Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{173936,
        author = {Mr. M.Sathish kumar and Mr.M.SUBBAREDDY and Mr. P.SREEDHAR and CH V S SAI KUMAR REDDY},
        title = {Efficient urban traffic management with real time traffic prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {4679-4684},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173936},
        abstract = {Efficient urban traffic management is critical for mitigating congestion, optimizing transportation networks, and enhancing commuter experiences. This research presents a real-time traffic prediction framework that integrates spatio-temporal data analytics with advanced machine learning techniques to enhance urban traffic flow. The proposed system utilizes Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Federated Learning (FL) to improve traffic forecasting accuracy while maintaining data privacy. The study also employs Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL) for dynamic traffic signal optimization and route planning.Real-time traffic data is collected from IoT-enabled traffic sensors, GPS-enabled vehicles, and video surveillance, followed by data preprocessing techniques such as feature extraction, normalization, and outlier detection. Experimental evaluations conducted on real-world datasets from metropolitan areas demonstrate significant improvements in traffic prediction accuracy. CNN-LSTM models achieve an 89% accuracy rate in traffic congestion forecasting, while Federated Learning enhances scalability and privacy with a 92% success rate in decentralized traffic prediction models. Furthermore, DRL-based adaptive traffic signal control reduces average traffic delays by 30%, contributing to improved urban mobility.The integration of predictive analytics with intelligent transportation systems (ITS) enables proactive traffic management, including dynamic route optimization, congestion mitigation, and intelligent traffic light control. The results confirm that combining machine learning with real-time data enhances traffic flow efficiency, reduces congestion, and fosters sustainable urban mobility. This study provides valuable insights for policymakers, urban planners, and transportation authorities, paving the way for smarter and more adaptive traffic management strategies.},
        keywords = {Real-time traffic prediction, urban traffic management, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Federated Learning (FL), Graph Neural Networks (GNN), Deep Reinforcement Learning (DRL)},
        month = {April},
        }