AI-Driven Urban Traffic Monitoring, Prediction, and Integrated Traffic Optimization

Author

Prof. Snehal Rewatkar, Harsha Ghodpage, Aishwarya Bhagat, Rupali Mahule, Saloni Dhole

Abstract

 Urban traffic congestion is a major challenge that affects travel time, road efficiency, fuel consumption, and emergency response. This paper presents an AI-powered urban traffic congestion monitoring, prediction, and management system designed for Nagpur city. The proposed system integrates real-time traffic information, weather conditions, road topology, vehicle and queue parameters, incidents, road blockages, pedestrian activity, events, and public transport information to provide a comprehensive view of traffic conditions. The system monitors traffic conditions, predicts congestion for the next 15 minutes, identifies possible causes of congestion, recommends alternative routes, and dynamically suggests traffic signal adjustments. It also provides emergency vehicle priority, green corridor recommendations, Nagpur Metro alternatives, and traffic alerts through an integrated dashboard and notification system. A machine-learning-based traffic prediction approach is combined with rule-based traffic management and explainable congestion analysis. The proposed system aims to support traffic authorities and commuters by providing timely information and assisting in efficient traffic management. The system is implemented using Python, Flask, HTML, CSS, JavaScript, and external traffic, weather, and map data sources.

Keywords

Traffic Congestion, Machine Learning, Traffic Prediction, Intelligent Transportation System, Route Recommendation, Traffic Management.

Full Text:

Download Paper PDF

References

 [1] B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting,” in Proc. 27th Int. Joint Conf. Artif. Intell. (IJCAI), Stockholm, Sweden, 2018, pp. 3634–3640, doi: 10.24963/IJCAI.2018/505.

[2] Z. Cui, K. Henrickson, R. Ke, Z. Pu, and Y. Wang, “Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting,” arXiv preprint arXiv:1802.07007, 2018.

[3] A. Essien, I. Petrounias, P. Sampaio, and S. Sampaio, “A deep-learning model for urban traffic flow prediction with traffic events mined from Twitter,” World Wide Web, vol. 24, pp. 1345–1368, 2021, doi: 10.1007/s11280-020-00800-3.

[4] S. Du, T. Li, X. Gong, and S.-J. Horng, “A hybrid method for traffic flow forecasting using multimodal deep learning,” Int. J. Comput. Intell. Syst., vol. 13, pp. 85–97, 2020, doi: 10.2991/ijcis.d.200120.001.

[5] S. Afandizadeh, S. Abdolahi, and H. Mirzahossein, “Deep learning algorithms for traffic forecasting: A comprehensive review and comparison with classical ones,” Journal of Advanced Transportation, vol. 2024, Art. no. 9981657, 2024, doi: 10.1155/2024/9981657.

Share your valuable work from Social Media Buttons