EEG-based evaluation of motion sickness and reducing sensory conflict in a simulated autonomous driving environment

Li, Zhibin; Zhao, Leilei; Chang, Jing; Li, Wei; Yang, Menghui; Li, Chong; Wang, Rencheng; Ji, Linhong

doi:10.1109/embc48229.2022.9871407

Cited by 4 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…et al evaluated the reliability of using the EEG to evaluate motion sickness and identified specific waves and regions [ 9 ]. Li, Z. et al further demonstrated the validation of the mean EEG frequency of theta band as an indicator of motion sickness [ 10 ]. Ji-Un, H. et al fused five physiological signals—EEG, ECG, respiration (RESP), photoplethysmography (PPG), and galvanic skin response (GSR)—to construct a motion sickness classification model based on real-world vehicle testing [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

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

2023

View full text Add to dashboard Cite

Motion sickness is a common physiological discomfort phenomenon during car rides. In this paper, the functional near-infrared spectroscopy (fNIRS) technique was used in real-world vehicle testing. The fNIRS technique was utilized to model the relationship between changes in blood oxygenation levels in the prefrontal cortex of passengers and motion sickness symptoms under different motion conditions. To enhance the accuracy of motion sickness classification, the study utilized principal component analysis (PCA) to extract the most significant features from the test data. Wavelet decomposition was used to extract the power spectrum entropy (PSE) features of five frequency bands highly related to motion sickness. The correlation between motion sickness and cerebral blood oxygen levels was modeled by a 6-point scale calibration for the subjective evaluation of the degree of passenger motion sickness. A support vector machine (SVM) was used to build a motion sickness classification model, achieving an accuracy of 87.3% with the 78 sets of data. However, individual analysis of the 13 subjects showed a varying range of accuracy from 50% to 100%, suggesting the presence of individual differences in the relationship between cerebral blood oxygen levels and motion sickness symptoms. Thus, the results demonstrated that the magnitude of motion sickness during the ride was closely related to the change in the PSE of the five frequency bands of cerebral prefrontal blood oxygen, but further studies are needed to investigate individual variability.

show abstract

Section: Introductionmentioning

confidence: 99%