PATTERN ANALYSIS OF ECG SIGNAL FOR DIFFERENT DATA

Abstract

This dissertation deals with the work done in the area of analysis of electrocardiogram. Electrocardiography is extensively used by cardiologists in clinical interpretations for knowing the functioning of the heart. Electrocardiogram has good correlation with the mechanical activity of the heart which is responsible for the flow of blood throughout the circulatory system. We have developed a real — time algorithm for detection of the QRS complexes of ECG signals. It reliably recognizes QRS complexes based upon digital analysis of slop, amplitude, and width. A special digital band pass filter reduces false detections caused by the various types of interfere-nce present in ECG signal like baseline wander and power line interference etc. This filtering permits use of low thresholds, thereby increasing detection sensitivity. The algorithm automatically adjusts thresholds and parameters periodically to adapt to such ECG changes as QRS morphology and heart rate. We used the MITBIH arrhythmia database to evaluate the QRS detection algorithm. The database consists of 48 half-hour recordings for a total of 24 hour of ECG data. The database is on four - channel FM magnetic tape. Channels 1 and 2 are the two-channel ECG signals. Channel 3 is an annotation channel recorded in a standard binary format, and channel 4 is a binary-recorded timing track. Before measure the parameters for a signal, Least Mean Square (LMS) algorithm and Recursive Least Square (RLS) algorithm used to measure the Mean Square Error (MSE) and Signal —to- Noise Ratio for different signals. Pan — Tompkins's algorithm with modification have been used for the analysis of cardiovascular system and to measure the no. of R-peaks in given signals.