A Novel Method for ECG Signal Discrimination of Cardiac Arrhythmias Based on Pade’s Approximation Technique

This paper presents an electrocardiogram (ECG) beat classification scheme based on Pade’s approximation technique and neural networks for discriminating five ECG beat types. These are normal rhythm (NR), ventricular couplet (VC), ventricular tachycardia (VT), ventricular bigeminy (VB), and ventricular fibrillation (VF). ECG signal samples from MIT-BIH arrhythmia database are used to evaluate the proposed method. The ECG signal is modeled as a rational function of two polynomials of unknown coefficients using Pade’s approximation technique, where the model coefficients, poles of the denominator, are used as a feature for the ECG signals. The classification is performed using a multilayered perceptron (MLP) neural network. The experimental results demonstrate the efficiency of the proposed techniques for modeling and classifying the ECG beat types using Pade’s approximation technique and MLP neural network.

[1]  Albert Berni,et al.  Target Identification by Natural Resonance Estimation , 1975, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Tapan K. Sarkar,et al.  A discussion of E-pulse method and Prony's method for radar target resonance retrieval from scattered field , 1988, 1988 IEEE AP-S. International Symposium, Antennas and Propagation.

[3]  F. El-Hefnawi.  Frequency perturbation for circular array of coupled cylindrical dipole antennas , 1988, 1988 Symposium on Antenna Technology and Applied Electromagnetics.

[4]  X. G. Li,et al.  Target feature extraction of frequency domain data with optimal rational approximation , 1992, IEEE Antennas and Propagation Society International Symposium 1992 Digest.

[5]  Jianguo Huang,et al.  Source classification using pole method of AR model , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  F. El-Hefnawi,et al.  Use of Prony's method for extracting the poles and zeros yielding a wideband window type response of circular antenna arrays , 1998, Proceedings RAWCON 98. 1998 IEEE Radio and Wireless Conference (Cat. No.98EX194).

[7]  Szi-Wen Chen,et al.  A two-stage discrimination of cardiac arrhythmias using a total least squares-based Prony modeling algorithm , 2000, IEEE Trans. Biomed. Eng..

[8]  Stephane H Maes.  Monitoring, identification, and selection of audio signal poles with characteristic behaviors, for separation and synthesis of signal contributions , 2000 .

[9]  Branko G. Celler,et al.  Classification of the electrocardiogram using selected wavelet coefficients and linear discriminants , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[10]  Carsten Peterson,et al.  Clustering ECG complexes using Hermite functions and self-organizing maps , 2000, IEEE Trans. Biomed. Eng..

[11]  M. Vajta.  Some remarks on Padé-approximations , 2000 .

[12]  Y.M. Kadah,et al.  of the 23 rd Annual EMBS International Conference , October 25-28 , Istanbul , Turkey ROBUST FEATURE EXTRACTION FROM ECG SIGNALS BASED ON NONLINEAR DYNAMICAL MODELING , 2004 .

[13]  D. Ge,et al.  Cardiac arrhythmia classification using autoregressive modeling , 2002, Biomedical engineering online.

[14]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[15]  Walter Van Assche,et al.  Pade and Hermite-Pade approximation and orthogonality , 2006, math/0609094.

[16]  Gregory T. A. Kovacs,et al.  Robust Neural-Network-Based Classification of Premature Ventricular Contractions Using Wavelet Transform and Timing Interval Features , 2006, IEEE Transactions on Biomedical Engineering.

[17]  Nicholas V. Shuley,et al.  Radar Target Identification Using a “Banded” E-pulse Technique , 2006 .

[18]  Sarabjeet Singh Mehta,et al.  Support Vector Machine for Cardiac Beat Detection in Single Lead Electrocardiogram , 2007, IMECS.

[19]  Xin-Jian Xiang,et al.  Study of Feature Extraction Based on Autoregressive Modeling in EGG Automatic Diagnosis , 2007 .

[20]  V. C. Veera Reddy,et al.  ANN FOR CLASSIFICATION OF CARDIAC ARRHYTHMIAS , 2008 .

[21]  Moncef Gabbouj,et al.  A Generic and Robust System for Automated Patient-Specific Classification of ECG Signals , 2009, IEEE Transactions on Biomedical Engineering.