Real-time analytics on video data requires substantial computational resources and high energy consumption, and computational offloading has emerged as a promising solution to support such resource-intensive services. Nevertheless, most of the existing research overlook the resource dependencies induced by object-level correlations in dependent video processing tasks. To address this challenges, we propose a theoretical framework employing a novel scaling factor to model resource dependencies among video tasks, enabling accurate estimation of computation and transmission demands for video blocks with multiple interdependent objects. In contrast to conventional single-objective methods, we formulate the problem as a constrained multi-objective optimization and present a decomposition-based meta-deep reinforcement learning (DOMDRL) framework to balance competing objectives. The proposed approach employs meta-learning to train a meta-model, which is then fine-tuned through limited gradient updates to construct the Pareto front. Simulation results based on real-world datasets demonstrate that DOMDRL reduces average task delay by approximately 9.32%, decreases energy consumption by around 6.26%, and improves video analytics accuracy by about 18.9% compared to state-of-the-art task offloading methods.

Multivehicle collaborative sensing has emerged as a new paradigm to boost the safety of autonomous vehicles. The cornerstone of this vision is the real-time and accurate registration of mmWave radar point clouds among multiple vehicles. To accomplish this, we design mmReg, an innovative system capable of achieving centimeter-level and real-time sensing fusion between vehicles. mmReg consists of three major components: 1) an SAR imaging-driven point cloud generation component leverages SAR imaging to image sparse and disordered radar point clouds to generate high-quality point clouds; 2) a motion-aware frame synchronization component can achieve the spatiotemporal alignment of point clouds between vehicles for effectively mitigating the impact of asynchronous radar frames; and 3) a shared object-based registration component can capture and understand the unique global position of shared objects, supporting real-time and accurate registration. We implement and evaluate mmReg on CARLA and real-world campus datasets. The results demonstrate that mmReg can improve the vehicle's sensing range by 117% in an average of 99.91 ms, achieving a 4.82 X improvement in accuracy.

With the rapid evolution of 5G/6G communication networks and the continuous expansion of mobile video services, video transmission in massive MIMO broadcast scenarios is challenged by heterogeneous multi-user channel conditions, strong inter-layer dependencies of SVC streams, and competition for multi-antenna resources. These factors make minimizing the average video distortion across users a critical yet difficult task. To address this, this paper proposes a distortion-minimization-oriented cross-layer video scheduling framework that integrates the layered SVC structure with the massive MIMO broadcast channel. The video-layer-antenna mapping is formulated as a nonlinear combinatorial optimization problem with rate constraints and layer dependencies. To overcome the exponential complexity of exhaustive search and the local-optimum issue of conventional greedy scheduling, a lightweight Hybrid Greedy-Backtracking Algorithm (HGBA) is developed. By incorporating dynamic priority sorting, a restricted backtracking window, and dependency-aware distortion modeling, HGBA achieves near-optimal scheduling under polynomial complexity. Furthermore, to explore cross-physical-layer cooperation, HGBA is integrated with WMMSE beamforming, forming an extendable joint layer-activation and beamforming optimization framework that leverages spatial and cross-layer gains. Simulation results demonstrate that HGBA consistently outperforms greedy, MIN&MAX, and random scheduling algorithms across all SNR ranges: it saves 1-2 dB SNR to reach the same PSNR at low and medium SNR (12-20 dB), improves PSNR by 0.5-1 dB at high SNR (>= 22 dB), and avoids the 1-2 dB PSNR degradation caused by key-layer misallocation in other algorithms. The extended HGBA+WMMSE framework further confirms the effectiveness of joint cross-layer and physical-layer optimization, achieving continuous reductions in overall video distortion under complex channel conditions.

