Abstract :

Prediction Of Cybersickness, Which Refers To Discomfort Or Sickness Caused By Virtual Reality (VR), Is An Essential Issue In Developing VR Environments. Proactive Identification And Mitigation Of Users Cybersickness Can Be Achieved Through Early Prediction Of Cybersickness Based On Physiological Signals, Such As EEG Data. This Paper Proposes A Machine Learning Framework For Predicting Users Cybersickness Risk In Advance Using Their EEG Signals. For This Task, We Leverage Spectral And Temporal Features Extracted From EEG Signals For Training And Validating Several Classification Models. Experimental Results Obtained On The Public VR EEG Dataset Show That Ensemble Learning Algorithms, I.e., Random Forest, XGBoost, And LightGBM, Yield Superior Performance, Where The Best-performing Model Achieves High Accuracy And AUC Score. In Addition, XAI Approaches, Specifically, Feature Importance And SHAP Method, Are Adopted To Interpret Classification Models Trained On EEG Features To Reveal Important Physiological Predictors Of Cybersickness. Our Experimental Findings Suggest That Beta And Alpha Band Power, Along With Temporal Variability, Contribute To Cybersickness Risk Prediction.

Published:

17-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

595-601

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite