An AI-Enabled Intelligent Traffic Guidance System for Expressway Networks Based on IoT and GIS Integration
TL;DR
This study integrates predictive traffic inference, GIS-based coordination, and adaptive guidance generation into a scalable ITS architecture, providing a viable foundation for next-generation smart expressway management.
Abstract
Purpose: Managing expressway traffic under recurrent and non-recurrent congestion remains a critical challenge for modern highway systems, particularly in high-capacity corridors with strong spatial dependencies. Design / Methodology / Approach: The proposed framework operates in a closed loop, supporting real-time traffic state classification, short-horizon flow prediction, congestion risk assessment, and adaptive selection of guidance and control strategies. The effectiveness of the framework was evaluated using a microscopic traffic simulation environment configured to represent an Indian expressway corridor under varying demand levels and incident-induced disturbances. Multiple baseline strategies, including no guidance, static information dissemination, and rule-based dynamic control, were implemented for comparative assessment. Research Limitation: The effectiveness of the framework was evaluated using a microscopic traffic simulation environment configured to represent an Indian expressway corridor under varying demand levels and incident-induced disturbances. Findings: The simulation results demonstrate that the proposed approach reduces the average travel time by approximately 15–28%, shortens the congestion duration by 20–35%, improves the network throughput by 8–16%, and decreases the incident recovery time by up to 40% relative to conventional strategies. Practical Implication: The results highlight the practical benefits of anticipatory, risk-aware traffic guidance and coordinated spatial control for mitigating congestion propagation and enhancing traffic stability. Social Implication: Enhancing traffic stability and reducing congestion in modern highway systems. Originality/Value: The main contribution of this study lies in integrating predictive traffic inference, GIS-based coordination, and adaptive guidance generation into a scalable ITS architecture, providing a viable foundation for next-generation smart expressway management.