Secure Vehicular Communication for IOV Using CNN

The Internet of Vehicles (IoV) is revolutionizing intelligent transportation by enabling seamless data exchange between vehicles and infrastructure. However, high dissemination delay in vehicular communication poses challenges to real-time decision-making, traffic management, and safety. This study employs a deep learning-based approach to predict and optimize dissemination delay in IoV networks. By leveraging Convolutional Neural Networks (CNN) and Long Short- Term Memory (LSTM) networks, the system accurately models spatial and temporal dependencies in vehicular data. Furthermore, reinforcement learning using Q-learning is applied to optimize peer selection, reducing information propagation time. The proposed approach utilizes key IoV parameters such as vehicle speed, traffic density, network connectivity, and transaction rate to minimize latency and improve communication efficiency. Experimental results demonstrate a significant reduction in dissemination delay, making the system a scalable and effective solution for real- time vehicular communication. This work contributes to the advancement of intelligent transportation by enhancing data dissemination strategies in dynamic IoV environments.