We present a systematic performance comparison and analysis of full-duplex (FD) and half-duplex (HD) operation modes for cell-free integrated sensing and communication (ISAC) systems. To ensure a fair comparison, we first establish an analytical framework benchmarked on the HD system, and then introduce an FD system model that incorporates a residual self-interference (SI) channel. The core of the research lies in FD systems ability to achieve significant sensing aperture gain by enabling all network nodes to perform simultaneous transmission and reception, but this concurrently introduces SI as a critical performance bottleneck. The main contribution of this paper is a systematic characterization of the fundamental performance trade-offs between FD and HD modes. We first uncover a distinct divergence in resource sensitivity within the HD architecture: while communication spectral efficiency scales monotonically with the number of transmitting nodes, sensing performance exhibits a concave trajectory, strictly peaking at a symmetric transceiver configuration. Building on this insight, we rigorously evaluate the FD mode against this optimal HD benchmark. Our analysis reveals that the superiority of the FD architecture is regime-dependent rather than absolute: while it consistently unlocks massive spectral efficiency gains for communication by utilizing the full network aperture, its sensing advantage is conditional, determined by the interplay between the potential aperture gain and the penalty induced by residual self-interference. The results indicate that the choice between FD and HD modes depends not only on the level of SI suppression but is also closely related to specific service requirements. This study provides key quantitative evidence and analytical guidance for the design and deployment of FD-ISAC systems in next-generation wireless networks.

Multi-modal fusion has emerged as a promising paradigm for modern object detection systems. However, existing works often involve substantial redundant computation during the stages of feature extraction, processing, and fusion, thereby limiting their ability to achieve both high accuracy and real-time performance. To this end, we propose Eagle, a real-time, high-accuracy detection system that integrates camera and millimeter-wave radar data via the three-level entropy-driven mechanism, which consists of three key components: (i) an entropy measurement-based feature extraction, which quantifies feature uncertainty through entropy computation, generating a weight matrix to adjust feature channels, followed by enhancing the discrimination of informative features while suppressing redundant ones; (ii) an entropy-contrast-based proposal selection, which utilizes the similarity between anchor boxes from camera and radar modalities to calculate a contrast entropy value, where low-quality proposals are filtered based on this metric, thereby reducing both false positives and false negatives; (iii) an entropy-guided-based feature fusion, which dynamically weights the feature mapping according to entropy values, achieving effective multi-modal integration through spatial-level interactions. Experimental results demonstrate that Eagle improves the mean average precision (mAP) and nuScenes detection score (NDS) by 2.3

Accurate traffic flow forecasting is essential for the stable operation and efficient scheduling of intelligent transportation systems. The key lies in identifying the complex spatio-temporal dependencies within the road network structure. In the real world, traffic data are often noisy and incomplete due to sensor failures, communication interruptions, and other unexpected disturbances. To overcome these challenges, this paper proposes an adaptive spatio-temporal self-supervised traffic flow forecasting method based on contrastive learning (ASTSS-CL). At the graph level, structural perturbations are generated by combining node centrality with nonlinear probabilities, while a learnable temporal-periodic parameter matrix and an attention-based fusion mechanism are introduced to adaptively optimize adjacency relationships. At the temporal level, complementary augmentations are designed in both the time and frequency domains. Dynamic interpolation captures continuous traffic variations, while wavelet decomposition and node-adaptive frequency masking balance low-frequency trends and high-frequency details; random masking further improves robustness to missing observations and disturbances. In addition, spatial heterogeneity learning and contrastive consistency learning are jointly employed to enhance representation quality. Experiments on the PeMS04 and PeMS08 datasets show that ASTSS-CL achieves MAE, RMSE, and MAPE values of 17.95, 28.86, and 12.07% on PeMS04, and 13.78, 22.05, and 9.46% on PeMS08, respectively, outperforming the best-performing baseline. These results validate the effectiveness of the proposed method and demonstrate its potential to support traffic management and the operation of intelligent transportation systems.

