two-dimensional inputs for trajectory prediction not provide sufficient contextual information for the diffusion model. Furthermore, the diffusion model suffers from substantial inference time. To address these conundrums, we propose a trajectory prediction method based on the diffusion model, named as Motion Latent Diffusion (MLD). The core of MLD is the Conditional Variational Autoencoder (CVAE) to transform the original low-dimensional inputs into a higher-dimensional latent space, expanding the receptive field to yield more comprehensive and intricate representations. Simultaneously, during the inferential stage of the diffusion model, we adopt a leapfrogging inference strategy, which facilitates a faster sampling process. Experiments conducted on the ETH/UCY and Stanford Drone datasets (SDD) corroborate the superiority of our method.

Roadside 3D object detection is crucial for vehicle infrastructure cooperation systems. Due to the distinctive placement of roadside LiDAR, the distribution patterns of roadside point clouds and vehicle-side point clouds differ. In roadside point clouds, the proportion of foreground points in each instance is lower, leading to a notable decline in accuracy when using current sampling methods because of an unguided down-sampling strategy. To address this issue, this paper proposes a point-based single-stage 3D object detector called RDSSD for 3D object detection in roadside scenes. The paper designs a class-guided sampling strategy to efficiently select foreground points associated with potential objects. Furthermore, a task-oriented candidate prediction approach is introduced to generate candidate points that accurately represent the local scene from sampled key points. The experimental results on the DAIR-V2X-I have demonstrated that our method achieves the best detection performance with minimal computational cost.

Networks Anomaly Detection is very critical to ensure the security in IoT. However, the noise in training and detection samples varies due to differences in scenarios and devices, and this different noise information corresponds to distinct false correlation relationships. This leads to a lack of stability in existing detection models based on correlation reasoning. To address these issues, in this paper, we propose a novel causal diffusion approach to detect anomalies in IoT. The model first generates independent features by adding noise to remove false correlations and subsequently addresses the problems of Not Independent and Identically Distributed (N-IID) sample distributions by calculating the causal effect relationships between the labels and features to remove noise. Finally, through the validation of one broad and representative network intrusion detection dataset, the experimental results show that method can achieve a maximum detection rate of >99% in the actual different network environments in CICIDS2019.

Task offloading is a widely used technology in Edge Computing (EC), which declines the makespan of user task with the aid of resourceful edge servers. How to solve the competition for computation and communication resources among tasks is a fundamental issue in task offloading. Besides, real-life user tasks often comprise multiple interdependent subtasks. Dependencies among subtasks significantly raises the complexity of task offloading, and makes it difficult to propose generalized approaches for scenarios of different size. In this paper, we study the Dependent Task Offloading (DTO) problem within both single-user single-edge and multi-user multi-edge scenario. First, we use Directed Acyclic Graph (DAG) to model dependent task, where nodes and directed edges represent the subtasks and their interdependencies respectively. Then, we propose a task scheduling method based on Graph Attention Network (GAT) and Deep Reinforcement Learning (DRL) to minimize the makespan of user tasks. More specifically, our method introduces a multi-discrete action DRL scheduler that simultaneously determines which subtask to consider and whether it should be offloaded at each step, and employs GAT to encode the graph-based state representation. To stabilize and speed up DRL scheduler training, we pretrain GAT encoder with unsupervised learning. Extensive experiments demonstrate that our proposed approach can be applied to various environments and outperforms prior methods.

Nowadays, the Internet of Things (IoT) technology has been widely applied in the police security system. However, with more and more image data that concerns crime scenes being transmitted through the police IoT, there are some new security and privacy issues. Therefore, how to design a safe and efficient secret image sharing solution suitable for police IoT has become a very urgent task. In this work, a grid multibutterfly memristive Hopfield neural network (HNN) with three memristive systems is constructed and its complex dynamics are deeply analyzed. Among them, the first memristive system is modeled by emulating a self-connection synapse, the second memristive system is modeled by coupling two neurons, and the third memristive system is modeled by describing external electromagnetic radiation. Dynamic analyses show that the proposed memristive HNN can not only generate two kinds of 1-directional (1-D) multibutterfly chaotic attractors but also produce complex grid (2-D) multibutterfly chaotic attractors. More importantly, by switching the initial states of the second and third memristive systems, the grid multibutterfly memristive HNN exhibits initial-boosted plane coexisting multibutterfly attractors. Moreover, the number of butterflies contained in a multibutterfly attractor and coexisting attractors can be easily adjusted by changing memristive parameters. Based on these complex dynamics, an image security solution is designed to show the application of the newly constructed grid multibutterfly memristive HNN to police IoT security. Security performances indicate the designed scheme can resist various attacks and has high robustness. Finally, the test results are further demonstrated through Raspberry Pi-based hardware experiments.

In the digital divide regions, the edge computing can improve the performance of application services for the Internet of Things (IoT) devices. However, the lagging of information and communication technology (ICT) results in congested access spectrum and imbalanced computational load. Moreover, the mobility of IoT devices further exacerbates the fluctuating quality of communication links and the frequent changing of access positions. So, how to realize the reliable service requirements of devices in a heterogeneous environment with multiscale constraints should be considered appropriately and comprehensively. In this article, we model a relay-assisted multiaccess edge computing (MEC) framework, employing multihop transmission to enable the cross-domain service coverage. Under this framework, we formulate a quantitative model to characterize communication and computation processes within task migration, and derive analytical results for service latency. To improve the access resource efficiency, we adopt a joint nonorthogonal multiple access (NOMA) scheme to extend the transmission dimension, and employ proportional fairness to dynamically allocate resources. Besides, we propose a multiagent deep reinforcement learning (DRL) for optimizing the long-term task offloading scheduling, address the optimization problem of maximizing the system throughput efficiency. And we improve the action exploration and output dimensions of DRL to achieve convergence and performance enhancement. Simulation and analytical results show that our proposed algorithm outperforms the comparison algorithms in the key performance indicators.

Due to the unstable and complex social network environment, the sole user–item interaction data become insufficient for generating precise recommendations. However, too much emphasis on user–item interactions prevents the discovery of internal connections among them, such as trustworthy user relations. In this work, we have integrated the collaborative and the sequential relations into an end-to-end graph neural network (GNN) simultaneously and proposed a novel framework, namely multirelational collaborative filtering (MRCF), to explore the evolutional social relations. MRCF mainly consists of two components: relational GNN (RGNN) and simple dot-product attention (SDPA), where RGNN is used to capture not only the collaborative but also the sequential relationship from reliable user–item historical interactions through the graph representation, while SDPA can further concentrate on the dominated interaction sequences between users and items. Moreover, a negative sampling method based on user interest is proposed to help train our model. Extensive experiments on three real-world datasets show that the proposed model performs competitively with other state-of-the-art methods in CF.

