With the rapid development of the Internet of Vehicles (IoV), the tight coupling between In-Vehicle Networks (IVN) and External Vehicle Networks (EVN) has made vehicular systems vulnerable to sophisticated cross-network attack chains. Existing Intrusion Detection Systems (IDS), however, typically operate in isolation on either IVN or EVN, and lack effective context-aware mechanisms for capturing inter-domain dependencies. To overcome this limitation, we propose CATwin-IDS, a context-aware intrusion detection framework that integrates digital twin technology with a lightweight Distilled Bidirectional Encoder Representations from Transformers (DistilBERT) model. In our design, Conditional Mutual Information (CMI) and Borderline Synthetic Minority Over-sampling Technique (Borderline-SMOTE) are applied for feature optimization and data balancing, while Temporal Self-Attention (TSA) enhances the modeling of spatiotemporal dependencies across heterogeneous traffic. The digital twin provides real-time bidirectional synchronization and a simulation environment, enabling proactive adaptation to dynamic threats. Experimental results on benchmark datasets (Car-Hacking, CICIoV2024, CICIDS2018, CICIoT2023) demonstrate that CATwin-IDS achieves higher accuracy and real-time efficiency compared with state-of-the-art methods, providing a holistic solution for securing IoV against cross-network intrusions.

With the rapid advancement of the Internet of Vehicles (IoV), the scale of intelligent connected vehicles has expanded dramatically. Alongside this, the development of the low-altitude economy (LAE) has introduced new types of nodes, such as unmanned aerial vehicles (UAVs) operating in low-altitude airspace. This has led to an exponential increase in the demand for secure and efficient authentication between low-altitude UAVs and ground vehicles. The Chinese Remainder Theorem (CRT), characterized by its efficient computation, low storage requirements, high parallelism, and excellent real-time performance, CRT-based authentication schemes are highly compatible with the resource-constrained and low-latency requirements of IoV scenarios. However, existing CRT-based authentication schemes suffer from scalability bottlenecks. As the number of connected nodes increases, CRT-based authentication schemes exhibit a superlinear growth trend in computational overhead, posing significant challenges to their practical deployment scalability. In response to this challenge, we propose a Dynamic Group Management and Authentication Scheme based on CRT (DGMA-CRT). The proposed scheme employs dynamic grouping of vehicles to enable efficient intra-group domain key updates, avoiding the significant communication overhead caused by global domain key updates. The parameters for domain key updates depend solely on the group size, not the overall system scale, thus significantly enhancing efficiency while ensuring scalability. Furthermore, the scheme incorporates Shamir’s threshold mechanism to mitigate the risks of single-point attacks in key management and leverages elliptic curve cryptography (ECC) to establish a secure foundation for authentication. Simulation results show that DGMA-CRT, by utilizing grouped key updates and cryptographic mechanisms, significantly reduces computational overhead while maintaining robust security. Additionally, the scheme retains high efficiency as the system scales, demonstrating its suitability for large-scale IoV applications.

Rate splitting multiple access (RSMA) is a powerful multiple access technology that enables communication systems to achieve both reliable and fair data transmission by splitting and encoding user messages into common and private streams. This capability is particularly critical for space-air-ground-sea (SAGS) integrated networks, where heterogeneous nodes (e.g., satellites, UAVs, and underwater sensors) coexist with significant channel quality disparities. The common stream is formed by consolidating the diverse common messages that all users can decode, allowing the system to balance resource allocation and maintain reliable connectivity even for users with weaker channel conditions. Nevertheless, the performance of the common stream is often limited by the user with the weakest channel strength, a prevalent challenge in SAGS integrated networks with mixed near-far field communications and dynamic topology. To address this issue, this study proposes a generalized RSMA strategy to mitigate the rate limitation of common streams in RSMA systems, thereby enhancing system fairness and overall performance. The solution holds potential for crossdomain applications where strong and weak maritime/aerial users share spectrum resources. Furthermore, an algorithm is designed to optimize Max-min fairness (MMF) rate among all users. This is formulated as a non-convex optimization problem, which poses significant challenges for direct solution. To tackle this challenge, we design a low-complexity suboptimal iterative algorithm employing the successive convex approximation (SCA) method. Simulations demonstrate that the proposed generalized RSMA system outperforms traditional one-layer RSMA system and other existing counterparts, particularly in systems with weak users, by effectively enhancing the MMF rate and overall system fairness. This improvement suggests broader applicability for future integrated networks requiring unified management of heterogeneous links.