In automotive radar applications, the scanning area translates or rotates along with the motion of the vehicle, leading to spatial misalignment of multi-frame measurements. This misalignment poses a significant challenge for directly applying traditional track-before-detect algorithms based on dynamic programming (DP-TBD), consequently limiting the detection and tracking performance for weak targets. Furthermore, the traditional DP-TBD algorithms are usually applicable to scenarios with a single target or where the target motion model is fixed and unchanging. However, these approaches are clearly not suitable for actual traffic scenarios where the number of targets and their motion models are unknown. To address these issues, a novel DP-TBD algorithm based on multi-coordinate system collaboration (MCSC-DP-TBD) is proposed in this manuscript. The algorithm first converts the target state in the antenna coordinate system to a unified navigation coordinate system through multi-coordinate system transformation, thereby compensating for the observation offset caused by radar platform movement. Subsequently, within the navigation coordinate system, the maximum acceleration of targets is used to constrain the state transition range of the previous frame, thus overcoming the dependence of traditional DP-TBD algorithms on target motion models. Finally, during the trajectory backtracking stage, a successive-track-cancellation (STC) strategy is introduced to enable the simultaneous detection and tracking of an unknown number of targets. Simulation results demonstrate that the proposed MCSC-DP-TBD algorithm significantly outperforms conventional methods, offering markedly improved detection and tracking capabilities for multiple weak targets in automotive radar applications.

As a transformative technology in next-generation digital innovation, digital twin is instrumental in enhancing the efficiency and safety of traffic management while driving advancements in intelligent transportation systems. To this end, we systematically examine the primary challenges associated with the implementation of digital twin technology in transportation and introduce a novel 5 + 2 digital twin model tailored for this domain. Additionally, a comprehensive five-layer architecture is proposed to support the development of digital twin transportation. We further investigate the potential applications of digital twins in critical areas, including traffic flow management, intelligent transportation planning, resource allocation of Internet of Vehicles, traffic safety control, and assisted autonomous driving. Alongside these discussions, we provide an in-depth analysis of the current technological limitations and identify key areas requiring further research. Finally, we explore future development trajectories and the broader impact of digital twin transportation, offering new perspectives and insights to propel the evolution of intelligent transportation systems.

Millimeter-wave radar-based gesture recognition has emerged as a promising paradigm for human-computer interaction, with applications spanning diverse domains. Nevertheless, the development of robust and generalizable deep learning models in these areas remains hindered by the limited availability of large-scale training datasets, particularly in scenes involving lying postures. Existing radar data synthesis approaches are often inadequate, largely due to the scarcity and narrow scope of available data sources. To this end, we propose RadSyn, a novel system designed to synthesize large-scale, realistic radar data from either video or textual inputs. The central contribution of RadSyn lies in its ability to establish a reliable cross-modal mapping from semantic representations to radar signals. The system comprises four core components: (i) a video feature encoding network, (ii) a text feature encoding network, and (iii) a radar feature encoding network, which independently capture modality-specific representations, and (iv) a data fitting and decoding network that leverages a variational autoencoder-based mechanism to align latent distributions and synthesize realistic radar data at scale. Experimental results demonstrate that, when training the gesture recognition model solely on the synthetic radar data, RadSyn achieves an accuracy improvement of 32.88% over the state-of-the-art method.

With the increasing popularity of video streaming platforms, demand for live video traffic has surged. Low latency is crucial for real-time interaction, and mobile edge computing (MEC) offers a promising solution. By proactively caching anticipated content at edge nodes, user-perceived latency can be significantly reduced. However, most existing studies fail to exploit inter-node correlations and collaborative potential, thereby limiting prediction accuracy and affecting the overall performance of caching and scheduling. To address the above challenges, we propose PCCUA, a Prediction-driven Collaborative Caching and User Association algorithm based on attention mechanisms. Specifically, we introduce a gated fusion mechanism to dynamically balance service latency and video quality satisfaction based on individual user characteristics. We further design a multi-edge collaborative prediction model that integrates a Graph Attention Network (GAT) with local behavior modeling, enabling accurate prediction of future user requests by capturing cross-node request pattern similarities. Based on the prediction results, we develop a scalable algorithm that exploits the layered structure of Scalable Video Coding (SVC) to support efficient layered caching and user scheduling at edge nodes, thereby accommodating multi-quality user demands and promoting inter-layer resource sharing. Under typical experimental settings, the proposed prediction model achieves MSE, MAE, and R2 of 1.57, 1.16, and 0.71, respectively, showing clear superiority over existing methods. Leveraging these results, PCCUA further enhances caching performance and user experience, improving cache hit ratio, delay improvement rate, and quality matching degree by 52.50%, 57.15%, and 80.19% compared with prior approaches.