Camouflaged object detection has been considered a challenging task due to its inherent similarity and interference from background noise. It requires accurate identification of targets that blend seamlessly with the environment at the pixel level. Although existing methods have achieved considerable success, they still face two key problems. The first one is the difficulty in removing texture noise interference and thus obtaining accurate edge and frequency domain information, leading to poor performance when dealing with complex camouflage strategies. The latter is that the fusion of multiple information obtained from auxiliary subtasks is often insufficient, leading to the introduction of new noise. In order to solve the first problem, we propose a frequency domain reconstruction module based on contrast learning, through which we can obtain high-confidence frequency domain components, thus enhancing the model’s ability to discriminate target objects. In addition, we design a frequency domain representation decoupling module for solving the second problem to align and fuse features from theRGBdomain and the reconstructed frequency domain. This allows us to obtain accurate edge information while resisting noise interference. Experimental results show that our method outperforms 12 state-of-the-art methods in three benchmark camouflaged object detection datasets. In addition, our method shows excellent performance in other downstream tasks such as polyp segmentation, surface defect detection, and transparent object detection.

Edge intelligence has emerged as a promising paradigm to accelerate DNN inference by model partitioning, which is particularly useful for intelligent scenarios that demand high accuracy and low latency. However, the dynamic nature of the edge environment and the diversity of end devices pose a significant challenge for DNN model partitioning strategies. Meanwhile, limited resources of the edge server make it difficult to manage resource allocation efficiently among multiple devices. In addition, most of the existing studies disregard the different service requirements of the DNN inference tasks, such as its high accuracy-sensitive or high latency-sensitive. To address these challenges, we propose a Multi-Compression Scale DNN Inference Acceleration (MCIA) based on cloud-edge-end collaboration. We model this problem as a mixed-integer multi-dimensional optimization problem, jointly optimizing the DNN model version choice, the partitioning choice, and the allocation of computational and bandwidth resources to maximize the tradeoff between inference accuracy and latency depending on the property of the tasks. Initially, we train multiple versions of DNN inference models with different compression scales in the cloud, and deploy them to end devices and edge server. Next, a deep reinforcement learning-based algorithm is developed for joint decision making of adaptive collaborative inference and resource allocation based on the current multi-compression scale models and the task property. Experimental results show that MCIA can adapt to heterogeneous devices and dynamic networks, and has superior performance compared with other methods.

With the ever-growing interest in modeling complex graph structures, graph neural networks (GNN) provide a generalized form of exploiting non-Euclidean space data. However, the global graph may be distributed across multiple data centers, which makes conventional graph-based models incapable of modeling a complete graph structure. This also brings an unprecedented challenge to user privacy protection in distributed graph learning. Due to privacy requirements of legal policies, existing graph-based solutions are difficult to deploy in practice. In this paper, we propose a privacy-preserving graph neural network based on local graph augmentation, named LGA-PGNN, which preserves user privacy by enforcing local differential privacy (LDP) noise into the decentralized local graphs held by different data holders. Moreover, we perform local neighborhood augmentation on low-degree vertices to enhance the expressiveness of the learned model. Specifically, we propose two graph privacy attacks, namely attribute inference attack and link stealing attack, which aim at compromising user privacy. The experimental results demonstrate that LGA-PGNN can effectively mitigate these two attacks and provably avoid potential privacy leakage while ensuring the utility of the learning model.

The Internet of Things (IoT) mainly consists of a large number of Internet-connected devices. The proliferation of untrusted third-party IoT applications has led to an increase in IoT-based malware attacks. In addition, it is infeasible for the IoT devices to support the sophisticated detection systems due to the restricted resources. Edge computing is considered to be promising. It provides solutions to the data security and privacy leakage brought by untrusted third-party IoT applications. In this article, an intelligent trusted and secure edge computing (ITEC) system is proposed for IoT malware detection. In this system, a signature-based preidentification mechanism is built for matching and identifying the malicious behaviors of untrusted third-party IoT applications. A delay strategy is then embedded into the risk detection engine in order to “buy time” for threat analysis and rate-limit the impact of suspicious third-party IoT applications in the system. We conduct extensive experiments to verify the effectiveness of the ITEC system and show that we can achieve accuracies of up to 98.52%.

Although collaborative 3D perception has successfully improved detection performance by sharing LIDAR information among multiple agents, its impact under adverse weather is under poor investigation. It is non-trivial to reduce the noise effect in the multi-agent system, as each agent may generate defective feature representations with aleatoric uncertainty, and such uncertainty will be further amplified in the collaborative stage due to deterministic collaboration models. To mitigate the negative effects of weather noise on the collaborative framework, we proposed a method called Co-Denoising, which incorporates a two-stage denoising approach within the intermediate collaborative framework. In our method, a sampling-based noise filtering is first performed at each agent to make a coarse denoising. Then, during the collaboration stage, the global feature representations are expanded through Bayesian neural networks to improve the robustness against environmental noise. The extensive experiments on sunny and rainy datasets have indicated the proposed collaborative perception method can significantly reduce performance degradation under adverse weather.

It is inevitable to recognize objects in adverse weather conditions where the uncertainty of contour areas is increased. Although some multi-task learning frameworks have gained from the directional supervision between boundary detection and semantic segmentation, the interaction between those two tasks is poorly investigated. Moreover, the performance of the contour detection is expected to degrade under foggy scenarios, because the auxiliary task also has no benefits from the main task. To address the potential risk in intelligent transportation systems, this paper proposes a mutual learning framework, named CE-MGN (Confidence-Enhanced Mutual Graph Network), to propagate confidence through continuous interaction between different tasks rather than only focusing on the accuracy of the main task. The CE-MGN performs an end-to-end training paradigm and jointly learns two tasks, contour detection and semantic segmentation, through pairwise confidence-enhancement mechanism. Moreover, the task interaction is converted into graph space to further relieve the information loss during the feature aggregation in Euclidean space. Such a framework is capable to improve the robustness of respective tasks because of the encouragement from its peer task. Extensive experiments show that our CE-MGN achieved mean IoU scores of 79.35% and 79.03% on CityScapes and Foggy CityScapes datasets, respectively. Besides, our models have a stable performance on different weather severity, where the performance fluctuation is less than 1%.

The outbreak of COVID-19 has caused a serious impact on the traditional logistics industry. Considering that the truck-drone collaborative delivery system can both reduce the risk of COVID-19 propagation and deliver supplies in a cost effective and timely manner, this paper introduces the Multiple visits Travelling Salesman Problem with Multiple Heterogeneous Drones (MTSP-MHD). The model allows a truck to carry a fleet of heterogeneous multi-visit drones for cooperative deliveries, where the drones are capable of delivering to multiple customers on a single route and the flight is restricted by energy consumption and payload constraints. To solve MTSP-MHD, we develop an approach that combines K-Means$++$clustering, Nearest neighbor search and Greedy strategies (KNG) to construct feasible solutions. Meanwhile, an Improved Artificial Bee Colony algorithm combining Metropolis acceptance criterion of Simulated Annealing, Tabu list of Tabu Search, and Elite selection strategies (IABC-MTE) is proposed to enhance the quality of solutions. Particularly, three problem-specific neighborhood operators are adopted to search for new solutions. The massive experimental results indicate that IABC-MTE achieves significant improvements over other competitors, with average objective value reductions ranging from 1.81% to 29.16% and standard deviations reduced by 0.04 to 26.44. Finally, the influencing factors of the drone fleet, the performance of different drone fleets and delivery modes are evaluated in detail.

