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{188700,
        author = {Azlan Ahmed and Advay Rathi and Miran Azmi},
        title = {AI Integrated Traffic information system},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3418-3425},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188700},
        abstract = {Congestion of vehicular traffic in urban areas has been a longstanding issue that caused time delays, environmental degradation, and economic loss. In this we present an artificial intelligence-based Traffic Information System based on Physics-informed Neural Networks (PINNs) and GPT-4 to improve vehicular traffic conditions predication and provide users with real-time support. The combination of physics-based traffic flow modeling and the use of sophisticated natural language processing helps the system predicts current traffic conditions accurately and passes actionable information to users in a natural conversational format. In the sparse-data environment, PINNs use real-time measurements of the sensor network, GPS, and CCTV images to make accurate traffic forecasts. At the same time, GPT-4 can provide route recommendations based on adaptivity, vehicular traffic congestion and vehicular traffic summaries. By 20-30 percent, the integration should relieve the traffic, improve movement in the city and support smart city programs. It is a scalable also and smart answer to present-day vehicular traffic management and planning.},
        keywords = {Traffic estimation, Physics-Informed Neural Networks, GPT-4, AI traffic system, real-time traffic assistance.},
        month = {December},
        }