Classifications of motor imagery tasks using k-nearest neighbors

Abstract

We address a classification method for motor imagery tasks-based brain computer interface (BCI). The wavelet coefficients are used to extract the features from the motor imagery electroencephalographic (EEG) signals and the k-nearest neighbor classifier is applied to classify the pattern of left or right hand imagery movement and rest. The performance of the proposed method is evaluated using EEG data recorded with 8 g.tec active electrodes by means of g.MOBIlab+ module. The maximum classification accuracy is 91%.