ECG beat classification by a novel hybrid neural network

This paper presents a novel hybrid neural network structure for the classification of the electrocardiogram (ECG) beats. Two feature extraction methods: Fourier and wavelet analyses for ECG beat classification are comparatively investigated in eight-dimensional feature space. ECG features are determined by dynamic programming according to the divergence value. Classification performance, training time and the number of nodes of the multi-layer perceptron (MLP), restricted Coulomb energy (RCE) and a novel hybrid neural network are comparatively presented. In order to increase the classification performance and to decrease the number of nodes, the novel hybrid structure is trained by the genetic algorithms (GAs). Ten types of ECG beats obtained from the MIT-BIH database and from a real-time ECG measurement system are classified with a success of 96% by using the hybrid structure.

[1]  Carlo Marchesi,et al.  Supervised and unsupervised learning for diagnostic ECG classification , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Marcelo R. Risk,et al.  Beat detection and classification of ECG using self organizing maps , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[3]  W.J. Tompkins,et al.  A patient-adaptable ECG beat classifier using a mixture of experts approach , 1997, IEEE Transactions on Biomedical Engineering.

[4]  Rosaria Silipo,et al.  Artificial neural networks for automatic ECG analysis , 1998, IEEE Trans. Signal Process..

[5]  Z Dokur,et al.  Detection of ECG waveforms by neural networks. , 1997, Medical engineering & physics.

[6]  Arnon D. Cohen,et al.  Biomedical Signal Processing , 1986 .

[7]  Willis J. Tompkins,et al.  Classification of PVCs with a fuzzy logic system , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[8]  Yu Hen Hu,et al.  Customization of ECG beat classifiers developed using SOM and LVQ , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[9]  Jin Li,et al.  Pruning algorithm in wavelet neural network for ECG signal classification , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[10]  S.M. Szilagyi Event recognition, separation and classification from ECG recordings , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[11]  B.G. Celler,et al.  Low computational cost classifiers for ECG diagnosis using neural networks , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[12]  G. Bortolan,et al.  Feature reduction and RBF in classifiers based on ANN , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  T. Ölmez,et al.  Comparison of discrete wavelet and Fourier transforms for ECG beat classification , 1999 .

[14]  C Marchesi,et al.  Classification of arrhythmic events in ambulatory electrocardiogram, using artificial neural networks. , 1995, Computers and biomedical research, an international journal.

[15]  Wei-Chih Hu,et al.  ECG events detection and classification using wavelet and neural networks , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[16]  H. Nakajima,et al.  Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network , 1999, IEEE Transactions on Biomedical Engineering.

[17]  M. R. S. Reddyt,et al.  Automatic detection of PVC's using Autoregressive Models. , 1997 .

[18]  M. Reddy,et al.  Automatic detection of PVCs using autoregressive models , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[19]  B.G. Celler,et al.  Selecting a neural network structure for ECG diagnosis , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[20]  Jin Jie,et al.  Paced ECG analysis based on neural networks , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[21]  L. Leija,et al.  Personal computer system for ECG recognition in myocardial infarction diagnosing based on an artificial neural network , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[22]  I. Daubechies Ten Lectures on Wavelets , 1992 .

[23]  T. Olmez,et al.  Classification of ECG waveforms by using genetic algorithms , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[24]  I. Jouny,et al.  Adaptive wavelet representation and classification of ECG signals , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  T. Olmez,et al.  Classification of ECG waveforms using a novel neural network , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[26]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[27]  T. Olmez,et al.  Detection of ECG waveforms by using artificial neural networks , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  G. Breithardt,et al.  Application of learning vector quantization for localization of myocardial infarction , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[29]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[30]  F.M. Ham,et al.  Classification of cardiac arrhythmias using fuzzy ARTMAP , 1996, IEEE Transactions on Biomedical Engineering.

[31]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[32]  J. Makhoul,et al.  Formation of disconnected decision regions with a single hidden layer , 1989, International 1989 Joint Conference on Neural Networks.

[33]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .