AI-Based Intelligent Traffic Signal Management System: A Review

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 3 | 02 | Page :
    By

    Divya Narchal,

  • Amrik Singh,

  • Dr. Manpreet Kaur,

  1. Student, Department of Computers, Guru Kashi University Talwandi Sabo, Bathinda, Punjab, India
  2. Faculty of Computing, Guru Kashi University Talwandi Sabo, Bathinda, Punjab, India
  3. Assistant Professor, Guru Kashi University Talwandi Sabo, Bathinda, Punjab, India

Abstract

Traffic congestion is a growing problem in urban areas worldwide, leading to economic losses, increased pollution, and commuter frustration. Traditional traffic management systems rely on fixed timing cycles and lack adaptability to real-time traffic conditions. Intelligent traffic light control systems based on artificial intelligence (AI) have become a viable substitute for traditional techniques. These systems are able to evaluate large volumes of traffic data in real time, identify patterns, and dynamically adjust signal timings by utilizing sophisticated computational techniques including machine learning, deep learning, reinforcement learning, and computer vision. In contrast to conventional systems, AI-driven methods have the capacity to self-learn, continuously enhance decision-making, and adjust to changes in road usage, traffic density, and outside variables like bad weather or accidents. With an emphasis on how sensor technology and optimization algorithms enable real-time decision-making, this paper investigates the incorporation of AI approaches into traffic light control. Additionally, it looks into computer vision for vehicle recognition and traffic density prediction, as well as reinforcement learning for adaptive traffic flow management. In addition, practical applications of AI-powered traffic control systems are examined to demonstrate how well they work to ease traffic, cut down on travel time, and enhance urban mobility in general. The potential of AI-driven traffic management systems is further supported by real-world applications. Major city pilot projects have shown reduced carbon emissions, increased fuel economy, and shorter commute times. For instance, AI-powered adaptive traffic signal management systems have successfully decreased junction wait times and increased peak-hour traffic flow efficiency. By facilitating collaborative and anticipatory traffic control, integration with cutting-edge technology like connected and autonomous vehicles (CAVs) further enhances the potential of AI-based solutions. Urban traffic control is undergoing a paradigm shift with AI-based intelligent traffic signal management technologies. These technologies might greatly reduce traffic, cut emissions, and enhance the quality of life in cities across the globe by substituting flexible, data-driven decision-making processes with strict, pre-programmed cycles. The combination of AI, IoT, and smart infrastructure offers a promising route toward sustainable, effective, and future-ready transportation networks, even while issues like cost, data privacy, and scalability still exist.

Keywords: Traffic congestion, Urban traffic management, AI-based traffic signal control, Smart cities, Real-time traffic optimization, Adaptive traffic signals .

How to cite this article:
Divya Narchal, Amrik Singh, Dr. Manpreet Kaur. AI-Based Intelligent Traffic Signal Management System: A Review. International Journal of Electronics Automation. 2025; 03(02):-.
How to cite this URL:
Divya Narchal, Amrik Singh, Dr. Manpreet Kaur. AI-Based Intelligent Traffic Signal Management System: A Review. International Journal of Electronics Automation. 2025; 03(02):-. Available from: https://journals.stmjournals.com/ijea/article=2025/view=235239


References

  1.  Texas A&M Transportation Institute. 2019 Urban Mobility Report. College Station, TX: Texas A&M Transportation Institute; 2019 [cited 2025 Mar 22. Available from: https://mobility.tamu.edu
  2. Kumar A, Singh P, Kaur J. Machine learning-based traffic prediction for smart cities. IEEE Access. 2022;9:31245–31256.
  3. Lee B, Kim M, Park H. Real-time traffic flow prediction using random forest. IEEE Trans Intell Transp Syst. 2023;23(1):87–98.
  4. Zhang C, et al. Deep learning for traffic flow prediction: a review. IEEE Trans Neural Netw. 2023;34(3):489–502.
  5. Chen D, Xu X. LSTM-based traffic signal optimization. IEEE Smart Cities J. 2022;5(4):321–335.
  6. Wang E, Patel R, Rao S. Reinforcement learning for adaptive traffic signals. IEEE Intell Syst. 2023;37(6):41–53.
  7. Xie F, et al. Vehicle detection in traffic using YOLOv4 and image processing. IEEE Trans Veh Technol. 2021;70(8):7863–7873.
  8. Zhang G, Zhang L. Real-time traffic monitoring using Faster R-CNN and deep learning. IEEE Trans Image Process. 2021;30:1230–1241.
  9. Chen H, et al. IoT-based traffic management and prediction using smart sensors. IEEE Internet Things J. 2021;8(5):3765–3776.
  10. Li J, et al. Traffic flow estimation and vehicle detection using LiDAR and RADAR data fusion. IEEE Trans Robot. 2022;39(9):1218–1232.
  11. Liu KY, et al. CCTV-based traffic monitoring and signal control using AI. IEEE Trans Intell Transp Syst. 2023;24(10):1600–1611.
  12. Yang M, Liu S, Wang X. Vehicular communication (V2X) for traffic signal control. IEEE Trans Veh Technol. 2019;68(11):10493–10505.
  13. Patel N, Hegde R, Bhattacharya P. V2X communications in intelligent traffic systems: challenges and future directions. IEEE Trans Commun. 2024;72(8):3076–3090.
  14. Shah O, Jain S. Genetic algorithm-based traffic signal control for congestion reduction. IEEE Access. 2020;8:8520–8534.
  15. Wang P, et al. Particle swarm optimization for dynamic traffic signal control. IEEE Trans Evol Comput. 2021;25(6):1210–1224.
  16. Zhang Q, Zhao X, Wang H. Fuzzy logic control for real-time traffic signal adjustment. IEEE Trans Syst Man Cybern. 2021;51(5):1472–1483.
  17. Liu R, Zhang S, Wu T. Multi-agent systems for decentralized traffic control. IEEE Trans Cybern. 2022;52(7):4292–4304.
  18. Kumar SBPRS. AI-based traffic management in Pittsburgh. In: IEEE Smart Cities Conference; 2023; Pittsburgh, USA. p. 45–50.
  19. Zhang T, Wei Z, Li SX. City Brain Project: AI-powered traffic management in Hangzhou, China. IEEE Access. 2022;8:11245–11253.
  20. Shah U, Verma V. Comparison of AI and conventional traffic signal systems in smart cities. IEEE Trans Sustain Comput. 2022;15:92–105.
  21. Li V, Yu L. AI traffic signal optimization: a comparative study between fixed and adaptive systems. IEEE Trans Intell Syst. 2023;37(6):65–77.
  22. Turner W. Challenges in implementing AI-based traffic signals. IEEE Trans Intell Transp Syst. 2021;24(7):1723–1735.
  23. Zhang X, et al. Large-scale deployment challenges in AI-driven traffic systems. IEEE Trans Smart Cities. 2023;9(3):212–224.
  24. He Y, Wu Z, Wang J. Computational challenges in real-time traffic management using AI. IEEE Trans Comput Intell AI Games. 2021;13(5):599–610.
  25. Huo Z, Li H. Ethical concerns in AI-driven traffic systems: privacy and data protection. IEEE Trans Ethics Eng. 2022;7(2):45–58
Ahead of Print Subscription Review Article
Volume 03
02
Received 27/05/2025
Accepted 28/07/2025
Published 30/12/2025
Publication Time 217 Days
77

Login


My IP

PlumX Metrics