Modeling and feature extraction of ECG using independent component analysis

Abstract

Independent Component Analysis (ICA) is a new technique for analyzing multi-variant data. The idea is to replace PCA (Principal component analysis), which is used as the preprocessing of many ICA algorithms. The purpose of applying ICA will be to segregate ECG from all these. Removal of the baseline drift is required, since it is not of our interest and might affect the quality of the derived respiration. After the preprocessing which removes base line wander, an ICA algorithm is used to estimate the separation matrix and mixing system. The proposed PCA-ICA combined algorithm had a twofold utility of finding QRS complex location as well as marking of all R-peaks in signal s-1 for exact reading and interpretation. Such an approach allows for the consideration of priors on the structural nature of the different class of ECG signals that are to be separated. In the present work, Joint diagonalization of eigen values (JADE) algorithm for ICA is applied to two ECG CSE data base files and the two ECG waveforms are separated as Independent components. The source signal si had base line wander which was removed using ICA.