Research Status of Motor Imagery EEG Signal Based on Deep Learning

In recent years, deep learning algorithms have been rapidly developed and applied more and more widely in the field of biomedical engineering. Among them, the use of deep learning algorithms to decode physiological, psychological, or pathological states from electroencephalogram (EEG) signals is also attracting more and more attention. This paper reviews the applications of deep learning algorithms in motor imagery (MI) EEG in recent years and introduces the common algorithms, application status, and existing problems. Firstly, the research status of CNN and DBN on EEG signal classification in MI is described. Then, the classification of EEG signals by CNN and DBN in MI is discussed. Finally, some key problems of deep learning in MI-EEG signal decoding are summarized, such as high model complexity and lack of training data.