Unmanned Aerial Vehicles (UAVs) can be employed as short-term aerial base stations or as access points for User Equipments (UEs) to communicate with other UEs effectively. However, communication links may be obstructed by buildings, leading to poor data transfer performance and significant energy consumption. Deploying Reconfigurable Intelligent Surfaces (RIS) as part of the UAV-assisted communication system proves to be an effective means to avoid building obstructions and enhance wireless information quality. However, the complexity of communication relationships in multi-UAV systems with RIS-aided communication poses a significant challenge in energy reduction. Therefore, this study investigates a new RIS-aided multi-UAV communication framework for edge computing systems. The system aims to meet the quality-of-service (QoS) for UEs while minimizing the total energy consumption. To optimize the total energy consumption of RIS-aided multi-UAV communication, the impact of communication between multiple UAVs and differences between UE clusters on that system’s performance is also considered. We introduce a Stackelberg game to deal with the communication relationship between multiple UAVs and design a K-means-based clustering algorithm to segment UEs periodically. A model-free deep reinforcement learning algorithm grounded in maximum entropy is proposed to jointly optimize UAV trajectory design, phase shift control, and power allocation to reduce energy consumption further. Experimental results indicate that the system proposed performs favorably concerning both energy consumption and throughput.

Location Dependent Mobile Crowdsensing (LDMC) often needs to collect data at different time points in various regions to ensure the coverage of sensing data. An incentive mechanism is needed to encourage participants to move to sparse areas and improve coverage. However, there are two problems: 1) most incentive mechanisms assume that the participants can get accurate information about tasks; 2) those mechanisms encourage participants through absolute utility so that the platform can obtain an improvement of incentive effect by increasing the reward. However, nodes usually get inaccurate information in reality. Moreover, behavioral economics finds that decision-making is often affected by relative utility rather than absolute utility. Path-dependence means that choices made on the basis of transitory conditions can persist long after those conditions change, which can solve the above problems. This study uses cognitive bias and the reference effect to explain the principle of path-dependence, and proposes a mechanism called Task Coverage promotion based on Path-dependence (TCPD). TCPD cultivates the cognitive bias of participants, causing an overestimation of expected utility. Then, it sets dynamic reference points to prevent participants from quitting early. The simulation results show that TCPD can improve the coverage and effectiveness of the platform.

Digital twins (DT) and mobile networks have evolved forms of intelligence in Internet of Things (IoT). In this work, we consider a Digital Twin Mobile Network (DTMN) scenario with few multimedia samples. Facing challenges of knowledge extraction with few samples, stable interaction with dynamic changes of multimedia data, time and privacy saving in low-resource mobile network, we propose an edge computing and few-shot learning featured intelligent framework. Considering time-sensitive property of transmission and privacy risks of directly uploads in mobile network, we deploy edge computing to locally run networks for analysis, thus saving time to offload computing request and enhancing privacy by encrypting original data. Inspired by remarkable relationship representation of graphs, we build Graph Neural Network (GNN) in cloud to map physical mobile systems to virtual entities with DT, thus performing semantic inferences in cloud with few samples uploaded by edges. Occasionally, node features in GNN could converge to similar, non-discriminative embeddings, causing catastrophic unstable phenomena. An iterative reweight and drop structure (IRDS) is thus constructed in cloud, which nonetheless contributes stability with respect to edge uncertainty. As part of IRDS, a drop Edge&Node scheme is proposed to randomly remove certain nodes and edges, which not only enhances distinguished capability of graph neighbor patterns, but also offers data encryption with random strategy. We show one implementation case of image classification in social network, where experiments on public datasets show that our framework is effective with user-friendly advantages and significant intelligence.

The proliferation of Internet-connected devices and the complexity of modern network environments have led to the collection of massive and high-dimensional datasets, resulting in substantial information redundancy and sample imbalance issues. These challenges not only hinder the computational efficiency and generalizability of anomaly detection systems but also compromise their ability to detect rare attack types, posing significant security threats. To address these pressing issues, we propose a novel causal genetic network-based anomaly detection method, the CNSGA, which integrates causal inference and the nondominated sorting genetic algorithm-III (NSGA-III). The CNSGA leverages causal reasoning to exclude irrelevant information, focusing solely on the features that are causally related to the outcome labels. Simultaneously, NSGA-III iteratively eliminates redundant information and prioritizes minority samples, thereby enhancing detection performance. To quantitatively assess the improvements achieved, we introduce two indices: a detection balance index and an optimal feature subset index. These indices, along with the causal effect weights, serve as fitness metrics for iterative optimization. The optimized individuals are then selected for subsequent population generation on the basis of nondominated reference point ordering. The experimental results obtained with four real-world network attack datasets demonstrate that the CNSGA significantly outperforms existing methods in terms of overall precision, the imbalance index, and the optimal feature subset index, with maximum increases exceeding 10%, 0.5, and 50%, respectively. Notably, for the CICDDoS2019 dataset, the CNSGA requires only 16-dimensional features to effectively detect more than 70% of all sample types, including 6 more network attack sample types than the other methods detect. The significance and impact of this work encompass the ability to eliminate redundant information, increase detection rates, balance attack detection systems, and ensure stability and generalizability. The proposed CNSGA framework represents a significant step forward in developing efficient and accurate anomaly detection systems capable of defending against a wide range of cyber threats in complex network environments.

Heterogeneous communication environments and broadcast feature of safety-critical messages bring great challenges to mode selection and resource allocation problem. In this paper, we propose a federated multi-agent deep reinforcement learning (DRL) scheme with action awareness to solve mode selection and resource allocation problem for ensuring quality of service (QoS) in heterogeneous V2X environments. The proposed scheme includes an action-observation-based DRL and a model parameter aggregation algorithm considering local model historical parameters. By observing the actions of adjacent agents and dynamically balancing the historical samples of rewards, the action-observation-based DRL can ensure fast convergence of each agent’ individual model. By randomly sampling historical model parameters and adding them to the foundation model aggregation process, the model parameter aggregation algorithm improves foundation model generalization. The generalized model is only sent to each new agent, so each old agent can retain the personality of its individual model. Simulation results show that the proposed scheme outperforms the comparison algorithms in the key performance indicators.

Most object detection methods have achieved impressive performance on several public benchmarks, instead, facing underwater detection tasks, it is challenging to detect marine targets because of the inherent illumination inhomogeneity in underwater images. Moreover, the imbalanced foreground-background proposals further aggravate the situation of capturing marine organisms. To address the problems, we analyze the deficiency of existing feature pyramid structures and propose a multi-depth and multi-breadth pyramid architecture named Refined Pyramid Grid (RPG). A Harmonizing Focal Loss (HFL) is then proposed to generalize the discrete labels in focal loss to the continuous version to improve the optimization. Experimental results on the real-world datasets have demonstrated the efficiency and reliability of the proposed framework regarding underwater object detection tasks.

