Emergency Traffic Prioritization System with Priority-based Dynamic Route Optimization and IoT-Enabled Dynamic Signal Control

This paper presents a dynamic traffic management system that prioritizes emergency vehicles in urban environments through real-time route optimization and IoT-enabled signal control. The proposed system integrates GPS tracking, Raspberry Pi 4B edge computing, and RFID for detecting emergency vehicles. Our implementation demonstrates a 35% reduction in ambulance response times compared to conventional traffic systems through dynamic signal control and machine learning-based congestion prediction. This system combines IoT sensors (RFID, ANPR cameras, GPS modules) for vehicle detection with a modified $\mathrm{A}^{*}$ algorithm for route optimization, achieving $92 \%$ precision in traffic pattern analysis. Experimental results from simulations through the Simulated Urban Mobility tool validate the effectiveness of our approach in improving emergency response efficiency while maintaining optimal traffic flow. To optimize real-time decision-making, our system uses edge computing and adaptive traffic signal control, dynamically adjusting the traffic signal times based on traffic density. A precedence-based model ensures that multiple ambulances approaching a junction are managed effectively based on assigned priority, reducing deadlocks and optimizing passage. Our system reduces false positive detections by employing a redundant detection method. The system is deployed using an NGINX server with Flask and Gunicorn to ensure efficient and scalable web-based management.