K - Shrinkage Function for ECG Signal Denoising.

Abstract

ECG signals is a graphical way of recording the electrical actions of the heart for the various diagnostic purposes. ECG signals are affected by various noises such as Electrode Contact, Baseline Wandering, Motion artifact, Power-line interference, Muscle Contractions, and Electrosurgical noise during data acquisition. Denoising is a technique which is used for removing the noise in ECG signals which keeps the useful information. In this paper, a new category of Wavelet shrinkage methods is proposed. The white Gaussian noise is mixed with the ECGs for simulation and tested with the new class of shrinkage function and is compared with the other wavelet shrinkage functions such as hard and soft shrinkage. The performance measures such as Signal to Noise Ratio (SNR) and Percent Root mean - square Difference (PRD) etc. are used to examine the performance of various shrinkage functions. The experimental result shows that it gives better MSE over conventional shrinkage functions.