30, November 2025

Hybrid deep learning and reinforcement learning framework for adaptive and cost-efficient traffic signal control

VOLUME-11; ISSUE-11; NOV-2025

Author(s): 1 Ankusha P., 2 Mahalakshmi C V,

Authors Affiliations:

1Student, Department of CS&E, Bangalore Institute of Technology, Bangalore, India

2Assistant Professor, Faculty of CS&E, Bangalore Institute of Technology, Bangalore, India

DOIs:10.2015/IJIRMF/202511026     |     Paper ID: IJIRMF202511026


Abstract
Keywords
Cite this Article/Paper as
References

  Traffic congestion and road accidents have become major issues in rapidly growing urban centres. Bangalore, being one of India’s fastest-growing cities, faces significant challenges in traffic management and road safety. This study investigates commuter awareness of traffic rules, analyses traffic congestion patterns, and evaluates the effectiveness of traffic management measures. Data was collected using a combination of a survey among 100 commuters and secondary data from Bangalore Traffic Police reports. The study finds gaps in public awareness, frequent traffic violations, and identifies key areas for improvement. Recommendations include enhanced awareness campaigns, better traffic monitoring, and promotion of public transportation to improve road safety and traffic flow.

Artificial Intelligence, Deep Learning, YOLOv8, Reinforcement Learning, Traffic Signal Control, Smart City.

Ankusha P.,  Mahalakshmi C V, (2025); Hybrid deep learning and reinforcement learning framework for adaptive and cost-efficient traffic signal control, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-11, Issue-11, Pp. 160-162.          Available on –   https://www.ijirmf.com/

  1. Lakshay, et al., AI-Driven Traffic Signal Optimization for Better Congestion Control, IEEE International Conference on Computational Data Science (ICCDS), 2025, pp. 1-10.
  2. Abhay K. P., et al., Smart Traffic Management and Control System Using Deep Learning, IEEE Annual Conference on Electronics and Control Engineering (AECE), 2024, pp. 11-20.
  3. Bhalerao, et al., Adaptive Traffic Signal Control using Reinforcement Learning, IEEE Intelligent Transportation Systems Conference (ITS), 2023, pp. 21-30.
  4. Gamarra, et al., Deep Learning-based Signal Timing Optimization, Conference on Emerging Systems and Urban Planning (CESUP), 2023, pp. 31-40.
  5. Sharma, and Jaffery, Multi-vehicle Tracking for Traffic Analysis, IEEE Computer Vision and Image Understanding (CVIU), 2023, pp. 41-50.
Post Views: 151

Download Full Paper

Download PDF No. of Downloads:8 | No. of Views: 130