Study of Motion Sickness Model Based on fNIRS Multiband Features during Car Rides

Area of Science:

• Neuroscience
• Biomedical Engineering

Background:

• Motion sickness is a prevalent issue during travel, impacting passenger comfort and experience.
• Understanding the physiological underpinnings of motion sickness is crucial for developing effective countermeasures.

Purpose of the Study:

• To investigate the relationship between prefrontal cortex blood oxygenation changes and motion sickness severity using functional near-infrared spectroscopy (fNIRS).
• To develop a classification model for motion sickness based on neuroimaging data.

Main Methods:

• Real-world vehicle testing employing fNIRS to measure cerebral blood oxygenation.
• Principal Component Analysis (PCA) for feature extraction and Wavelet decomposition for Power Spectrum Entropy (PSE) analysis.
• Support Vector Machine (SVM) model for classifying motion sickness severity based on fNIRS data.

Main Results:

• The study achieved an overall motion sickness classification accuracy of 87.3% using 78 datasets.
• Analysis revealed a strong correlation between motion sickness magnitude and changes in the PSE of prefrontal blood oxygenation across five frequency bands.
• Individual classification accuracy varied significantly (50%-100%) among the 13 subjects, indicating personal differences.

Conclusions:

• fNIRS is a viable technique for modeling and classifying motion sickness by assessing prefrontal cortex activity.
• Changes in cerebral blood oxygenation, specifically PSE, are closely linked to the severity of motion sickness.
• Further research is necessary to address the observed individual variability in motion sickness responses.