ITSC 2025 Paper Abstract

Paper TH-EA-T29.2

Zhao, Yang (University of Electronic Science and Technology of China), Yu, Yewei (university of electronic science and technology of china), Shi, Kecheng (University of Electronic Science and Technology of China), Deng, Ruoyu (Chengdu Technological University), Cheng, Hong (University of Electronics Science and Technology of China)

An fNIRS-Based Multi-Sensor Fusion Approach for Passenger Comfort Assessment

Scheduled for presentation during the Regular Session "S29b-Human Factors and Human Machine Interaction in Automated Driving" (TH-EA-T29), Thursday, November 20, 2025, 13:50−14:10, 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 User-Centric HMI Design for Autonomous Vehicle Control Systems, Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety

Abstract

This paper presents a multimodal framework for passenger comfort assessment in intelligent vehicles. By integrating functional near-infrared spectroscopy (fNIRS), vehicle dynamics data, and subjective ratings, we propose a Multi-Branch Joint Network (MBJNet) capable of extracting complementary features from heterogeneous sources. To address inter-subject variability, transfer learning and elastic weight consolidation are incorporated, enabling improved generalization across passengers with limited labeled data. Experimental evaluations on a real-vehicle platform demonstrate that the proposed method significantly outperforms existing baselines in both within-subject and cross-subject classification tasks. Our approach achieves 91.73% accuracy in within-subject settings and 74.99% in cross-subject evaluations, highlighting its robustness and practical viability. This work provides a scalable and adaptive solution for comfort-aware intelligent cockpit systems.