Intelligent Transportation System using Vehicular Networks in the Internet of Vehicles for Smart cities

Modern smart cities face significant mobility difficulties, and the combination of Intelligent Transportation Systems (ITS) and Vehicular Networks (VN) within the context of the Internet of Vehicles (IoV) promises a transformative approach to tackling these challenges. This abstract captures the core of this ground-breaking approach. Traffic congestion, environmental challenges, and road safety are crucial considerations in the context of smart cities. Traffic management systems and automobiles can communicate real-time data thanks to the support provided by vehicular networks. By incorporating automobiles into the larger IoT ecosystem, the Internet of automobiles expands this connection and broadens the range of available services and applications. This study introduces a novel Intelligent Transport System designed for the context of vehicular network traffic based on Internet of Vehicles (IoV) in smart cities. The machine learning models used to build the system are Decision Tree (DT), Support Vector Machine (SVM), Neural Network, K-Nearest Neighbours (KNN), and Naive Bayes. The simulation results show the system's effectiveness in producing astonishing results through a thorough review. In particular, it maintains computing efficiency while achieving a noteworthy level of detection accuracy. This success can be due to the skilful use of feature selection and ensemble learning approaches, which together improve the system's performance. In summary, this research provides a state-of-the-art approach that makes use of machine learning models to enhance traffic control in IoV-based vehicle networks in smart city scenarios. In comparing different model in intelligent system the CNN leads with 98.87% followed by the other methods as discuss in result section. It also promising development in the field of intelligent transportation systems because it not only improves detection accuracy but also ensures computing efficiency.