ECG and PLI Artifacts Cancellation from Electromyogram

Abstract

Electromyography (EMG) is a test used to discern primary muscle conditions from muscle weakness caused by neurological disorders. EMG recordings are frequently contaminated by noise. The objective of this research was to remove or reduce the two main noises which disturb the EMG signal with help of filtering. The most common noises which are present in the EMG signal are the electrocardiogram (ECG) and the power line interference (PLI). The butter worth filter is proposed to cancel the ECG noise ,and notch filter for removal of PLI artifacts from the main EMG signal and artificial neural network (ANN) which give the error signal (i.e. difference between the actual and target values ) and enhance the signal-to-noise ratio of the output signal. The performance evaluation of the proposed technique is done in terms of signal- to- noise ratio, mean square error, and convergence time. Keywords - Artificial neural network, Digital Filters, Electromyogram (EMG), ECG artifact, PLI.