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{178448,
        author = {Aparna Umesh Kharat and Mehwish Qureshi and Sadaf Khan and Sonali Bodekar},
        title = {Traffic Flow: Traffic Prediction and Optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {5627-5634},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178448},
        abstract = {Urban traffic congestion remains a top concern, increasing travel times, fuel usage, and environmental contamination. This report provides a forecasting traffic optimization sys- tem using Support Vector Regression (SVR) models for predicting traffic flows, supported by YOLOv8 for vehicle classification and detection. The system merges multiple sources of data, including traffic cameras, to provide detailed traffic forecasts and optimally time signal changes in real-time. A mathematical model is suggested to determine optimal green signal duration using real-time traffic density, vehicle type, and anticipated congestion levels. Simulation with a real-world dataset indicates that the suggested system reduces average predicted congestion by 22.62% compared to conventional fixed-time systems. Furthermore, dynamic green light allocation was increased by 16–18.5% for all lanes, which indicates improved adaptation to lane-specific vehicle loads. These optimizations reduced an estimated 20–30% in travel delays that parallel improvements in fuel efficiency and eco-friendliness. Results substantiate our approach to intelligent traffic management and attest to the validity of delivering scalability and economy at the solution scale, promising smart city plans through mitigation against metropolitan congestion while strengthening road safety.},
        keywords = {Traffic Prediction, Machine Learning, Intelligent Traffic Management, Real-time Optimization, Smart Cities, YOLOv8, Support Vector Regression (SVR)},
        month = {May},
        }