Extraction of Various Features of ECG Signal

Abstract

Principal component analysis (PCA) is one of the most valuable results oriented techniques of applied linear algebra. PCA is used abundantly in all forms of analysis from neuroscience to computer graphics because it is a simple, non-parametric method of extracting relevant information from confusing data sets. Extracting or decoding this information or feature from ECG signal has been found very helpful in explaining and identifying various pathological conditions. The feature extraction procedure can be accomplished straightforward by analysing the ECG visually on paper or screen. In addition, manual feature extraction is always prone to error. Therefore, ECG signal processing has become an indispensable and effective tool for extracting clinically significant information from ECG signals, for reducing the subjectivity of manual ECG analysis and for developing advanced aid to the physician in making well-founded decisions. ECG analysis systems are usually designed to process ECG signals measured under particular conditions, like resting ECG interpretation, stress test analysis, ambulatory ECG monitoring and intensive care monitoring. Noise reduction is closely related to data compression as reconstruction of the original signal usually involves a set of eigenvectors whose noise level is low, and thus the reconstructed signal becomes low noise, such reduction is, however, mostly effective for noise with muscular origin. The purpose of the thesis is to provide an overview of PCA in ECG signal compression.