Smart Traffic Management System Using Machine Learning for Adaptive Signal Control and Emergency Vehicle Prioritization

Abstract: The rapid growth of urban populations and vehicle density has resulted in severe traffic congestion, increased travel time, and environmental pollution in modern cities. Conventional traffic control systems rely on fixed signal timings or reactive approaches, which are inefficient in handling dynamic and unpredictable traffic conditions. This paper proposes a Smart Traffic Management System (STMS) that leverages machine learning and data-driven techniques to optimize traffic flow. The system employs a Random Forest Regression model to predict future traffic density based on historical datasets and simulated scenarios, analysing parameters such as vehicle count, time intervals, and lane-wise traffic patterns. An intelligent decision-making module dynamically adjusts signal timings based on these predictions. The system additionally incorporates an emergency vehicle prioritization mechanism and a visualization module providing analytical insights into traffic trends and prediction accuracy. By eliminating costly IoT infrastructure and focusing on predictive analytics, the proposed system offers a cost-effective, scalable, and flexible solution for modern traffic management, achieving over 96% packet delivery reliability and end-to-end latency as low as 200-350 ms under Wi-Fi conditions.

Keywords: Adaptive Signal Control, Emergency Vehicle Prioritization, IoT, Machine Learning, Predictive Analytics, Random Forest Regression, Smart Traffic Management.