Intrinsic multiclass classification for motor imagery recognition
Résumé
While intrinsic multiclass classifiers are an intuitive approach to discriminate more than two classes, they have not been deeply evaluated on BCI multiclass problems. This study aimed at comparing intrinsic multiclass classifiers and ensembles of 2-class classifiers on the BCI competition IV, dateset IIa with four motor imageries (left hand, right hand, feet and tongue) using a standard protocol as those used in the competition.