MaDeNet: Disentangling Individuality of EEG Signals through Feature Space Mapping and Detachment

The cross-subject variability, or individuality, of electroencephalography (EEG) signals often has been an obstacle to extracting target-related information from EEG signals for classification of subjects' perceptual states. In this paper, we propose a deep learning-based EEG classification approach, which learns feature space mapping and performs individuality detachment to reduce subject-related information from EEG signals and maximize classification performance. Our experiment on EEG-based video classification shows that our method significantly improves the classification accuracy.