The existing empirical risk minimization algorithms learn the association between inputs and labels, and face substantial difficulties when apply to different distributions because of various confounders. Causal intervention becomes a solid solution to this issue by analyzing the visual causality, instead, those approaches fail at disentangling the confounders and mediators within the causality, and bring negative effects to the prediction. In this paper, we propose a disentangled visual causal model to eliminate the effects of confounders while reserving the corresponding mediators. Specifically, confounders are considered as different objects on the image, while mediators are formulated as some critical components of the targets that contribute to a distinctive identification. Extensive experiments on coco datasets have demonstrated the superiority of our model over other state-of-the-art baselines.

Graph Neural Networks (GNNs) as an emerging technique have shown excellent performance in a variety of fields, such as social networks and recommendation systems. However, GNNs may have to overcome privacy concerns as large amounts of information about their training datasets may be compromised. In this paper, we develop a privacy-preserving GNN to enforce privacy preservation, which utilizes a private Functional Mechanism (FM) to train the learning model. This mechanism perturbs the polynomial approximation of the objective function to enforce Differential Privacy (DP) in the GNN model. We show that our method can maximize the accuracy of the results with comparable prediction power to the unperturbed results while satisfying the privacy guarantees.

Neural Networks’ performance on a sequence of incremental class tasks drops over time for Class Incremental Learning (IL). The gradient-based IL methods can simultaneously adapt to both new and previous tasks by promoting the update of model in the correct direction. However, existing methods simply consider the previous/new task gradients separately. In this paper, we propose Parallel Gradient Blend (PGB) paradigm. On the one hand, PGB uses the gradients generated by mixing previous and new samples in equal proportions with Batch-Normal layers to adjust a reasonable model update direction. By comparing gradient similarities, the model selects either the previous task gradient or mixed gradient to update. On the other hand, PGB uses the sample feature gradient distribution difference to construct a regularized gradient. Finally, we experimentally demonstrate that PGB outperforms state-of-the-art methods on class-IL benchmarks.

In this paper, we study the design of neural network based joint source-channel coding (JSCC) for point-to-point communication of Gauss-Markov sources over the additive white Gaussian noise (AWGN) channel with bandwidth compression. Among the existing deep learning (DL) -based JSCC methods for such sources, the long short-term memory (LSTM) based structure has good performance. However, it takes up huge time and space consumption because of its complex structure. In this work, we propose to adopt the causal convolution and dilated convolution to form our encoder and decoder due to their abilities of effectively extracting the temporal information of sources and their superiority in terms of reducing the time and space consumption. Experimental results show that the proposed model outperforms the traditional JSCC schemes and is comparable to the LSTM-based model in terms of source reconstruction quality. Besides, the proposed model shows a great robustness in the case of channel quality mismatch and correlation coefficient mismatch. Furthermore, our model takes lower time in the test phase and much lower space consumption compared to LSTM-based model.

The development of Industrial Internet of Things (IIoT) and Industry 4.0 has completely changed the traditional manufacturing industry. Intelligent IIoT technology usually involves a large number of intensive computing tasks. Resource-constrained IIoT devices often cannot meet the real-time requirements of these tasks. As a promising paradigm, the mobile-edge computing (MEC) system migrates the computation intensive tasks from resource-constrained IIoT devices to nearby MEC servers, thereby obtaining lower delay and energy consumption. However, considering the varying channel conditions as well as the distinct delay requirements for various computing tasks, it is challenging to coordinate the computing task offloading among multiple users. In this article, we propose an autonomous partial offloading system for delay-sensitive computation tasks in multiuser IIoT MEC systems. Our goal is to provide offloading services with minimum delay for better Quality of Service (QoS). Enlighten by the recent advancement of reinforcement learning (RL), we propose two RL-based offloading strategies to automatically optimize the delay performance. Specifically, we first implement the$Q$-learning algorithm to provide a discrete partial offloading decision. Then, to further optimize the system performance with more flexible task offloading, the offloading decisions are given as continuous based on deep deterministic policy gradient (DDPG). The simulation results show that the$Q$-learning scheme reduces the delay by 23%, and the DDPG scheme reduces the delay by 30%.

Compared with cloud computing, edge computing is capable of effectively solving the high latency problem in cloud gaming. However, there are still several challenges to address for optimizing system performance. On the one hand, the unpredictable bursts of game requests can cause server overload and network congestion. On the other hand, the mobility of players makes the system highly dynamic. Although existing research has studied game fairness and latency separately to improve the Quality of Experience (QoE), a tradeoff between fairness and latency has been largely ignored. Furthermore, how to balance network and computing load is identified as another constraint during optimization. Focusing on latency, fairness, and load balance simultaneously, we propose an adaptive resource allocation strategy through deep reinforcement learning (DRL) for a dynamic gaming system. The experimental results have demonstrated that the proposed algorithm outperforms the traditional optimization methods and classical reinforcement learning algorithms in solving complex multimodal reward problems.

The vision of heterogeneous vehicle networks (HetVNETs) embraces various highly dynamic scenarios with urgent requirements for delay-sensitive and reliability-guaranteed computation placement. Incorporating mobile-edge computing (MEC) technology into computation placement has a significant potential to reduce computational delay and enhance communication reliability. However, vehicle mobility and resource constraints make the multivehicle scramble for communication and computational resources challenging. This article intends to investigate collaborative computing by comprehensively considering vehicle mobility, channel condition, and computational resources with two goals: 1) high-reliability transmission (HRT) and 2) computational delay minimization (CDM). Specifically, we develop a hybrid MEC-enabled computation placement orchestrator for HetVNET, where the HRT and CDM are formulated as mixed-integer programming and nonconvex optimization problems, respectively. To ensure high-reliability communication, we leverage the conditional value at risk theory to tackle the nonsmooth HRT problem. To solve the CDM problem, we transform it into two subproblems: resource allocation and task offloading problems, aiming at reducing computational delay and improving resource utilization. Furthermore, we construct an iterative optimization algorithm to capture the optimal computation placement scheme in closed form for the HRT and CDM problems. Performance evaluations show that the proposed methods can significantly improve communication reliability and reduce computational delay.

Due to their inherent capability in the semantic alignment of aspects and their context words, Attention and Long-Short-Term-Memory (LSTM) mechanisms are widely adopted for Aspect-Based Sentiment Classification (ABSC) tasks. Instead, it is challenging to handle long-range word dependencies on multiple entities due to the deficiency in attention mechanisms. To solve this problem, we propose a Context-Focused Aspect-Based Network to align attention before LSTM, making the model focus more on aspect-related words and ignore irrelevant words, improving the accuracy of final classification. This can either alleviate attention distraction or reinforce the text representation ability. Experiments on two benchmark datasets show that the results achieve respectable performance compared to the state-of-the-art methods available in ABSC. Our approach has the potential to improve classification accuracy by adaptively adjusting the focus on context.

As the demand for Internet of Things (IoT) technologies continues to grow, IoT devices have been viable targets for malware infections. Although deep learning-based malware detection has achieved great success, the detection models are usually trained based on the collected user records, thereby leading to significant privacy risks. One promising solution is to leverage federated learning (FL) to enable distributed on-device training without centralizing the private user records. However, it is non-trivial for IoT users to label these records, where the quality and the trustworthiness of data labeling are hard to guarantee. To address the above issues, this paper develops a semi-supervised federated IoT malware detection framework based on knowledge transfer technologies, named by FedMalDE. Specifically, FedMalDE explores the underlying correlation between labeled and unlabeled records to infer labels towards unlabeled samples by the knowledge transfer mechanism. Moreover, a specially designed subgraph aggregated capsule network (SACN) is used to efficiently capture varied malicious behaviors. The extensive experiments conducted on real-world data demonstrate the effectiveness of FedMalDE in detecting IoT malware and its sufficient privacy and robustness guarantee.

