CDMS: A Real-Time System for EEG-Guided Cybersickness Mitigation Through Adaptive Adjustment of VR Content Factors

Authors

Affiliations

Ufuk Uyan

Hacettepe University

Ufuk Çelikcan

Hacettepe University

Published

Displays

DOI

10.1016/j.displa.2024.102704
Illustration of our methodology. During the data collection experiments (top half), cybersickness inducing content factors (navigation speed, scene complexity, and stereoscopic rendering) were simulated by the VE generator, in which subjects were immersed, and their responses in terms of brain activity and immediate self-reports of cybersickness severity were collected to train a two-stage shallow CNN model that first predicts the onset of cybersickness and then, in case of cybersickness, predicts the causal factor. Afterwards, the trained models are used in the CDMS loop (bottom half) to mitigate cybersickness based on the subjects' brain activity feedback by updating the VE generator simultaneously to adaptively adjust the parameters of the identified factor.
preprint frontpage
Paper

Ufuk Uyan, Ufuk Celikcan. "CDMS: A Real-Time System for EEG-Guided Cybersickness Mitigation Through Adaptive Adjustment of VR Content Factors", Displays (2024).
Preprint

Dataset and Code: Download link

Please kindly cite our paper in your publication if you use this dataset or code:

@article{uyan2024cdms,
	  title={CDMS: A real-time system for EEG-guided cybersickness mitigation through adaptive adjustment of VR content factors},
	  author={Uyan, Ufuk and Celikcan, Ufuk},
	  journal={Displays},
	  pages={102704},
	  year={2024},
	  publisher={Elsevier}
	}

Abstract

Cybersickness remains a major issue that can severely impact the user’s comfort, performance, and enjoyment of VR. While there are various approaches to combat cybersickness, only a few have been developed for real-time mitigation based on user biofeedback, and these do not aim to distinguish causal factors and apply mitigation accordingly. In this paper, we propose a novel real-time cybersickness detection and mitigation system (CDMS) that leverages a two-stage shallow convolutional network to detect cybersickness and identify the contributing factors from the user's electroencephalogram (EEG) activity. Based on the output of the convolutional network, CDMS adaptively modifies the parameters of the identified factor in the generated virtual environment to mitigate the onset cybersickness. For this, we conjointly consider three major content factors of cybersickness: navigation speed, scene complexity, and stereoscopic rendering. To train the network, we collected EEG data and self-reports of cybersickness from the subjects by simulating these factors in varying degrees of severity. For the performance evaluation of CDMS, we conducted a user study comprising one CDMS session and two different control sessions. The results show that the users experienced significantly less cybersickness after the CDMS session. Also, CDMS effectively avoided false positives that could otherwise degrade the VR experience.

Acknowledgements

This work was supported by TUBITAK-1001 Program (Grant No. 116E280)

Footnotes