A Fused Multidimensional EEG Classification Method Based on an Extreme Tree Feature Selection

Table 5

Classification accuracy for datasets III BCI 2003 and 2b BCI 2008 using different feature selection methods.

Dataset	Public datasets
	III BCI 2003			2b BCI 2008
	aa	bb	cc	dd	ee	ff
RFE + SVM	0.650	0.750	0.742	0.833	0.675	0.708
PCA + SVM	0.664	0.725	0.742	0.808	0.733	0.675
ET + SVM	0.692	0.783	0.775	0.850	0.750	0.717