With the coming of the Internet of Things (IoT) era, malware attacks targeting IoT networks have posed serious threats to users. Recently, the emerging of edge computing have paved the way for new data processing paradigms in IoT networks, but it is still a challenge for deploying malware detection systems on the IoT devices. This paper develops an IoT malware detection system based on trust hybrid user-edge evaluation, namely MDHE. This system decomposes a large and complex deep learning model into two parts, which are deployed on edge servers and end devices, respectively. Specifically, a trust evaluation mechanism is used to select the trusted devices to participate the model training. Moreover, we develop a private feature generation that leverages a graph mining technology to extract the subgraph features, which then are perturbed by leveraging the differential privacy technology to prevent user privacy from leaking. Finally, we reconstruct the perturbed features on edge server, and propose a Capsule Network (CapsNet) to identify malware. Experimental results show that MDHE can effectively detect malware. Specifically, it can reduce sensitive inference while maintaining the utility of data.

The advent of 5G brought new opportunities to leapfrog beyond current Industrial Internet of Things (IoT). However, the ever-growing IoT has also attracted adversaries to develop new malware attacks against various IoT applications. Although deep-learning-based methods are expected to combat the sophisticated malwares by exploring the latent attack patterns, such detection can be hardly supported by battery-powered end devices, such as Android-based smartphones. Edge computing enables the near-real-time analysis of IoT data by migrating artificial intelligence (AI)-enabled computation-intensive tasks from resource-constrained IoT devices to nearby edge servers. However, owing to varying channel conditions and the demanding latency requirements of malware detection, it is challenging to coordinate the computing task offloading among multiple users. By leveraging the computation capacity and the proximity benefits of edge computing, we propose a hierarchical security framework for IoT malware detection. Considering the complexity of the AI-enabled malware detection task, we provide a delay-aware computational offloading strategy with minimum delay. Specifically, we construct a coordinated representation learning model, named by Two-Stream Attention-Caps, to capture the latent behavioral patterns of evolving malware attacks. Experimental results show that our system consistently outperforms the state-of-the-art systems in detection performance on four benchmark datasets.

The integration of Mobile Edge Computing (MEC) and microservice architecture drives the implementation of the sustainable Internet of Vehicles (IoV). The microservice architecture enables the decomposition of a service into multiple independent, fine-grained microservices working independently. With MEC, microservices can be placed on Edge Service Providers (ESPs) dynamically, responding quickly and reducing service latency and resource consumption. However, the burgeoning of IoV leads to high computation and resource overheads, making service resource requirements an imminent issue. What’s more, due to the limited computation power of ESPs, they can only host a few services. Therefore, ESPs should judiciously decide which services to host. In this paper, we propose a Microservice-oriented Service Placement (MOSP) mechanism for MEC-enabled IoV to shorten service latency, reduce high resource consumption levels and guarantee long-term sustainability. Specifically, we formulate the service placement as an integer linear programming program, where service placement decisions are collaboratively optimized among ESPs, aiming to address spatial demand coupling, service heterogeneity, and decentralized coordination in MEC systems. MOSP comprises an upper layer to map the service requests to ESPs and a lower layer to adjust the service placement of ESPs. Evaluation results show that the microservice-oriented service deployment mechanism offers dramatic improvements in terms of resource savings, latency reduction, and service speed.

Multi-modal fusion is a promising approach to boost the autonomous driving performance and has already received a large amount of attention. Meanwhile, to increase driving reliability under distinct scenarios, it is important to handle unforeseen weather events in the training dataset, which is known as an Out-Of-Distribution (OOD) problem, for autonomous driving algorithms. In this paper, we consider those two aspects and propose an end-to-end multi-modal domain-enhanced framework, namely CrossFuser, to meet the safety orientated driving requirements. CrossFuser first integrates both image and lidar modalities to generate a robust environmental representation through conjoint mapping, elastic disentanglement, and attention mechanism. Further, the perception embedding is used to calculate corresponding waypoints by a waypoint prediction network, consisting of Gate Recurrent Units (GRUs). Finally, the final control commands are calculated by low-level control functions. We conduct experiments on the Car Learning to Act (CARLA) driving simulator involving complex weather conditions under urban scenarios, the results show that CrossFuser can outperform the state of the art.

It is challenging to detect 3D objects from noise point clouds by Graph Neural Networks (GNNs), though graph-based methods have shown promising results in 3D classifications. Since strong robustness against noise is offered by hypergraph, a relative paradigm named HyperGraph Construction-Compression-Conversion (HG3C) is proposed for detecting 3D objects from noise point clouds. Our method presents the capacity of reducing graph redundancy and capturing the variances from multiple features, by pre-encoding the graph, to improve the graph representations in point clouds. A fused graph neural network is further designed to predict the shape and category of the target in converted graphs. The experiments, on both the KITTI and Nuscene, show that the proposed approach achieves leading accuracy. Our results demonstrate the potential of using the hypergraph transformation to extract and compress point cloud information from noisy point clouds.

Given the distributed nature of the massively connected “Things” in IoT, IoT networks have been a primary target for cyberattacks. Although machine learning based network intrusion detection systems (NIDS) can effectively detect abnormal network traffic behaviors, most existing approaches are based on a large amount of labeled traffic flow data, which hinders their implementation in the highly dynamic IoT networks with limited labeling. In this paper, we develop a novel Flow Topology based Graph Convolutional Network (FT-GCN) approach for label-limited IoT network intrusion detection. Our main idea is to leverage the underlying traffic flow patterns,$i.e.$, the flow topological structure, to unlock the full potential of the traffic flow data with limited labeling, where the FT-GCN will be deployed at the edge servers in IoT networks to detect intrusions via software defined network technologies. Specifically, FT-GCN first takes the time correlation of traffic flows into account to construct an interval-constrained traffic graph (ICTG). Besides, a Node-Level Spatial (NLS) attention mechanism is designed to further enhance the key statistical features of traffic flows in ICTG. Finally, the combined representation of statistical flow features and flow topological structure are learned by the cost-effective Topology Adaptive Graph Convolutional Networks (TAGCN) for intrusion identification in IoT networks. Extensive experiments are conducted on three real-world datasets, which demonstrate the effectiveness of the proposed FT-GCN compared to state-of-the-art approaches.

The recent success of Artificial Intelligence (AI) has enabled autonomous driving with better perception capabilities. However, on-ramp merging remains one of the main challenging scenarios for reliable autonomous driving. Within the limited onboard sensing range, a merging vehicle can hardly observe and predict the main road conditions properly, restricting appropriate merging maneuvers. In this poster, we outline ongoing research ideas for reliable and autonomous on-ramp merging assisted by vehicular communications. By jointly leveraging the basic safety messages (BSM) from neighboring vehicles and the surveillance images, a merging vehicle can perform reliable driving via robust multimodal reinforcement learning. Some experimental results are provided to evaluate our idea under the Simulation of Urban MObility (SUMO) platform.

