Modelling the Relationship Between Physiological Measures of Motion Sickness

Car sickness is anticipated to occur more frequently in self-driving vehicles because of their design. This thesis involved an investigation using machine learning techniques with physiological measures to detect and predict the severity of car sickness in real-time every two minutes. A total of 40 adults were exposed to two conditions, each involving a 20-minute ride on a motion-base simulator. Car sickness incidence and severity were subjectively measured using the Fast Motion Sickness (FMS) and Simulator Sickness Questionnaire (SSQ). Car sickness symptom was successfully elicited in 31 participants (77.5%) while avoiding simulator sickness. Results showed that head movement had the strongest relationship with car sickness, and there was a moderate correlation between heart rate and skin conductance. The machine learning models revealed a medium correlation between the physiological measures and the FMS scores. An acceptable classification score distinguishing between motion-sick and non-motion-sick participants was found using the random forest model.