Determination method of motor imagined limbs based on the EEG signals

Abstract

Recently, many researchers have been studying the Brain Computer Interface (BCI). As one of them, there are some methods for extracting the ERD and ERS from EEG during motor imagery and discriminating the motor of right and left hand using them. Currently, however, these methods enable us to discriminate among a few classes, such as the left and right hand only or the right hand and leg only. Furthermore, they require a long-term training to improve the discrimination rate. In this paper, we construct a system for discriminating motor imaged limbs using Movement-Related Cortical Potential(MRCP), such as BereitschaftsPotential(BP), Negative Slope(NS) and Contingent Negative Variation(CNV), in which it does not require a long-term training.