Urban traffic congestion remains a persistent and critical issue, leading to substantial economic and environmental consequences. This research paper introduces an innovative approach to improving traffic flow and reducing congestion by implementing machine learning (ML)-based traffic management strategies. Our study utilizes real-time traffic data, including vehicle counts, speed measurements, and historical traffic patterns, to develop ML models that can predict congestion hotspots and optimize traffic signal timings. Through rigorous simulations and empirical evaluations conducted in urban settings, our findings highlight the substantial efficacy of ML-driven traffic management strategies in reducing travel times and mitigating congestion-related emissions. Moreover, we investigate the potential synergies between autonomous vehicles and ML-based traffic management systems, presenting a comprehensive framework for their seamless integration while discussing the associated advantages and challenges. This paper emphasizes the significance of our research for urban planners, policymakers, and transportation authorities, offering a pathway towards creating intelligent, efficient, and sustainable urban transportation systems.
Enhancing Traffic Flow Efficiency and Mitigating Congestion through ML-Based Traffic Management Strategies
2023-11-23
1227099 byte
Conference paper
Electronic Resource
English
Michigan Toolbox for Mitigating Traffic Congestion
NTIS | 2011
|Springer Verlag | 2025
|Wiley | 2008
|