The effects of layer-wise relevance propagation-based feature selection for EEG classification: a comparative study on multiple datasets

• Published in: Frontiers in Human Neuroscience Vol. 17; p. 1205881
• Main Authors: Nam, Hyeonyeong, Kim, Jun-Mo, Choi, WooHyeok, Bak, Soyeon, Kam, Tae-Eui
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media SA 05.06.2023; Frontiers Research Foundation; Frontiers Media S.A
• Subjects: analysis; Brain; Brain research; brain-computer interface; Classification; Computer applications; Datasets; Deep learning; EEG; Electrodes; Electroencephalography; Feature selection; Human Neuroscience; Implants; Invasiveness; layer-wise relevance propagation; Mental task performance; motor imagery classification; Neural networks; Neurosciences. Biological psychiatry. Neuropsychiatry; RC321-571; electroencephalography; motor imagery classification; layer-wise relevance propagation; analysis; brain-computer interface; feature selection

The brain-computer interface (BCI) allows individuals to control external devices using their neural signals. One popular BCI paradigm is motor imagery (MI), which involves imagining movements to induce neural signals that can be decoded to control devices according to the user's intention. Ele...