Relevance-based channel selection in motor imagery brain–computer interface

• Published in: Journal of neural engineering Vol. 20; no. 1; pp. 16024 - 16044
• Main Authors: Nagarajan, Aarthy, Robinson, Neethu, Guan, Cuntai
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.02.2023
• Subjects: Algorithms; Brain-Computer Interfaces; channel selection; deep learning; Electroencephalography - methods; explainable AI; Humans; Imagery, Psychotherapy; Imagination - physiology; layer-wise relevance propagation; MI-BCI; Neural Networks, Computer; MI-BCI; channel selection; deep learning; explainable AI; layer-wise relevance propagation

Objective. Channel selection in the electroencephalogram (EEG)-based brain–computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep...