Minimization of EOG artefacts from corrupted eeg signals using a neural network approach

摘要: In this paper, we propose a neural network (NN) approach to the enhancement of EEG signals in presence EOG artefacts. We recast problem into optimization framework by developing an appropriate cost function. The function is nothing but energy enhanced signal obtained through nonlinear filter formulation, unlike conventionally-used linear formulation. minimization property feedback-type networks exploited solve problem. An analysis has been performed characterize stationary points suggested hardware set-up developed also derived. optimum coefficients from algorithm are used estimate artefact which then subtracted corrupted signal, sample sample, get minimized signal. time plots as LP spectrum show that proposed method very effective. Thus power and efficacy NN have for purpose minimizing artefacts signals.