With the rapid advancement of digital twin-enabled intelligent transportation systems, efficient migration has become essential for maintaining real-time responsiveness and reliability. Existing approaches, however, primarily emphasize resource-aware optimization while neglecting the substantial overhead from state synchronization and redundant data transmission. Moreover, they typically treat digital twins as indivisible entities, overlooking optimization opportunities at the sub-model level. This limitation results in excessive migration costs and suboptimal resource utilization. To overcome these challenges, we propose a fine-grained model-level digital twin migration framework, FGDT, featuring three key components: (i) an explicit-implicit fused coupling graph construction captures both functional depen-dencies and latent collaborations among heterogeneous sub-models; (ii) a skew-aware migration pattern selection dynamically balances joint versus independent migration, thereby minimizing communication overhead and improving resource allocation; and (iii) a model-level migration strategy optimization strategy leverages dual-network PPO with a soft-constraint co-placement mechanism to support adaptive, fine-grained migration decisions. Extensive experiments validate the effectiveness of FGDT, which significantly reduces average system latency while maintaining low migration overhead, thereby enhancing both resource efficiency and overall system performance.

With the growing prevalence of privacy risks and data leakage in the Internet of Vehicles (IoV), federated unlearning (FU) has emerged as a promising paradigm to safeguard user privacy by selectively removing client contributions from global models. However, although the existing FU methods based on retraining can achieve complete data influence elimination, their computational overhead is relatively large. Furthermore, most FU methods based on fine-tuning are usually based on static client selection strategies, without considering the model iteration bias caused by the dynamics of vehicle nodes. They also lack a dynamic adjustment mechanism for the intensity of unlearning, and thus are difficult to be applied in the IoV environment. To this end, we propose PSODS-FU, a federated unlearning framework for Internet of Vehicles based on particle swarm optimization and dynamic scoring drive. Firstly, we design a dynamic vehicle node selection strategy, mainly through the particle swarm optimization algorithm to dynamically adjust the weights of the calculation slope, communication load and energy consumption resources, and screen out highly stable nodes to improve the accuracy of the global model. Secondly, we design a dynamic scoring-driven federated unlearning strategy, which dynamically generates unlearning factors based on historical average stability scores and environmental adaptive benchmarks, precisely quantifies and eliminates the influence of target vehicle nodes, and uses knowledge distillation technology to compensate for the performance degradation of the model. The experimental results show that PSODS-FU outperforms existing methods in terms of prediction accuracy, computational time, and attack precision, and performs more closely to the retrained reference model on metrics such as test accuracy gap, parameter distance, and prediction disagreement rate, thereby significantly optimizing the balance between privacy protection and model performance.

3D object detection is a crucial task for autonomous vehicles to perceive traffic environments. Existing methods typically employ tightly coupled feature fusion strategies with fixed sensor combinations, but it fails to adequately capture the modality-specific characteristics, resulting in suboptimal object detection performance. To this end, we propose Chameleon, a novel multi-sensor decoupling system capable of selecting the appropriate sensor combination for object detection across diverse traffic conditions, which consists of two key components: (i) an uncertainty-aware contribution calculation component leverages the uncertainty perceived by sensors to predict the parameters of traffic factors, followed by evaluating their importance; (ii) a mutual information-enhanced sensor combination optimization component leverages mutual information calculations to enhance the mixture of experts and improve the reliability of sensor combination predictions, followed by achieving adaptive multi-sensor decoupling to ensure accurate 3D object detection while reducing inference latency. We implement and evaluate Chameleon using the nuScenes and nuScenes-C datasets. The experimental results show that Chameleon achieves average improvements of 1.10% in the mAP and 0.61% in the NDS compared to the state-of-the-art method across various traffic scenes.