Similarity measurement is an important basis in time series analysis.Among them, dynamic time warping distance (DTW) is considered to be the most effective distance measurement method.However DTW's huge computational overhead is difficult to meet the application requirements in the era of big data.Previous optimization methods often focus on reducing unnecessary calculation objects and do not involve warping distance calculation itself.After studying many related optimization algorithms, we propose a DTW matching algorithm based on key structure point alignment.By extracting the key structure points of time series and calculating the warping alignment relationship between the key structure points, the constraint range of the cumulative distance matrix of the approximate optimal warping distance from the path is mapped, which greatly reduces the amount of calculation of the distance cumulative matrix, then approximate warping distance can be calculated quickly.The experimental results show that the calculation speed of our method is significantly improved compared with the traditional algorithm in similarity matching, and it also has a good performance in classification accuracy. Keywords-time series

Unmanned-aerial-vehicle (UAV)-aided target tracking has been applied in many important practical scenarios such as target vehicle tracking missions. However, the limited computation capability of UAVs can hardly support computation-intensive tasks, like the target tracking with real-time video processing. Inspired by the strong computation capabilities of edge computing servers nowadays, this article develops an energy-efficient UAV-aided target tracking system, where the video processing tasks can be offloaded from a UAV to the edge nodes (ENs) along its flight trajectory. To select appropriate offloading ENs for efficient task processing and energy saving, we formulate a cost minimization problem by jointly optimizing the task execution time and the offloading energy consumption. To devise a practical offloading strategy, we propose an energy-efficient UAV’s task distribution (EUTD) algorithm by jointly taking the different computation capabilities among ENs, time and energy requirements for different tasks, and fast-changing wireless channel conditions into account. Extensive experimental results demonstrate that our proposed algorithm can achieve significantly higher energy efficiency and lower latency in UAV-aided target tracking as compared with existing methods.

The sixth-generation network (6G) is expected to achieve a fully connected world, which makes full use of a large amount of sensitive data. Federated Learning (FL) is an emerging distributed computing paradigm. In Vehicular Edge Computing (VEC), FL is used to protect consumer data privacy. However, using FL in VEC will lead to expensive communication overheads, thereby occupying regular communication resources. In the traditional FL, the massive communication rounds before convergence lead to enormous communication costs. Furthermore, in each communication round, many clients upload large quantity model parameters to the parameter server in the uplink communication phase, which increases communication overheads. Moreover, a few straggler links and clients may prolong training time in each round, which will decrease the efficiency of FL and potentially increase the communication costs. In this work, we propose an efficient-communication approach, which consists of three parts, including “Customized”, “Partial”, and “Flexible”, known as FedCPF. FedCPF provides a customized local training strategy for vehicular clients to achieve convergence quickly through a constraint item within fewer communication rounds. Moreover, considering the uplink congestion, we introduce a partial client participation rule to avoid numerous vehicles uploading their updates simultaneously. Besides, regarding the diverse finishing time points of federated training, we present a flexible aggregation policy for valid updates by constraining the upload time. Experimental results show that FedCPF outperforms the traditional FedAVG algorithm in terms of testing accuracy and communication optimization in various FL settings. Compared with the baseline, FedCPF achieves efficient communication with faster convergence speed and improves test accuracy by 6.31% on average. In addition, the average communication optimization rate is improved by 2.15 times.

The location of participants in Location-based CrowdSensing (LCS) represents important information for task completion. Tasks in areas with high concentration of participants (AHCP) can be completed quickly, whereas task completion is difficult in areas with sparse participants (ASP). Incentive mechanisms are necessary to motivate participants to move toward ASP. Previous studies have faced two main problems. First, most incentive mechanisms assume that participant motivation is not affected by external factors. Second, when participants fail to complete tasks, only the cost of the participant is considered the loss. However, reference effect from behavioral economics proves that participants are influenced by both internal and external factors. Furthermore, loss aversion studies have shown that participant evaluations of loss are more severe than simple costs. Therefore we propose an incentive mechanism based on behavioral economics (IBE) consisting of two schemes for participant selection (IBE-PS) and payment decisions (IBE-PD). Based on reference effect, IBE-PS is proposed to control the task selection and pricing of participants. Based on loss aversion, IBE-PD is proposed to encourage participants to complete tasks in ASP many times. Theoretical analysis and simulation results demonstrate that IBE can improve the task completion rate, the participant utility, and the platform welfare.

The number of smart devices newly connected to the Internet has grown exponentially in recent years. These smart devices are interwoven into huge Internet of Things. There is a contradiction between mass data transmission and communication bandwidth, the distance between supercomputing power and processing object, and the demand of frequent interaction and real-time response. As a new computing paradigm, edge computing processes tasks on computing resources close to data sources. Considering the limited energy of the mobile terminal and the user's demand for low delay, making decisions about tasks executed locally and offloaded to edge computing servers. In the edge environment, resources are dynamically allocated to users on demand, and users need to pay for the resources they actually consume. By considering energy consumption, delay, and price, a user-centered joint optimization loading scheme is proposed to minimize the weighted cost of time delay, energy consumption, and price under the constraint of satisfying the advanced personalized needs of users. The optimization problem is modeled as a mixed-integer nonlinear programming problem, and a branch-and-bound algorithm based on linear relaxation improvement is proposed to solve the problem. Considering the complexity of the algorithm, a particle swarm optimization algorithm based on 0-1 and weight improvement is proposed to solve the problem. Simulation results show that the method proposed in this article can achieve higher performance in terms of delay, energy consumption, and price and provide personalized service for users.

In this paper, we explore how a rotary‐wing unmanned aerial vehicle (UAV) acts as an aerial millimeter wave (mmWave) base station to provide recharging service and radio access service in a postdisaster area with unknown user distribution. The addressed optimization problem is to find out the optimal path starting and ending at the same recharging point to cover a wider area under limited battery capacity, and it can be transformed to an extended multiarmed bandit (MAB) problem. We propose the two improved path planning algorithms to solve this optimization problem, which can improve the ability to explore the unknown user distribution. Simulation results show that, in terms of the total number of served user equipment (UE), the number of visited grids, the amount of data, the average throughput, and the battery capacity utilization level, one of our algorithms is superior to its corresponding comparison algorithm, while our other algorithm is superior to its corresponding comparison algorithm in terms of the number of visited grids.

Directional communication is helpful to improve the performance of millimeter Wave (mmWave) links. However, the dynamic nature of vehicular scenarios raises the complexity of directional mmWave vehicular communications. Also, a mmWave link is susceptible to blockages. Therefore, a mmWave vehicular communication system requires high environmental adaptability and context‐awareness. Due to inadequate context information and insufficient beam settings in the existing related algorithm, it is difficult to pick out the set of beams with more reasonable widths and directions, which hinders the further promotion of network capacity in vehicular networks. Therefore, we propose an improved fast machine learning (IFML) algorithm to overcome this shortcoming. In order to improve network capacity while suppressing the additional beam search overhead, a partitioned search method is designed in the IFML. Also, in order to be robust to occasional fluctuations and timely adapt to significant changes in communication environments, the IFML adopts a flexible beam performance update approach based on adjustable weight coefficient. The simulation results show that the IFML significantly outperforms the existing related algorithm in terms of aggregate received data after a certain number of online learning time periods.

