Comparison of Different Features and Classifiers for Driver Fatigue Detection Based on a Single EEG Channel

Table 2

Comparison of mean accuracy (%) of combination of four features and ten classifiers.

Classifier	Feature
	SE	FE	AE	PE	Mean ± SD
AB
DT
GP
LS
GNB
KNN
MLP
QDA
RF		91.8 ± 2.7
RS
Mean ± SD

Boldface indicates FE + RF is the optimal method.