Nonlinear Blind Source Separation for EEG Signal Pre-processing in Brain-Computer Interface System for Epilepsy

Abstract

Epilepsy is one of the most common neurological disorders characterized by transient and unexpected electrical disturbance of the brain. The electroencephalogram (EEG) is an invaluable measurement for the purpose of assessing brain activities, containing information relating to the different physiological states of the brain. The EEG potentials represent the combined effect of potentials from a fairly wide region of the scalp. Mixing some underlying components of brain activity apparently generates these potentials. The present study aims to separate the original components of brain activity waveforms from their linear mixture, without further knowledge about their probability distributions and mixing coefficients. This is called the problem of "Nonlinear Blind Source Separation" (NBSS). It consists of the recovery of unobservable original independent sources from several mixed data masked by mixing of the sources. The current study used recently developed source separation method known as "Independent Component Analysis" (ICA) technique for solving blind EEG source separation problem. The ICA algorithm that was used for linear BSS problem is the Principal Component Analysis Nonlinear BSS algorithm. The proposed ICA NBSS model has been implemented using the Matlab version 7.7. The measured real EEG data signals obtained from epileptic states. The results of the present work show the good performance of the proposed model in separating the mixed signals. Since the present ICA model is a reliable, robust and effective unsupervised learning model which, enable us to separate the EEG signals from their observation records. This information further helps in extracting and classifying required features from the analyzed EEG signals to build an EEG based Brain-Computer Interface (BCI) system applied to epilepsy. The system is of great help to neurologists and psychologist in diagnosing and treating various neurological disorders.