Empirical mode decomposition based ECG enhancement and QRS detection

Authors:
Saurabh Pal;Madhuchhanda Mitra
Affiliations:
Department of Applied Electronics and Instrumentation Engineering, Heritage Institute of Technology, Kolkata, West Bengal, India;Department of Applied Physics, University of Calcutta, West Bengal, India
Venue:
Computers in Biology and Medicine
Year:
2012

Citing 6
Cited 0

Syntactic Pattern Recognition of the ECG

IEEE Transactions on Pattern Analysis and Machine Intelligence
Characterization and elimination of AC noise in electrocardiograms: a comparison of digital filtering methods

Computers and Biomedical Research
ECG signal denoising and baseline wander correction based on the empirical mode decomposition

Computers in Biology and Medicine
A new mathematical based QRS detector using continuous wavelet transform

Computers and Electrical Engineering
Automatic detection of ECG wave boundaries using empirical mode decomposition

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
QRS complex detection using Empirical Mode Decomposition

Digital Signal Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper an Empirical Mode Decomposition (EMD) based ECG signal enhancement and QRS detection algorithm is proposed. Being a non-invasive measurement, ECG is prone to various high and low frequency noises causing baseline wander and power line interference, which act as a source of error in QRS and other feature extraction. EMD is a fully adaptive signal decomposition technique that generates Intrinsic Mode Functions (IMF) as decomposition output. Here, first baseline wander is corrected by selective reconstruction based slope minimization technique from IMFs and then high frequency noise is removed by eliminating a noisy set of lower order IMFs with a statistical peak correction as high frequency noise elimination is accompanied by peak deformation of sharp characteristic waves. Then a set of IMFs are selected that represents QRS region and a nonlinear transformation is done for QRS enhancement. This improves detection accuracy, which is represented in the result section. Thus in this method a single fold processing of each signal is required unlike other conventional techniques.