CyberSense: A Closed-Loop Framework to Detect Cybersickness Severity and Adaptively apply Reduction Techniques
Rifatul Islam, Samuel Ang, John Quarles
Abstract
Researchers often collect subjective measurements before, after, and during the immersive experience to measure cybersickness severity. However, collecting data before and after the immersive experience does not provide a sufficiently granular understanding of cybersickness during the immersion. Thus, no preventive measures can be taken during immersion. This research presents CyberSense - an automated framework for cybersickness severity detection during immersion. The framework collects the users' physiological data at user-defined intervals. It uses a pre-trained neural network to detect cybersickness severity on the experience with a root mean square error of 2.61 and adaptively adjusts the cybersickness reduction techniques.