ITSC 2025 Paper Abstract

Paper TH-LA-T29.2

Liu, Tianqi (Tsinghua University), Qin, Yanjun (Xinjiang University), Zhang, Shanghang (Peking University), Tao, Xiaoming (Tsinghua University)

Driver Road Rage Detection and Event Perception Analysis Based on EEG Functional Connectivity

Scheduled for presentation during the Regular Session "S29c-Human Factors and Human Machine Interaction in Automated Driving" (TH-LA-T29), Thursday, November 20, 2025, 16:20−16:40, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Driver Behavior Monitoring and Feedback Systems for Semi-autonomous Vehicles, Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety

Abstract

Road rage, an emotional loss of control while driving, has become a significant cause of traffic accidents and a key focus for driver monitoring systems. To effectively detect and prevent road rage behavior, we proposed a road rage detection system EFGNet, which acquires graphic structural data by extracting the functional brain network from electroencephalogram (EEG) signals and employs the graph attention (GAT) module for classification. Moreover, we analyzed the behavioral characteristics of drivers under road rage conditions, as well as the topological features of EEG power density. The proposed system has been comprehensively evaluated on the manD dataset, demonstrating a classification accuracy of 93.42% that surpasses baseline models. Analysis of driving behavior and EEG data indicates that road rage leads to an increase in EEG power, a decrease in responsiveness, and an increase in aggressive behavior. This research provides a novel perspective on the characteristics, detection, and prevention of road rage, thereby contributing to the advancement of driving safety assistance systems.