Removal OF EMG and ECG artifacts from EEG based on real time recurrent learning algorithm

Abstract

EEG (Electroencephalograph) recording from the scalp has biological artifacts and external artifacts.  Biological artifacts, which are generated, can be EMG (Electromyograph) signal, EOG  (Electrooculograph) signal or ECG (Electrocardiograph) signal. These artifacts appear as noise in the  recorded EEG signal individually or in a combined manner. Usually physicians are misled by these  noisy signals and the EEG analysis can go wrong. This paper presents noise cancellation i.e. removal  of noise signal which can be either EMG, ECG or a combination of these two artifacts from the  corrupted EEG signal and also signal enhancement both using recurrent learning technique. For this  purpose, we have implemented the RTRL (Real Time Recurrent Learning) algorithm, which is the most  recent and sophisticated real time neural networks algorithm. This algorithm is coded using C language  and is executed on the DSP processor TMS320CV5402. The obtained result is verified using MATLAB.    Key words: Electroencephalograph (EEG), Recurrent Multilayer Perceptron (RMLP), Real Time Recurrent  Learning (RTRL).