Binary DE-Based Channel Selection and Weighted Ensemble of SVM Classification for Novel Brain–Computer Interface Using Devanagari Script-Based P300 Speller Paradigm

Abstract

ABSTRACTP300 speller-based Brain–Computer Interface (BCI) is a direct communication from human brain to computer machine that is based on the decoding of brain responses generated by stimulation of a subject using P300 speller paradigm. This communication does not require any muscular movements. A novel Devanagari script (DS) input-based P300 speller system is proposed in this article. A novel 8 × 8 matrix consisting of Devanagari characters, digits, and special symbols has also been proposed as a DS paradigm. The character set associated with the DS paradigm is comparatively larger than the standard 6 × 6 English Row/Column (RC) paradigm. The problems related to crowding effect, fatigue, and task difficulty increase while using the DS paradigm for the P300 speller. This leads to either exhaustive or false detection of characters. In order to overcome these problems, a novel Weighted Ensemble of Support Vector Machines (WESVM)-based method has been proposed for classification. Further improvement in the system performance in terms of accuracy and reduced computational cost has been achieved by employing a binary Differential Evolution (DE) method for optimal channel selection. The proposed method has been tested on the EEG data collected from nine subjects using the DS paradigm. An average accuracy of 94.2% was achieved when the WESVM method was applied with the binary DE-based channel selection method.