Subject-Independent Deep Architecture for EEG-Based Motor Imagery Classification

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; pp. 718 - 727
• Main Authors: Sartipi, Shadi, Cetin, Mujdat
• Format: Journal Article
• Language: English
• Published: United States IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Benchmarking; Brain; Brain modeling; Brain-Computer Interfaces; Classification; Classifiers; Computer applications; Convolutional neural networks; EEG; Electroencephalography; Electroencephalography - methods; Embedding; Feature extraction; Heterogeneity; Human-computer interface; Humans; Image classification; Imagination; Implants; Learning; Machine Learning; Mental task performance; motor imagery; Performance assessment; Recording; semi-supervised deep architecture; Task analysis; Training

Motor imagery (MI) classification based on electroencephalogram (EEG) is a widely-used technique in non-invasive brain-computer interface (BCI) systems. Since EEG recordings suffer from heterogeneity across subjects and labeled data insufficiency, designing a classifier that performs the MI independ...