9 May 2024 in IEEE Transactions on Vehicular Technology
Data sharing plays an important role in assisting traffic management centers to obtain traffic operation status and make accurate traffic decisions. However, there are still many security problems associated with data sharing, such as privacy breaches. To address these problems, we propose a s ecurity- e nhanced d ata s haring scheme with location privacy preservation for Internet of Vehicles, called SEDS. Specifically, the scheme first exploits an autonomous and controllable dynamic pseudonym mechanism to protect the privacy of vehicles' location, thereby preventing the leakage of vehicle trajectory information. Secondly, SEDS utilizes homomorphic encryption to aggregate data at the edge of the network to achieve privacy protection of data content. Thirdly, SEDS uses batch verification with privacy protection to achieve integrity and authenticity of data, and can effectively filter false data. Finally, SEDS applies blockchain technology to store shared data, which can guarantee the immutability of shared data. The security proof and analysis show that SEDS has security features, containing confidentiality, location privacy, authentication and data integrity, filtering false data and immutability. Experimental results exhibit that the SEDS is superior to other recently proposed schemes in terms of computational and communication overhead, as well as network performance.
12 March 2024 in The Journal of Supercomputing
27 November 2025 in IEEE Transactions on Knowledge and Data Engineering
Traffic prediction is essential for modern transportation systems, enhancing traffic management and urban planning. Accurate predictions of traffic flow and speed are crucial for understanding road usage, mitigating congestion, and providing real-time traffic monitoring and dynamic route guidance, thus improving road safety and infrastructure efficiency. Traditional research has often focused on predicting traffic flow or speed independently, leading to higher resource consumption due to the need for separate models. Few studies have explored the simultaneous prediction of both metrics, with recent attempts failing to account for spatial correlations, resulting in suboptimal performance. To address these challenges, we propose MTNet, a multi-task learning framework for joint traffic flow and speed prediction. MTNet employs a Transformer-like Encoder-Decoder architecture to process and enhance feature representations, capturing complex spatio-temporal correlations. Specifically, MTNet extracts intra-task dependencies using a cross-task interaction module and models task-specific spatiotemporal dependencies using spatial and temporal-aware modules with cascaded residual structures. Additionally, spatio-temporal positional encoding is integrated to increase awareness of long-term and long-distance dependencies. Extensive experiments on three diverse traffic datasets—Manchester, PeMSD4, and PeMSD8—demonstrate that MTNet significantly outperforms state-of-the-art methods in both traffic flow and speed prediction. MTNet achieves substantial improvements in prediction accuracy and efficiency, striking an optimal balance between performance and computational resource usage.
3 November 2024 in International Journal of Machine Learning and Cybernetics