Related Experiment Video
Updated: May 22, 2025
08:45
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
Published on: October 24, 2012
14.6K
Dual-pathway EEG model with channel attention for virtual reality motion sickness detection
Chengcheng Hua1, Yuechi Chen1, Jianlong Tao1
1School of Automation, C-IMER, CICAEET, Nanjing University of Information Science & Technology, Nanjing 210044, China.
Journal of Neuroscience Methods
|March 14, 2025
Summary
A new dual-pathway model accurately detects Virtual Reality Motion Sickness (VRMS) using EEG and brain networks. This breakthrough offers objective guidance for improving VR experiences by minimizing motion sickness.
Area of Science:
- Neuroscience
- Computer Science
- Human-Computer Interaction
Background:
- Virtual Reality (VR) induced motion sickness significantly hinders user experience and industry growth.
- Accurate detection of VR Motion Sickness (VRMS) is crucial for addressing this challenge.
Purpose of the Study:
- To propose and validate a novel dual-pathway model for detecting VRMS.
- To enhance VR user experience by providing objective VRMS detection.
Main Methods:
- A dual-pathway model utilizing Convolutional Neural Network (CNN) blocks and channel attention modules.
- Input pathways include raw EEG signals and transformed brain network adjacency matrices (using PLV or RHO).
- Model validation through a VR flight simulation experiment, collecting resting-state EEG before and after the task.
Main Results:
- The proposed model achieved an average accuracy of 99.12%, precision of 99.12%, recall of 99.11%, and F1 score of 99.12%.
- Outperformed eight reference models and four fused hybrid models, demonstrating superior performance.
Conclusions:
- The developed model significantly surpasses state-of-the-art methods in VRMS detection.
- Offers objective and direct guidance for mitigating VRMS and optimizing the overall VR experience.
