Enhancing EEG Signals in Brain Computer Interface Using Intrinsic Time-Scale Decomposition

Abstract

A brain-computer interface (BCI) provides a link between the human brain and a computer. The EEG signal is nonlinear and non-stationary. Feature extraction is one of the most important steps in any BCI system; as such, enhancement to the existing methods has been incorporated in this work. For this, we propose a four-class movement imaginations of the right hand, left hand, both hands, and both feet, and develop feature extraction methods utilizing an intelligent method based on intrinsic time-scale decomposition (ITD) and Artificial neural networks (ANN). Based on the processed electroencephalography (EEG) data recorded from nine subjects, ITD accurately classified and discriminated the four classes of motor imagery; the average accuracy achieved is 92.20%.