Intrinsic multiclass classification for motor imagery recognition

Cecilia Lindig-León (1) , Laurent Bougrain (1)

1 NEUROSYS - Analysis and modeling of neural systems by a system neuroscience approach

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.

Mots clés: BCI; multi-class; motor imagery; CSP

Domaines: Automatique / Robotique

Cecilia Lindig-León, Laurent Bougrain. Intrinsic multiclass classification for motor imagery recognition. Berlin Brain-computer interface winter school 2014, Feb 2014, Berlin, Germany. ⟨hal-01092250⟩