Vehicle trajectory prediction is a key technology in autonomous driving systems, playing a decisive role in ensuring autonomous driving safety and improving traffic efficiency. In complex traffic environments, the dynamic interactions between vehicles and pedestrians are extremely intricate, posing great challenges for accurate trajectory prediction. Traditional physical models exhibit obvious limitations when facing the nonlinear behaviors of traffic participants, while existing deep learning methods, although improved to some extent, still struggle to meet the practical application requirements in terms of computational efficiency and multimodal prediction capabilities. To address this, this paper proposes a novel vehicle trajectory prediction method based on Group-Rational KAN Enhanced Motion Transformer (GR-KAMT). This method combines the nonlinear modeling capability of the Kolmogorov-Arnold Network (KAN) with the attention mechanism of Transformer, effectively enhancing the trajectory prediction ability for complex scenes. Its uniqueness lies in the introduction of the efficient GR-KAN module, which demonstrates higher efficiency and accuracy in handling complex data relationships compared to traditional Multilayer Perceptrons (MLP), while supporting multimodal trajectory prediction to more comprehensively capture the behavioral patterns of traffic participants. Experiments on the NuScenes dataset demonstrate that GR-KAMT significantly outperforms existing methods in key performance indicators such as minimum average displacement error (minADE) and minimum final displacement error (minFDE), providing reliable support for safe decision-making in autonomous driving.

Edge caching is crucial for enhancing the performance of vehicular networks primarily by reducing service latency and improving data availability. However, existing research typically focuses only on unidirectional vehicle movement, which limits its application in complex scenarios, such as those in urban areas. To address this, we propose two novel edge caching strategies specifically tailored for the intricate vehicle movements and traffic signal controls at urban intersections, taking into account temporal variability of content popularity, making them more practical in the real world. The first caching strategy, based on dynamic programming (DP), is suited for scenarios with low traffic flow, providing an optimal solution and serving as a benchmark for evaluating the performance of the second strategy. This benchmark assesses how closely the second strategy approaches the optimal solution. The second strategy employs deep reinforcement learning (DRL) and is suitable for high traffic scenarios. Its performance, when compared with the DP approach in low traffic scenarios, demonstrates results that are near-optimal. Simulation outcomes indicate that the DRL strategy effectively adapts to changes in content popularity, significantly optimizing service latency and hit rates.

For vehicularad hocnetworks (VANETs), edge caching has attracted considerable research attention to maximize the efficiency and reliability of infotainment applications. In this article, we propose a two-layer distributed content caching scheme for VANETs by jointly exploiting the cache at both vehicles and roadside units (RSUs). Specifically, we formulate the content caching problem to minimize the overall transmission delay and cost as a nonlinear integer programming (NLIP) problem and propose an alternate dynamic programming search (ADPS)-based algorithm to solve it. In ADPS, we divide the original problem into three subproblems and then we use the dynamic programming (DP) method to solve each subproblem separately. To reduce the complexity, we further propose a cooperation-based greedy (CBG) algorithm to solve the large-scale original problem. Both numerical simulation results and experiments in the testbed show that the proposed caching scheme outperforms existed caching schemes, and the transmission delay and cost can be reduced by 10% and 24%, respectively, while the hit ratio can be increased by 30% in a practical environment, as compared to the popularity-based caching scheme.

Cloud gaming has emerged as a promising approach to more affordable and accessible games. By rendering high-end video games in the cloud and streaming encoded game scenes to players via the broadband networks, users are relieved from downloading or installing game software. With cloud gaming, users can easily play high-end 3-D video games on any devices anytime and anywhere. In this paper, we conducted a comprehensive measurement study of a leading cloud gaming system in China, namely, CloudUnion. Unlike the previous work, our measurement study was based on an in-depth understanding of the internal mechanisms of CloudUnion, and thus we were able to reveal problems that cannot be observed in a black-box approach. We built a dedicated measurement platform, which enables us to study CloudUnion from different views, including the global view, local view, and user view. We also conducted a comparison study with another cloud gaming system, namely, GamingAnywhere. Our measurement results unveil the pros and cons of the current cloud gaming system design, and bring forth important insights about the cloud infrastructure, user behaviors, traffic patterns, user-perceived quality, and so on. Our work will be valuable for the design of future cloud gaming systems.

