ECG arrhythmia classification using simple reconstructed phase space approach

ECG arrhythmias such as ventricular and atrial arrhythmias are one of the common causes of death. These abnormalities of the heart activity may cause an immediate death or cause a damage of the heart. In this paper, an arrhythmia classification algorithm is presented. The proposed method uses the nonlinear dynamical signal processing techniques to analyze the ECG signal in time domain. The classification algorithm is based upon the distribution of the attractor in the reconstructed phase space (RPS). The behavior of the ECG signal in the reconstructed phase space is used to determine the classification features of the whole classifier. To evaluate the performance of the presented classification algorithm, data sets are selected from the MIT database. Two groups of data, learning and testing datasets, are used to design and test the proposed algorithm. A classification sensitivity and specificity of 100% are used to fine tune the parameters of the selected features using the learning dataset. Forty five signals are used to test the proposed approach resulting in 85.7- 100% sensitivity and 86.7-100% specificity are obtained respectively.

[1]  Amjed S. Al-Fahoum,et al.  A quantitative analysis approach for cardiac arrhythmia classification using higher order spectral techniques , 2005, IEEE Transactions on Biomedical Engineering.

[2]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[3]  Howell Tong,et al.  Non-linear time series analysis , 2005 .

[4]  Richard J. Povinelli,et al.  Identification of ECG Arrhythmias Using Phase Space Reconstruction , 2001, PKDD.

[5]  Richard J. Povinelli,et al.  Statistical models of reconstructed phase spaces for signal classification , 2006, IEEE Transactions on Signal Processing.

[6]  Richard J. Povinelli,et al.  Rhythm classification using reconstructed phase space of signal frequency sub-bands , 2003, Computers in Cardiology, 2003.

[7]  Richard J. Povinelli,et al.  Time series classification using Gaussian mixture models of reconstructed phase spaces , 2004, IEEE Transactions on Knowledge and Data Engineering.

[8]  W. J. Tompkins,et al.  Detecting ventricular fibrillation , 1995 .

[9]  Richard J. Povinelli,et al.  Are nonlinear ventricular arrhythmia characteristics lost, as signal duration decreases? , 2002, Computers in Cardiology.

[10]  R. Acharya U,et al.  Comprehensive analysis of cardiac health using heart rate signals , 2004, Physiological measurement.

[11]  K. Chan,et al.  Life-threatening ventricular arrhythmia recognition by nonlinear descriptor , 2005, Biomedical engineering online.

[12]  J. N. Watson,et al.  Evaluating arrhythmias in ECG signals using wavelet transforms , 2000, IEEE Engineering in Medicine and Biology Magazine.