Emerging Internet of vehicles systems brings interesting new applications, such as VR entertainment systems in a car. These applications frequently generate data processing requirements and require a rapid response to ensure user experience. The combination of edge computing mode and ultra-low-latency communications (URLLC) traffic can better meet the requirements of the above scenarios. All requests for signal transmission and data processing can be considered a latency-limited task. We study scheduling strategies of these tasks intending to maximize overall utility for all users. We show that finding an optimal schedule for at least N tasks is NP-hard in the utility-maximizing issue. We propose a heuristic algorithm to maximize the overall utility of all users from the perspective of residual utility. To simulate the tolerance of delay for different tasks, we designed three utility curves: exponential, linear, and step. Simulation results show that the proposed algorithm outperforms the benchmark.

Geographic routing is a research hotspot of the Internet of Vehicles (IoV) and intelligent traffic system (ITS). In practice, the vehicle movement is not only affected by its characteristics and the relationship between the vehicle and position but also affected by some implicit factors. Pointing to this problem, we combine the vehicle moving position probability matrix, the vehicle position association matrix, and the implicit factors to study the influence of vehicle position potential features and vehicle association potential features and propose a routing algorithm based on vehicle position (RAVP) analysis, which can obtain the more accurate vehicle prediction trajectory. Then, the vehicle distance is obtained based on the vehicle prediction trajectory. By the normalization of vehicle distance and cache, the vehicle data forwarding capability is obtained and the transmission decision is made. Simulation results show that the proposed algorithm outperforms the other three routing algorithms in terms of packet delivery ratio, average end-to-end delay, and routing overhead ratio.

Supervised learning is a powerful tool that has shown promise when applied towards bioinformatics data sets. Deep forest, a supervised ensemble model based on decision trees, has been proven to have excellent classification performance and strong generalization ability across different fields. However, when dealing with high-dimensional and small-sample gene expression data, commonly used supervised learning methods including deep forest may not be effective. In this paper, we propose DPCAForest, a deep-forest-based model, which integrates deep forest and dynamic principle component analysis. DPCAForest adaptively generates the minority samples based on sample distribution, then conducts principle component analysis dynamically synchronized with growth of deep forest to reveal the important features with the highest variance. Dynamic PCA enables the model to perform feature extraction in a data-driven way based on cross-validation, and the model can obtain fusion information across layers. In the experimental studies, DPCAForest is verified on Adenocarcinoma, Brain, Colon, Small Round Blue Cell Tumors (SRBCTs) and NCI-60 cancer data sets and demonstrated desirable or better performance than state-of-the-art methods in terms of accuracy and F-Measure.

Energy harvesting (EH) from ambient energy sources can potentially reduce the dependence on the supply of grid or battery energy, providing many benefits to green communications. In this paper, we investigate the device-to-device (D2D) user equipments (DUEs) multiplexing cellular user equipments (CUEs) downlink spectrum resources problem for EH-based D2D communication heterogeneous networks (EH-DHNs). Our goal is to maximize the average energy efficiency of all D2D links, in the case of guaranteeing the quality of service of CUEs and the EH constraints of the D2D links. The resource allocation problems contain the EH time slot allocation of DUEs, power and spectrum resource block (RB) allocation. In order to tackle these issues, we formulate an average energy efficiency problem in EH-DHNs, taking into consideration EH time slot allocation, power and spectrum RB allocation for the D2D links, which is a nonconvex problem. Furthermore, we transform the original problem into a tractable convex optimization problem. We propose joint the EH time slot allocation, power and spectrum RB allocation iterative algorithm based on the Dinkelbach and Lagrangian constrained optimization. Numerical results demonstrate that the proposed iterative algorithm achieves higher energy efficiency for different network parameters settings.

We investigate a mobile edge computing environment where edge computing nodes provide their computation capacities to process the computation intensive tasks submitted by end users. We introduce a Cloudlet Assisted Cooperative Task Assignment (CACTA) system that organizes edge nodes that are geographically close to a user into a cluster to collaboratively work on the user's tasks. The system enables a user to minimize his/her total cost which is a weighted combination of latency (i.e., the task's completion time), and the costs incurred in working on the task. The total cost captures the tradeoff that the user would like to make between latency and computing related costs. It is challenging for the system to find an optimal strategy that assigns workload to edge nodes to meet the user's optimization goal, due to the time-varying available capacities and the mobility of edge nodes. To address the challenge, we model the system as a discrete time system in which each edge node's capacity and cost vary over different time slots, and the system assigns parts of the task to the edge nodes in the cluster over time. We introduce a prediction-based dynamic task assignment algorithm, referred to PA-OPT, that assigns workload to edge nodes in each time slot based on the prediction of their capacities/costs and an empirical optimal allocation strategy which is learned from an offline optimal solution from historical data. Then we apply our system design to a video data analysis application, and conduct extensive simulations driven by a Google cloud data trace. We have demonstrated that our proposed algorithm/system achieves significantly higher performance than several other algorithms, and especially its performance is very close to that of an offline optimal solution.

Edge Computing is emerging as a promising solution to meet the ultra-low latency requirement of data processing at the edge of the Internet, and it is close to end users and the smart devices of Internet of Things. We propose an Edge Computing task scheduling model which utilizes the existing resources to achieve low latency by cooperative computing through multiple edge servers and close- range communication at the edge of the Internet. We treat the latency minimization design as an optimization problem. We formulate the latency minimization as an integer programming problem and solve it efficiently via dynamic programming, then we propose an optimal scheduling algorithm based on dynamic programming (OSA-DP). Considering the limited heterogeneous resources shared among tasks, we further propose a cooperative taskserver matchmaking scheduling heuristic (CTMS), which jointly optimizes the computation and communication cost. Extensive simulations demonstrate that ultra- low latency service provision can be achieved by the cooperative design of computation and communication in Edge Computing.

In stream processing applications, a data stream is a continuous stream of data items that are generated from multiple sources distributed at various geographic locations. A common method of streaming processing is to transfer raw data streams to a data center for unified processing. However, the method does not scale well when a huge amount of data for stream processing is generated at the edge of the Internet, with the development of smartphones, Internet of things, 5G and other technologies in recent years. For stream processing applications, processing data at the edge can significantly reduce the response latency of the applications. However, the mobility of edge nodes in a mobile edge environment poses a significant challenge to scheduling stream processing tasks efficiently to achieve high system throughputs. In this paper, we introduce a scheduling algorithm, referred to as Mobile Resource Aware (MRA) stream processing scheduling, for mobile edge environment. Compared with other existing scheduling algorithms, our MRA algorithm can optimally schedule resources for stream processing tasks through adapting to the mobile edge environment with limited node resources. We implement MRA scheduling algorithm in Storm through a custom scheduler and we evaluate the performance of MRA in an emulation mobile edge environment. Our experimental results have demonstrated that our MRA algorithm can achieve significantly higher system performance than the other two existing scheduling algorithms.

