Improving subject transfer in EEG classification with divergence estimation

• Published in: Journal of neural engineering Vol. 21; no. 6; pp. 66031 - 66049
• Main Authors: Smedemark-Margulies, Niklas, Wang, Ye, Koike-Akino, Toshiaki, Liu, Jing, Parsons, Kieran, Bicer, Yunus, Erdoğmuş, Deniz
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.12.2024
• Subjects: Algorithms; Brain-Computer Interfaces; brain–computer interface (BCI); domain adaptation; electroencephalography (EEG); Electroencephalography - classification; Electroencephalography - methods; Humans; Neural Networks, Computer; representation learning; subject transfer learning; brain–computer interface (BCI); electroencephalography (EEG); subject transfer learning; domain adaptation; representation learning

Objective . Classification models for electroencephalogram (EEG) data show a large decrease in performance when evaluated on unseen test subjects. We improve performance using new regularization techniques during model training. Approach . We propose several graphical models to describe an EEG class...