Analysis of QRS detection in ECG signal using entropy and edge detection

Abstract

Electrocardiogram (ECG) is the most vital and widely used methodology to check the guts connected diseases. For
identifying arrhythmia classification, it needs large storage space and intensive manual effort. The conventional technique
of visual analysis to examine the ECG signals by doctors or physicians does not seem to be effective and time
overwhelming. In this work, an attempt has been made towards the development of an automated system for investigation
of QRS detection in ECG signals using Entropy and Edge detection. Conventional ECG signals are used from MIT/BIH
arrhythmia database in this study. The ECG signals are processed using Edge based detection and related to Pan-Tompkins
algorithm extracting the QRS features using Entropy threshold of edge detection operators. Results show that about
98.11% of overall accuracy values of the proposed system with sensitivity of 99.2% and 98.9% Positive Predictivity using
Prewitt based Edge detection.