Cross-view geo-localization is a crucial task with diverse applications, yet it remains challenging due to the significant variations in viewpoints and visual appearances between images from different perspectives. While recent advancements have been made, existing methods often suffer from high model complexity, excessive resource consumption, and the impact of sample learning difficulty on optimization. To overcome these limitations, we optimize the Vision Mamba (Vim) model, built on a State Space Model (SSM) architecture, by replacing the traditional classification head with Channel Group Pooling (CGP) for efficient feature integration. This optimization reduces model parameters by 1.5% and computational complexity by 0.4%. Additionally, we propose a novel Dynamic Weighted Batch-tuple Loss (DWBL) to dynamically adjust the weighting of negative samples, improving model performance. By combining CGP and DWBL, we develop an efficient end-to-end network, VimGeo, which achieves state-of-the-art performance with enhanced computational efficiency. Specifically, VimGeo achieves a Recall@1 of 81.67% on the CVACT_test dataset, outperforming prior approaches. Extensive experiments on CVUSA, CVACT, and VIGOR datasets validate VimGeo's effectiveness and competitiveness in cross-view geo-localization tasks, achieving the leading results among sequence modeling-based methods. The implementation is available at: https://github.com/VimGeoTeam/VimGeo.

Abstract To better provide fast computing services, vehicular edge computing can improve the quality of service and quality of experience for intelligent transportation in 6G by reducing task transmission delay. However, vehicular edge networks face network capability limitations and privacy issues in practice. High‐speed vehicles and the time‐varying environment make them unpredictable. In the meantime, smart vehicles with distinct computation capabilities need to process various tasks with different resource requirements, which will inevitably cause untimely task offloading and massive energy consumption. This paper proposes to use the space‐air‐ground integrated network with blockchain to enhance the network capability and the privacy protection of vehicular edge networks. The digital twin is taken to better capture the dynamic characteristics of vehicles and the entire environment. The urgency level is introduced to meet the delay requirements of different tasks, while considering the impact of digital twin deviation on task offloading. Moreover, the selection algorithm and the task distribution algorithm based on the improved genetic algorithmare are proposed to obtain the optimal offloading strategy. Simulation results demonstrate that, compared with the existing algorithms, the proposed scheme can maximize the system utility while diminishing the total time for task processing.

Advanced driver assistance systems (ADASs) enhance driving safety and convenience by providing auxiliary functions. However, traditional rule-based or learning-based ADAS lack the capability for commonsense-based environmental understanding and multisensor data fusion, which leads to limitations in complex dynamic environments. Multimodal large language models (MLLMs) can effectively integrate data from different modalities and possess strong environmental perception and commonsense reasoning abilities, offering more intelligent driver assistance services within Internet of Things (IoT) networks. In this article, we propose a cloud-edge collaborative ADAS based on MLLMs, utilizing IoT networks by deploying a smaller model, CogVLM2, at the edge and a larger model, ChatGPT-4o, in the cloud to achieve collaborative driver assistance services. Specifically, we first reannotate the BDD-X dataset and use it to fine-tune CogVLM2 with LoRA, while applying few-shot learning to ChatGPT-4o to enhance their understanding and decision-making capabilities in traffic scenarios. We then formulate service latency, energy consumption, and Quality-of-Service (QoS) models for the cloud-edge collaborative ADAS in IoT networks, optimizing the combination of these models. Finally, we design an improved DDPG-based task offloading algorithm by introducing a multistep reward mechanism and using a diffusion model to generate noise, aiming to determine the optimal execution location (i.e., cloud, edge, or local) for each task. Experimental results show that both CogVLM2 and ChatGPT-4o can achieve basic ADAS functionality. After fine-tuning and few-shot learning, their task success rates were significantly improved. Moreover, compared to other mainstream deep reinforcement learning-based task offloading algorithms, the improved DDPG task offloading algorithm demonstrates better performance in latency, energy consumption, and QoS within IoT networks.

With the development of intelligent transportation systems (ITSs), digital twin (DT) technology is becoming increasingly widespread in the application of connected automated vehicles (CAVs) to enhance driving safety. However, when DT systems are used for driving safety decisions through virtual control of reality and virtual reflection of reality, decision errors may occur, which can be fatal for the driving safety of CAVs. The main reasons are attributed to three aspects: 1) the accuracy; 2) the communication delay; and 3) the safety control of the DT system. In this article, we study to improve the accuracy and safety of the DT system decisions with communication delay. First, we considered powertrain factors to construct a high-precision and high-fidelity DT system. We use the Goodness-of-Fit Functions (GoFs) and Measure-of-Performances (MoPs) to fit the vehicle’s model and carry out error measurements in the DT system. Second, we analyze the stability of the DT system using plant stability and string stability under time delay. The effective range of time delay ensures the accuracy and stability of the DT system, and provides a safety constraint for the design of the CAV’s controller. Finally, we propose a DT-assisted robust safety-critical traffic control (RSTC) strategy based on the control barrier functions (CBFs). This strategy ensures the driving safety of CAVs with preceding and following vehicles while maintaining traffic stability. The theoretical analysis and experimental results present that the proposed scheme can effectively avoid conflicts and crash risks to ensure driving safety.

