The study delves into emotion recognition (ER) using electroencephalography (EEG) within virtual reality (VR) environments. It involves data acquisition, pre-processing, feature extraction, and emotion classification. A 3D VR dataset was introduced to improve the precision of emotion elicitation. The data was recorded using the Interaxon Muse headband for EEG recording and Oculus Quest 2 for VR stimuli from 40 participants without reported mental illnesses. The analysis resulted in an average validation accuracy of 85.54% and a maximum accuracy of 90.20% in the best fold. The trained model showed a test accuracy of 82.03%.
Publication date: 7 Feb 2024
Project Page: Unknown
Paper: https://arxiv.org/pdf/2402.04142
