Towards Transparent Traffic Solutions: Reinforcement Learning and Explainable AI for Traffic Congestion

Abstract

This study introduces a novel approach to traffic congestion detection using Reinforcement Learning (RL) of machine learning classifiers enhanced by Explainable Artificial Intelligence (XAI) techniques in Smart City (SC). Conventional traffic management systems rely on static rules, and heuristics face challenges in dynamically addressing urban traffic problems' complexities. This study explains the novel Reinforcement Learning (RL) framework integrated with an Explainable Artificial Intelligence (XAI) approach to deliver more transparent results. The model significantly reduces the missing data rate and improves overall prediction accuracy by incorporating RL for real-time adaptability and XAI for clarity. The proposed method enhances security, privacy, and prediction accuracy for traffic congestion detection by using Machine Learning (ML). Using RL for adaptive learning and XAI for interpretability, the proposed model achieves improved prediction and reduces the missing data rate, with an accuracy of 98.10, which is better than the existing methods.