A Vehicle Congestion Prediction Approach for Smart City Traffic Management

Rapidly evolving smart cities across the globe are the new dimension in modern life. However, the slowly moving vehicles due to the swelling traffic volume is a major challenge in traffic management across these cities. The study emphasizes devising an approach to determine the traffic congestion in advance across different locations in the city to ensure better traffic management. The proposed approach devised a traffic management system by utilizing the graph neural network machine learning algorithm to analyze the tremendous traffic data and enabling the prediction about traffic congestion across different locations in the city with the aim of reducing the traffic congestion and planned routes for lowered traveling cost. The outcome of the extensive experimental work reflects the efficacy of the proposed approach in providing a better solution in determining the traffic congestion across different locations, well in advance.