Federated Learning (FL) has emerged as a key distributed framework for processing real-time vehicular data in the Internet of Vehicles (IoV), aiming to enhance driving experiences and service quality. However, challenges such as network congestion, limited signal coverage leading to latency, and inefficiencies arising from data and device heterogeneity hinder FL performance in IoV environments. To address these issues, we propose HierFed, a hierarchical federated learning algorithm that combines synchronous and asynchronous aggregation strategies, which comprises two components: (i) an asynchronous cache aggregation mechanism, where client-side cache updates are transmitted to the edge server for asynchronous aggregation. By calibrating the relationship between cache updates and model deviations, clients can update models without synchronous waiting, thereby mitigating latency; (ii) a synchronous aggregation mechanism, where the cloud server optimizes global model updates by computing aggregation weights under gradient normalization and constraint conditions, followed by reducing inter-client model inconsistency and enhances overall model convergence. Experimental results show that HierFed outperforms all baselines, achieving an 8.83% improvement in model accuracy at the edge tier (asynchronous FL), a 13.84% improvement at the cloud tier (synchronous FL), and a 10.79% overall improvement in hierarchical FL.

Digital twin (DT) migration technology is pivotal for ensuring seamless synchronization between physical entities and their virtual counterparts. However, in complex urban environments, high device mobility, dynamic network topology, and uncertain wireless channel conditions often lead to suboptimal migration decisions. Such inefficiencies exacerbate resource contention and diminish migration timeliness, thereby increasing DT state deviation and compromising service quality. To address these challenges, this article proposes an AP group-enhanced DT edge network (DITEN) model, where multiantenna access points (APs) are integrated as relay nodes to optimize channel quality and transmission reliability. Building on this, a group-collaborative multiagent proximal policy optimization (GC-MAPPO) migration strategy is presented. The strategy formulates the migration problem as a partially observable Markov decision process (POMDP). Specifically, the K-means++ clustering algorithm is first employed to construct optimal AP collaborative groups for mobile devices; subsequently, the multiagent proximal policy optimization (MAPPO) algorithm is utilized to derive optimal migration policies in dynamic environments. Experimental results demonstrate that, compared to existing baselines, the proposed GC-MAPPO scheme reduces the average synchronization delay by 6.69%-37.05% and decreases DT state deviation by 29.24%-82.91%.

Digital Twins (DTs) aim to achieve real-time integration between the virtual and physical worlds, demonstrating significant application potential in emerging fields such as smart cities and intelligent transportation. However, the reliance of DT on ultra-low latency and high computational resources poses considerable challenges for their deployment at edge nodes. Additionally, wireless signal interference in densely built environments further complicates edge deployments. To address these issues, this paper proposes an IRS-enhanced digital twin edge network architecture to improve the wireless channel quality for devices. Based on this architecture, considering device mobility and network dynamics, a digital twin dynamic placement strategy based on multi-objective deep reinforcement learning (MODRLDF) is proposed. The problem is formulated as a constrained multi-objective optimization problem, and a multi-objective double deep Q-learning method with a dynamic penalty mechanism (MODDQN-HER) is introduced. Unlike existing multi-objective reinforcement learning algorithms, the proposed strategy enhances training efficiency through hindsight experience replay and adaptively handles constraints via a dynamic penalty mechanism. It further obtains the optimal solution to the placement problem by balancing the interaction cost and service duration of device digital twins. Experimental results demonstrate that compared to existing approaches, the proposed DT placement strategy in this paper achieves a maximum reduction of 15.3% in average synchronization delay of devices. Moreover, it achieves a maximum reduction of 27.1% in DT migration rate and an average increase of 10.1% in service duration.

