Wavelet-Based ECG Signal Analysis and Classification

Authors: Madina Hamiane, May Hashim Ali

Abstract:

This paper presents the processing and analysis of ECG signals. The study is based on wavelet transform and uses exclusively the MATLAB environment. This study includes removing Baseline wander and further de-noising through wavelet transform and metrics such as signal-to noise ratio (SNR), Peak signal-to-noise ratio (PSNR) and the mean squared error (MSE) are used to assess the efficiency of the de-noising techniques. Feature extraction is subsequently performed whereby signal features such as heart rate, rise and fall levels are extracted and the QRS complex was detected which helped in classifying the ECG signal. The classification is the last step in the analysis of the ECG signals and it is shown that these are successfully classified as Normal rhythm or Abnormal rhythm.  The final result proved the adequacy of using wavelet transform for the analysis of ECG signals.

Keywords: ECG Signal, QRS detection, thresholding, wavelet decomposition, feature extraction.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1132423

References:

[1] MichiganTech , What is Biomedical Engineering, http://www.mtu.edu /biomedical/department/what-is/ (Accessed on 7 Feb 2016)
[2] Massachusetts Institute of Technology, ECG Overview http://web.mit.edu/2.75/lab/ECG%20Overview.pdf
[3] Rami Cohen, Signal Denoising using wavelets, Israel Institute of Technology, 2012
[4] Virginia Tech, Wavelet Transform and Denoising, https://theses.lib. vt.edu/ theses/available/etd-12062002 152858/unrestricted/Chapter4.pdf
[5] Physionet, MIT-BIH Arrhythmia Database https://www.physionet.org/physiobank/database/mitdb/
[6] Rajni, Inderbir Kaur, Electrocardiogram Signal Analysis - An Overview, International Journal of Computer Applications Volume 84, No 7, pp.22-25, 2013.
[7] Manuel Blanco-Velasco, Binwei Weng, Kenneth E Barne,ECG Signal denoising and baseline wander correction based on the empirical mode decomposition, Computers in Biology and Medicine, 38 (1): 1-13,2008
[8] Md Kafiul Islam, Artifact characterisation, Detection and Removal for in-vivo Neural recording, National university of Singapore.
[9] Sameer K. Salih , S. A. Aljunid , Abid Yahya ,Khalid Ghailan, A Novel Approach for Detecting QRS Complex of ECG signal, Computer & Communication School UNI-MAP, Perlis, Malaysia, 2012
[10] ECG Libray, Dean Jenkins and Stephen Gerred, http://www. cglibrary.com/norm.php
[11] N. Belgacem et. al., Supervised classification of ECG using neural networks, www.univ-tlemcen.dz/manifest/CISTEMA2003/./GBM8.pdf.