Modeling of Novel Ensemble Learning Method for Emergency Intelligent Transportation System Tracking and Mobility Management

Authors:

Abstract
Emergency vehicle preemption and multiintersection coordination remain critical challenges in dense urban traffic. Existing Intelligent Transportation Systems (ITSs) often rely on centralized or resource-intensive deep learning models, limiting scalability. This paper presents a lightweight rule-based ensemble decision framework that coordinates multiple intersections using a distributed logic function. The proposed model introduces a framework for tracking emergency vehicles and an ensemble that operates in a non-iterative, progressive mode to adapt green light duration dynamically. The decision-learning method is employed to develop a traffic rule that regulates traffic signals and intelligent routing. The simulation outcome shows that the proposed system reduces average vehicle delay and queue length while improving throughput and emergency response time. Results show faster emergency clearance with lower computational overhead than adaptive fixed-time baselines.

This publication has 40 references indexed in Scilit: