Data Driven Machine Learning Model for Traffic Flow Forecasting using VANET

This study focuses on the design and development of data-driven machine learning model using VANET sensing. The proposed model leverages the dynamic and decentralized nature of VANETs to gather extensive traffic-related data from various sensors embedded in vehicles. Advanced machine learning algorithms LSTM networks, CNNs, and hybrid models, are employed to analyze and predict traffic flow patterns. This model with VANET data aims to address the complexities and nonlinearities inherent in traffic dynamics. This study advances the subject of intelligent transportation systems by providing a scalable and helpful traffic management solution. The implementation of this model can lead to reduced traffic congestion, lower travel times, and enhanced road safety. Future work will explore the formation of additional data sources and the utilization of more intelligent machine learning techniques to further improve the robustness and accuracy of traffic flow forecasts.