With the rapid proliferation of intelligent video analytics in real-time applications such as the Internet of Vehicles and urban surveillance, Mobile Edge Computing (MEC) systems face persistent challenges, including complex inter-frame dependencies, severe bandwidth fluctuations, and intensive resource contention. Conventional offloading strategies based on fixed rules or static weights are often inadequate for maintaining robustness in scenarios with conflicting multi-objective requirements. To address these challenges, this paper proposes PGN-MO-DDQN, an adaptive multi-objective reinforcement learning framework for task offloading and scheduling, driven by a Preference Generation Network (PGN). The proposed framework leverages the multi-objective architecture of Double-DQN and incorporates a PGN to automatically produce dynamic weight vectors for latency, load balancing, and analytical accuracy (mean average precision, mAP) according to real-time system states, while dynamically determining the offloading ratio between local and edge processing to balance communication latency and computational load, thereby enabling adaptive multi-objective optimization. Experimental evaluations conducted on the EdgeSimPy platform show that, compared with representative baseline algorithms such as Greedy, Fixed-DDQN, HRL-V2I, and TOLB, PGN-MO-DDQN reduces average task latency by 17%, decreases server load imbalance by 13%, and improves mAP by 5.8%. Overall, the proposed framework provides a robust solution for adaptive multi-objective video offloading, effectively balancing latency, accuracy, and resource use in dynamic edge environments.

Video transmission, as one of the indispensable core services in the Internet of Vehicles (IoV), is confronted with numerous challenges such as the dynamics in the IoV environment, the limited resources, and the demand of vehicles for high-quality user experience (quality of experience, QoE). In real-time video streaming scenarios, multicast optimization strategies, including convex optimization, game theory, stochastic optimization, and so on, usually only group based on channel quality without considering task types and priorities, which may lead to the mixture of urgent tasks and ordinary tasks, affecting QoE. Therefore, we propose a task-aware three-stage collaborative optimization framework (TARA-IoV). The objective is to prioritize critical mission video services under limited bandwidth while maximizing the overall QoE. The framework first performs dynamic and adaptive vehicle grouping based on multidimensional features, including task type, priority, geographical location, and channel state. Second, it conducts QoE-driven video quality layer selection leveraging scalable video coding (SVC). Finally, it employs a deep reinforcement learning agent to dynamically allocate bandwidth with explicit task-priority awareness under resource constraints. Evaluations on a real-world vehicle trajectory dataset demonstrate that TARA-IoV achieves improved QoE performance and more stable video delivery compared with existing schemes.

Digital twin technology has emerged as a crucial paradigm for enhancing the responsiveness and management efficiency of transportation systems. A key technology to realize this vision is the real-time and accuracy twin placement. However, the limited resources and coverage of edge servers make it challenging to achieve effective twin placement in dynamic environments, where maximizing resource utilization and minimizing communication latency are crucial. To this end, we propose Nereus, which consists of four key modules: (i) a heterogeneous demand prediction module utilizes a heterogeneous graph neural network to capture complex relationships between twins and servers, facilitating accurate prediction of resource demands and loads; (ii) a feature-driven clustering module incorporates multi-dimensional twin features using principal component analysis and dynamic k-means clustering to adaptively generate twin groups; (iii) an adaptive association module exploits an attention mechanism to dynamically adjust twin group assignments; (iv) a multi-level placement optimization module employs a hierarchical actor-critic algorithm to refine twin placement strategies, enhancing resource utilization and minimizing communication latency. Experimental results demonstrate that, compared to state-of-the-art methods, Nereus achieves a 70.24% reduction in communication latency and improves computation resource matching by 52.43%.