Neurophisology Biosignals of Cognitive Training Classification in Virtual Reality Environment Using Deep Learning Model

Abstract

This research investigates the potential of neurophysiological biosignals fusion, such as electroencephalogram (EEG) and Eye Tracking signals (ET), to classify cognitive states during virtual reality (VR) training, specifically for the rehabilitation of neurodegenerative diseases. By analyzing EEG data collected from participants engaged in VR-based cognitive exercises, we aim to identify patterns associated with different cognitive states and develop a robust classification system. A Convolutional Neural Network (CNN) model was developed to predict task performance utilizing neurophysiological inputs in an immersive world. This system could be used to monitor cognitive function, assess treatment efficacy, and provide real-time feedback to adapt the VR environment to the individual's needs. The findings of this study could contribute to the development of personalized VR-based rehabilitation programs for neurodegenerative diseases, leading to improved outcomes for patients. The preliminary results of this framework were promising with an overall accuracy of 97% and an average precision of 96.7%.