A two-stage four-class BCI based on imaginary movements of the left and the right wrist

Abstract

This paper presents a new concept of a two-modality, four-class brain–computer interface (BCI) classifier based on motor imagination of the left and the right wrist. The noninvasive BCI combines classification of movements of the same limb (wrist flexion and extension) with classification of movements of different limbs, i.e., left and right wrist. Results were obtained from ten right-handed neurologically healthy volunteers. Subjects were not allowed to practice real movements before performing movement imagination. The mean classification accuracy for four different classes was 63±10%. Classification accuracy in four out of ten subjects was ≥70%. A two-stage four-class classifier showed significantly better classification results (p=0.014) than a single four-class classifier. Classifiers were based on Elman's neural networks and features were a selected set of absolute values of Gabor coefficients (GCs), calculated from the Independent Components, rather than the EEG signals’ time series. The most representative features for classification between movements of different limbs were in the alpha and the beta range, while for classification between movements of the same limb they were in the delta and the gamma range. There was no statistically significant difference between classification accuracy of movements of the right vs. the left wrist.