Passenger motion sickness binary classification model and analysis of vehicle lighting intervention effect
Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
  • Volume
  • Citation
    Ren B, Wang X, Ren P, Wu M. Passenger motion sickness binary classification model and analysis of vehicle lighting intervention effect. Artif. Intell. Auton. Syst. 2025(2):0007, https://doi.org/10.55092/aias20250007. 
  • DOI
    10.55092/aias20250007
  • Copyright
    Copyright2025 by the authors. Published by ELSP.
Abstract

This study investigated the effects of ambient lighting on passenger motion sickness during real-world nighttime driving. Motion sickness was assessed through subjective ratings and simultaneous EEG-ECG recordings. The binary classification model was proposed to optimize passenger comfort and tested in the intelligent cabin for Feifan F7 series electric vehicle of Shanghai Automotive Industry Corp (SAIC). The lighting conditions was tested for three volunteers: warm red light (620–650 nm), cool blue light (450–470 nm), and no-light. Results showed significant differences across conditions, with red light demonstrating the strongest protective effect, no motion sickness 77.8% red light vs. 38.9% blue light and 27.8% no light. Red light significantly enhanced alpha power and reduced delta power, suggesting neurological relaxation. Therefore, a comprehensive validation of wavelength-specific lighting effects on automotive motion sickness was completed, demonstrating that warm red light effectively mitigates symptoms through enhanced alpha wave activity.

Keywords

motion sickness; ambient lighting intervention; EEG-ECG fusion; deep learning classification; intelligent cabin comfort; Shanghai Automotive Industry Corp (SAIC)

Preview