Table 5.

Classification accuracy (%) for the detection of epileptic seizures as reported by the discussed stochastic relevance method and by other recent works

Authors	Features/Classifier	Subset	a ac [ % ]
[28]	TFR-2DPCA/k-nn	A,E	100
[42]	t-f analysis/RNN	A,E	99.60
[43]	WT/PNN	A,E	99.99
[44]	PCA FFT/AIRS	A,E	100
[41]	CC+PSD/voting of classifiers	A,E	100
[7]	t-f analysis/ANN	A,E	100
This work	short–time rhythms/k-nn	A,E	99.50
This work	short–time rhythms/SVM	A,E	100
[19]	PCA-RBF/ANN	A,D,E	96.60
[40]	EV/MLP NN	A,D,E	97.50
[45]	PSD+CLZ/SVMA	A,D,E	98.72
[28]	TFR-2DPCA/k-nn	A,D,E	98.80
[7]	t-f analysis/ANN	A,D,E	100
This work	short–time rhythms/k-nn	A,D,E	98.12
This work	short–timerhythms/SVM	A,D,E	100
[7]	t-f analysis/ANN	A,B,C,D,E	89.00
[28]	TFR-2DPCA/k-nn	A,B,C,D,E	94.40
[6]	(WT + eigenvectors)/SVM	A,B,C,D,E	99.20
This work	short–time rhythms/k-nn	A,B,C,D,E	95.78
This work	short–time rhythms/SVM	A,B,C,D,E	96.58