Frequent itemset mining (FIM) is an important topic in data mining, which extracts knowledge of the relationships among items in a transaction dataset. Apriori algorithm and its variants, apriori-like algorithms, are widely used FIM algorithms. However, in a big data environment, these algorithms are inefficient. Due to the iterative calculation and modification of intermediate results, if an apriori-like algorithm is applied on a high-dimension or large-scale dataset, the memory requirement is unacceptable for a single machine. Although parallel and distributed programming could be a solution to deal with big data problems, apriori-like algorithms are not quite suitable for parallel computing because they need extra time overhead of communication to update intermediate results iteratively in cluster memories. To solve this problem, we propose a novel FIM algorithm, Distributed Apriori Based on Itemset-Encoding (DABIE). Different from existing methods, DABIE has two main advantages. Firstly, it stores intermediate results encoded in the form of 0 and 1 to reduce memory usage. Secondly, generating frequent itemsets is based on logical operation of encoding to reduce modification of data in cluster memories. These two advantages make DABIE more friendly to cluster computing. We apply DABIE on datasets with different scales. Compared with other distributed apriori-like algorithms, the results of our experiments show that DABIE can efficiently improve the multi-iterative FIM in big data environment.

Communication networks in smart grid collect and transfer various information between smart meters and control centre to support different quality of service (QoS) requirements of smart grid applications. However, there are many factors which could affect high reliability and QoS communication such as electromagnetic interference, equipment noise and multi‐path effects. To address these challenges, a new routing metric is proposed in this study. The proposed metric takes into account the impacts caused by inter‐ and intra‐flow interference, yielding reliable and high capacity links for neighbourhood area network communications in smart grid. In addition, it differentiates traffic flows into four different classes and makes packets compete for accessing a channel according to their priorities. Based on the metric, an interference aware QoS routing protocol, named interference‐aware expected transmission time routing (IAEETR), is further proposed to provide reliable and real‐time data transmission. Extensive simulation results demonstrate that high‐priority traffic in the network is with small delay, and low‐priority traffic can also have chance to compete for a wireless channel to transmit information. Furthermore, IAEETR protocol can improve end‐to‐end delay and packet delivery ratio with multiple simultaneous connections, even with a higher flow rate of mesh nodes.

Many complex networks in practice can be described by weighted networks. Currently, most existing weighted network models only consider the node strength in evolving conditions, but neglect the influence of node attraction on network evolution. In this paper, we propose an accurate and practical weighted evolving network model based on node fitness dynamic evolution, which takes both node strength and node attraction into consideration. Our theoretical analysis and numerical simulations have demonstrated the scale-free property of the network model, which has been widely observed in many real-world networks. Additionally, the phenomenon that very few nodes possess greater fitness is observed via numerical simulations of our network model, which can be referred to as the fitness property of network. Our network model's dual assessment of node strength and node attraction leads to fewer node clustering and stronger robustness of the whole network than other existing network growth models.

Classification of imbalanced datasets has become one of the most challenging problems in big data mining. Because the number of positive samples is far less than the negative samples, low accuracy and poor generalization performance and some other defects always go with learning process of traditional algorithms. Ensemble construction algorithm is an important method to handle this problem. Especially, the ensemble construction algorithm based on random under-sampling or clustering can effectively improve the performance of classification. However, the former causes information loss easily and the latter increases complexity. In this paper, we propose ACUS, an improved ensemble algorithm based on automatic clustering and under-sampling. ACUS conducts clustering first according to the weight of samples, and then it constructs balanced-distributed dataset which consists of a certain percentage of the majority class and all of the minority class from each cluster. With Adaboost algorithm construction, these datasets are used to get an ensemble classifier. Experimental results demonstrate the advantages of our proposed algorithm in terms of accuracy, simplicity and high stability.

Many complex networks in practice can be described by weighted network models, and the BBV model is one of the most classical ones. In this paper, by introducing the concept of correlation degree between nodes, a new weighted network model based on the BBV model is proposed. The model takes the both node strength and node correlation into consideration during the network evolution, which better reveals the evolving mechanisms behind various real-world networks. Results from theoretical analysis and numerical simulation have demonstrated the scale-free property and small-world property of the network model, which have been widely observed in many real-world networks. Compared with the BBV model, the added correlation preferential attachment rule in the model leads to a faster network propagation velocity.

ABSTRACT To cope with the challenges existing in pervasive environments, based on the characteristics of pervasive environments, a semantic distance‐based trust model is proposed in this paper. The semantic distance between entities and between trust categories is borrowed to calculate trustworthiness more precisely. In the model, the behavior trust and capability trust are distinguished and evaluated separately; on the basis of the trust evaluations, all entities in pervasive environments make independent decisions that can maximize their own profit with the trust model. The simulation experiment results proved the effectiveness of the model in improving the interaction success ratio and efficiency between entities under pervasive environments. Copyright © 2013 John Wiley & Sons, Ltd.

Optimal routing in wireless mesh networks is a challenging problem considering inter- and intra-flow interference. To solve the problem, first, we define a new routing metric, expected path bandwidth (EPBW), where the varying link rate (due to wireless channel quality) and the dynamic link load (considering the inter- and intra-flow interference) have been considered to estimate EPBW accurately. Second, based on the proposed EPBW, we propose a distributed routing protocol for WMNs, aiming to maximize network throughput. We implement the proposed protocol and the routing metric EPBW in NS-2. We then design various scenarios to evaluate the protocol performance extensively using NS-2 simulation. Simulation results show that the proposed protocol and metric can substantially out-perform the state-of-the-art routing metrics, such as expected transmission count (ETX) and expected transmission time (ETT), and previous routing protocols including AODV, DSDV, and DSR.

The failed nodes lead to the phenomenon of coverage holes in Wireless Sensor Networks (WSN), which is due to the exhausted energy or destroyed environment. In this paper, the Best Fit Node Policy (BFNP) is proposed to repair coverage holes of WSN. The main idea of Best Fit Node Policy (BFNP) is that WSN detects the coverage holes when the base station has found the failed nodes of network, and selects the closest inactive node to the center of the minimal coverage circle of the polygon that surrounds the hole and then replaces the failed nodes, meanwhile activates the closest inactive node to repair the coverage holes. The simulation results show that Best Fit Node Policy can maintain better quality of coverage, make higher utilization of energy resources, and extend lifetime of networks. In conclusion, BFNP performs superior to the Coverage Hole Patching Algorithm (CHPA).

The topologies of Internet and Internet-based information systems have complex network properties. Designing Internet-based virtual computing environment topology with appropriate properties is significant for both the resource sharing and system performance. We analyses the topology properties of the typical P2P systems, and proposes a new topology generating method, which includes three phases, birth, growth and maturity, and supports multi-node concurrent joining in. The iVCE topology generation method can produce stable structure, with load balancing capability. Analysis of the generated topologies shows that the degree of their super-node obeys normal distribution law, the average path length between nodes shows small-world properties.