A Comparison of Adaptive Filter and Artificial Neural Network Results in Removing Electrocardiogram Contamination from Surface EMG

A Comparison of Adaptive Filter and Artificial Neural Network Results in Removing Electrocardiogram Contamination from Surface EMG

Surface electromyograms (EMGs) are valuable in the pathophysiological study and clinical treatment. These recordings are critically often contaminated by cardiac artifact. The purposeof this article was to evaluate the performance of an adaptive filter and artificial neural network (ANN) in removingelectrocardiogram (ECG) contamination from surface EMGs recorded from the pectoralismajor muscles. Performance of these methods was quantified by power spectral density, coherence, signal to noise ratio, relative error and cross correlation in simulated noisy EMG signals. In between these two methods theANN has better results