Deep Learning Algorithm for Brain-Computer Interface

Table 3

Summary of various methodologies in BCI systems.

Classification methods	Input EEG pattern	Features	References
Adaptive classifiers	Motor imaginary-based	Frequency band power, EEG time	[10, 12, 14]
Matrix and tensor classifiers	Steady-state visual evoked potentials, P300	Frequency band power, raw data	[2, 5, 7, 15]
Transfer learning and deep learning	Motor imaginary-based, P300, SSVEP	EEG time points, frequency band power, raw EEG data	[2, 4, 6, 7]
Miscellaneous classifiers	Motor imaginary-based, P300	Not specified	[1, 4, 15]