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

The coupling of federated learning (FL) and multi-access edge computing (MEC) has the potential to foster numerous applications. However, it poses great challenges to train FL fast enough with limited communication and computing resources of mobile edge devices. Motivated by recent development in ultra fast wireless transmissions and promising advances in artificial intelligence (AI) computing hardware of mobile devices, in this paper, we propose a time efficient FL over future mobile edge devices, called dynamic batch sizes assisted federated learning (DBFL) with convergence guarantee. The DBFL allows batch sizes to increase dynamically during training, which can unleash the computing potential of GPU’s parallelism for on- device training and effectively leverage the fast wireless transmissions (WiFi-6, 5G, 6G, etc.) of mobile edge devices. Furthermore, based on the derived DBFL’s convergence bound, we develop a batch size control scheme to minimize the total time consumption of FL over mobile edge devices, which trade-offs the “talking”, i.e., communication time, and “working”, i.e., computing time, by adjusting the incremental factor appropriately. Extensive simulations are conducted to validate the effectiveness of our proposed DBFL algorithm and demonstrate that our scheme outperforms existing time efficient FL approaches in terms of the total time consumption in various settings.

Federated learning (FL), an emerging distributed machine learning paradigm, in conflux with edge computing is a promising area with novel applications over mobile edge devices. In FL, since mobile devices collaborate to train a model based on their own data under the coordination of a central server by sharing just the model updates, training data is maintained private. However, without the central availability of data, computing nodes need to communicate the model updates often to attain convergence. Hence, the local computation time to create local model updates along with the time taken for transmitting them to and from the server result in a delay in the overall time. Furthermore, unreliable network connections may obstruct an efficient communication of these updates. To address these, in this paper, we propose a delay-efficient FL mechanism that reduces the overall time (consisting of both the computation and communication latencies) and communication rounds required for the model to converge. Exploring the impact of various parameters contributing to delay, we seek to balance the trade-off between wireless communication (to talk) and local computation (to work). We formulate a relation with overall time as an optimization problem and demonstrate the efficacy of our approach through extensive simulations.

Deep learning holds a great promise of revolutionizing healthcare and medicine. Unfortunately, various inference attack models demonstrated that deep learning puts sensitive patient information at risk. The high capacity of deep neural networks is the main reason behind the privacy loss. In particular, patient information in the training data can be unintentionally memorized by a deep network. Adversarial parties can extract that information given the ability to access or query the network. In this paper, we propose a novel privacy-preserving mechanism for training deep neural networks. Our approach adds decaying Gaussian noise to the gradients at every training iteration. This is in contrast to the mainstream approach adopted by Google's TensorFlow Privacy, which employs the same noise scale in each step of the whole training process. Compared to existing methods, our proposed approach provides an explicit closed-form mathematical expression to approximately estimate the privacy loss. It is easy to compute and can be useful when the users would like to decide proper training time, noise scale, and sampling ratio during the planning phase. We provide extensive experimental results using one real-world medical dataset (chest radiographs from the CheXpert dataset) to validate the effectiveness of the proposed approach. The proposed differential privacy based deep learning model achieves significantly higher classification accuracy over the existing methods with the same privacy budget.

Federated learning is a promising tool in the Internet-of-Things (IoT) domain for training a machine learning model in a decentralized manner. Specifically, the data owners (e.g., IoT device consumers) keep their raw data and only share their local computation results to train the global model of the model owner (e.g., an IoT service provider). When executing the federated learning task, the data owners contribute their computation and communication resources. In this situation, the data owners have to face privacy issues where attackers may infer data property or recover the raw data based on the shared information. Considering these disadvantages, the data owners will be reluctant to use their data to participate in federated learning without a well-designed incentive mechanism. In this article, we deliberately design an incentive mechanism jointly considering the task expenditure and privacy issue of federated learning. Based on a differentially private federated learning (DPFL) framework that can prevent the privacy leakage of the data owners, we model the contribution as well as the computation, communication, and privacy costs of each data owner. The three types of costs are data owners' private information unknown to the model owner, which thus forms an information asymmetry. To maximize the utility of the model owner under such information asymmetry, we leverage a 3-D contract approach to design the incentive mechanism. The simulation results validate the effectiveness of the proposed incentive mechanism with the DPFL framework compared to other baseline mechanisms.

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

With the rapid increase of mobile devices, the computing load of roadside cloudlets is fast growing. When the computation tasks of the roadside cloudlet reach the limit, the overload may generate heat radiation problem and unacceptable delay to mobile users. In this paper, we leverage the characteristics of buses and propose a scalable fog computing paradigm with servicing offloading in bus networks. The bus fog servers not only provide fog computing services for the mobile users on bus, but also are motivated to accomplish the computation tasks offloaded by roadside cloudlets. By this way, the computing capability of roadside cloudlets is significantly extended. We consider an allocation strategy using genetic algorithm (GA). With this strategy, the roadside cloudlets spend the least cost to offload their computation tasks. Meanwhile, the user experience of mobile users are maintained. The simulations validate the advantage of the propose scheme.

Cloud-enabled vehicular network is an emerging paradigm which utilizes cloud computing to enhance the performance of vehicular network. But some issues still need to be addressed and we focus on the pseudonym resources management, which is crucial for vehicles to guarantee location privacy. A new three-plane hierarchical architecture with software defined network technology is proposed to manage the pseudonym resources. We use two-sided matching theory to solve the pseudonym resources allocation problem among pseudonym pools in different roadside unit clouds. Numerical results show that our proposed approach optimizes the pseudonym resources utilization and also improves the privacy entropy of vehicles.

The limited lifetime of wireless nodes has become the essential bottleneck of system performance and wide-scale deployment of wireless networks. In this paper, we consider a practical mobile chargeable network in which each single mobile charger is able to charge multiple target nodes simultaneously. To tackle the problem, the cooperative grouping of the wireless nodes is proposed to reduce the number of traversing spots of the mobile chargers. Meanwhile, the cooperative charging among the mobile chargers is studied to conserve their energy consumption. The numerical results show that the proposed scheme outperforms existing strategies in both even-density and uneven-density wireless networks.