Neural Network Approach to the Enhancement of EEG Signals in the Presence of EOG Artefacts

Human electroencephalogram (EEG) contains useful diagnostic information on a variety of neurological disorders. However, like all biomedical signals, EEG is also contaminated with many , unwanted signals or artefacts which seriously affects its clinical usefulness. One of the main disturbances is due to the eye movements, which generate an electrical activity called electrooculogram (EOG). In this paper, we propose a Neural Network (NN) approach to the enhancement of EEG signals in the presence of EOG artefacts. We recast the EEG enhancement problem into the optimization framework by developing an appropriate cost function. The cost function is nothing but the energy in the enhanced EEG signal which is obtained through a non-linear prediction formulation, unlike the conventionally used linear prediction formulation. The minimization property of the Hopfield Neural Network is exploited to solve this problem. The optimum non- linear predictor coefficients obtained from this minimization algorithm are used to estimate the EOG artefact which is then subtracted from the corrupted EEG signal, sample by sample, to get the artefact minimized signal. Thus the power and efficacy of the NN approach have been exploited for the purpose of enhancement of CXG signals is the presence of EOG artefacts