Title: Detection of atrial fibrillation using continuous wavelet transform and wavelet coherence

Authors: Kora Padmavathi; Kalva Sri Ramakrishna

Addresses: Department of ECE, GRIET, Hyderabad, Telangana, India ' Department of ECE, VRSEC, Vijayawada, AP, India

Abstract: Atrial fibrillation (AF) is a type of heart ailment that occurs when atria beats quicker than normal to move blood from atria to the ventricles. Our present study proposes a technique to detect AF ECG patterns with the use of continuous wavelet transform (CWT), wavelet coherence (WTC) is presented. The wavelet coherence function finds common frequencies between two signals and evaluates similarity of the two signals. The mother wavelet used is db4. The ECG variation of atrial fibrillation (AF) is observed in lead II of ECG. For the detection of normal and AF beats, WTC output values are given as the input features for the Levenberg-Marquardt neural network (LMNN) classifier. The data was collected from MIT/BIH AF database.

Keywords: continuous wavelet transform; CWT; wavelet coherence; AF beats; LMNN classifier; MIT/BIH AF database; atrial fibrillation; heart conditions; atria; ECG patterns; electrocardiograms; heart beats; abnormal heart rhythm; cardiovascular disease; Levenberg-Marquardt neural networks.

DOI: 10.1504/IJSCC.2015.072519

International Journal of Systems, Control and Communications, 2015 Vol.6 No.4, pp.292 - 304

Received: 20 Oct 2014
Accepted: 18 Jan 2015
Published online: 16 Oct 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article