Improving EEG-Based Motor Imagery Classification for Real-Time Applications Using the QSA Method

Table 2

Accuracy of classifier in motor imagery based BCI: two classes. The classes are (T1) left imagined hand movements and (T2) right imagined hand movements.

Dataset	Activity	Subjects	Trials	Filter	Feature	Classifier	Accuracy	References
BCI competition III	T1, T2	5	280	Yes		LS-SVM (RBF kernel)	95.72%	[34]
	T1, T2	4	140	Yes		HMM	77.50% +	[35]
	T1, T2	4	200	Yes	CSP	SVM (Gaussian kernel)	77.50%	[36]
	T1, T2	7	100	Yes	CSP/EMD, PCA	KNN	85.8%	[37]
	T1, T2	4	100	Yes		SVM	81%	[29]
Other data sets	T1, T2	4	90	Yes	CSP	SVM (Gaussian kernel)	74.10%	[36]
	T1, T2	1	140	Yes	CSP/ERD-ERS	BSSFO-SVM	97.57%	[25]
	T1, T2		80	Yes	PLS Regression	Based on the decoding principle	64%	[1]
	T1, T2	109	90	Yes	CSP	SUTCCSP	90%	[38]
	T1, T2	4	480	Yes	CSP/ERD-ERS, FFT	LDA, SVM, BPNN	84%+	[39]
	T1, T2	3		Yes	BSS, CSP	SVM	92%	[40]
Epoc	T1, T2	5	120	Yes	CSP/EMD, MIDKRA	PSD, Hjort, CWT, DWT	97.79%	[41]
	T1, T2	8	100	Yes	ERS, ERD	LDA	70.37%	[42]
	T1, T2	2	140	Yes	CSP	Naive Bayes	79%	[43]
	T1, T2	15	40	Yes	Wavelet, PSD, EMD	KNN	91.80%	[44]