Trial Regeneration With Subband Signals for Motor Imagery Classification in BCI Paradigm

Electroencephalography (EEG) captures the electrical activities of human brain. It is an easy and cost effective tool to characterize motor imager (MI) task used in brain computer interface (BCI) implementation. The MI represented by short time trial multichannel EEG. In this paper, raw EEG regenerated using narrowband signals obtained from individual channel. Each channel decomposed into a set subband multivariate discrete wavelet transform. selected subbands are organized two different ways namely vertical arrangement (VaS) horizontal (HaS) regenerate trials. features extracted each arrangements common spatial pattern (CSP). An optimum number classify imagery tasks effectiveness classifiers– linear discriminant analysis (LDA) support vector machine (SVM) studied. performances proposed methods evaluated publicly available benchmark datasets. experimental results show that it performs better than recently developed algorithms.