As a new paradigm, cloud gaming allows users to play high-end video games instantly without downloading or installing the original game software. In this paper, we first conduct a series of well-designed active and passive measurements on a large-scale cloud gaming platform and identify the significant diversity in the queueing delay and response delay among users. We note that the latency problem largely results from user-specified request routing and inelastic server provisioning. To address latency problem of the cloud gaming platform, we further propose an online control algorithm called iCloudAccess to perform intelligent request dispatching and server provisioning. Our main objective is to cut down the provisioning cost of cloud gaming service providers while still ensuring the user quality-of-experience requirements. We formulate the problem as a constrained stochastic optimization problem and apply the Lyapunov optimization theory to derive the online control algorithm with provable upper bounds. We also conduct extensive trace-driven simulations to evaluate the effectiveness of our algorithm, and our results show that our proposed algorithm achieves significant gain over other alternative approaches.

Mobile video traffic, owing to the rapid adoption of smartphones and tablets, has been growing exponentially in recent years and started to dominate the mobile Internet. In reality, mobile video applications commonly adopt buffering techniques to handle bandwidth fluctuation and minimize the impact of stochastic wireless channels on user experiences. However, recent measurement work reveals that mobile users tend to abort more frequently than PC users during viewing videos. Such a high abortion rate results in a significant wastage of buffered video data, which is directly translated into monetary and energy cost for mobile users. In this paper, we propose an intelligent buffer management strategy called CBM (Cost-aware Buffer Management), for mobile video streaming applications. Our purpose is to minimize cost induced by un-consumed video data while respecting certain user experience requirements. To this objective, we formulate the problem into a constrained stochastic optimization problem, and apply the Lyapunov optimization theory to derive the corresponding online strategy for cost minimization. Different from conventional heuristic-based strategies, our proposed CBM strategy can provide provably performance guarantee with explicit bounds. We also conduct extensive simulations to validate the effectiveness of our proposed strategy and our experimental results show that CBM achieves significant gains over existing schemes.

MOTIVATION: Target enrichment, also referred to as DNA capture, provides an effective way to focus sequencing efforts on a genomic region of interest. Capture data are typically used to detect single-nucleotide variants. It can also be used to detect copy number alterations, which is particularly useful in the context of cancer, where such changes occur frequently. In copy number analysis, it is a common practice to determine log-ratios between test and control samples, but this approach results in a loss of information as it disregards the total coverage or intensity at a locus. RESULTS: We modeled the coverage or intensity of the test sample as a linear function of the control sample. This regression approach is able to deal with regions that are completely deleted, which are problematic for methods that use log-ratios. To demonstrate the utility of our approach, we used capture data to determine copy number for a set of 600 genes in a panel of nine breast cancer cell lines. We found high concordance between our results and those generated using a single-nucleotide polymorphsim genotyping platform. When we compared our results with other log-ratio-based methods, including ExomeCNV, we found that our approach produced better overall correlation with SNP data. AVAILABILITY: The algorithm is implemented in C and R and the code can be downloaded from http://bioinformatics.nki.nl/ocs/ CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Facial activities are the most natural and powerful means of human communication. Spontaneous facial activity is characterized by rigid head movements, non-rigid facial muscular movements, and their interactions. Current research in facial activity analysis is limited to recognizing rigid or non-rigid motion separately, often ignoring their interactions. Furthermore, although some of them analyze the temporal properties of facial features during facial feature extraction, they often recognize the facial activity statically, ignoring the dynamics of the facial activity. In this paper, we propose to explicitly exploit the prior knowledge about facial activities and systematically combine the prior knowledge with image measurements to achieve an accurate, robust, and consistent facial activity understanding. Specifically, we propose a unified probabilistic framework based on the dynamic Bayesian network (DBN) to simultaneously and coherently represent the rigid and non-rigid facial motions, their interactions, and their image observations, as well as to capture the temporal evolution of the facial activities. Robust computer vision methods are employed to obtain measurements of both rigid and non-rigid facial motions. Finally, facial activity recognition is accomplished through a probabilistic inference by systemically integrating the visual measurements with the facial activity model.