A New Nonlinear Model Using Neural Networks For Generating Electrocardiogram Signals

Jafarnia Dabanloo, Nader; Ayatollahi, Ahmad; Jouhari Majd, Vahid; Mclernon, Desmond

doi:10.22041/ijbme.2005.13584

A New Nonlinear Model Using Neural Networks For Generating Electrocardiogram Signals

Document Type : Full Research Paper

Authors

Nader Jafarnia Dabanloo ¹

Ahmad Ayatollahi ²

Vahid Jouhari Majd ³

Desmond Mclernon ⁴

¹ Department of Electrical Engineering, Iran University of Science and Technology School of Electronic and Electrical Engineering, The University of Leeds

² Department of Electrical Engineering, Iran University of Science and Technology

³ Department of Electrical Engineering, Tarbiat Modarres University

⁴ School of Electronic and Electrical Engineering, The University of Leeds

10.22041/ijbme.2005.13584

Abstract

The generation of electrocardiogram (ECG) signals by using a mathematical model has recently been investigated. One of the applications of a dynamical model which can artificially produces an ECG signal is the easy assessment of diagnostic ECG signal processing devices. In addition, the model may be also used in compression and telemedicine applications. It is also required that the model has capability to produce both normal and abnormal ECG signals. In this study, it is introduced a new method using radial basis function neural networks in a dynamical model based on McSharry model, to produce artificially the ECG signals. This new method has the advantage of capability to simulate a wider class of physiological signals (both normal and abnormal), compared to McSharry model. The simulation results are presented for normal ECG and three abnormal ones. The accuracy of the model has evaluated by using the error functions. The average of this error for a period of 100 seconds using 20 neurons is less than 2.5 percent for the four modeled cases (one normal and three abnormal).

Keywords

Electrocardiogram signals

dynamical model

Neural network

nonlinear methods

radial basis functions

Subjects

Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing

[1] Jafarnia-Dabanloo N, McLernon DC, Ayatollahi A, Johari-Majd V; A nonlinear signal processing approach to model heart rate variability; ISSPIT2004 conference proceeding 2004: 64-67.

[2] McSharry PE, Clifford G, Tarassenko L, Smith LA; A dynamical model for generating synthetic electrocardiogram signals; IEEE Trans Biomed Eng 2003; 50(3): 289-294.

[3] Malik M, Camm AJ; Heart Rate Variability; USA Futura Publication Comp; 1995.

[4] Huang TC, Ramaekers D, Lin J, De Geest H, Aubert A E; Analysis of heart rate variability using power spectral analysis and nonlinear dynamics; Computers in Cardiology 1994: 569-572.

[5] Haque MA; Investigation of the nonlinearity in the heart rate dynamics; Medical Engineering and Physics 2001; 23(2): 111 115.

[6] Narayana DD, Krishan SM, Srinivasan NA; A dynamic nonlinear time domain model for reconstruction and compression of cardiovascular signals with application to medicine; Computers in Biology and Medicine 2003; 33(1): 45-63.

[7] Bezerianos A, Papadimitriou S, Alexopoulos D; Radial basis function neural networks for the characterization of heart rate variability dynamics; Artificial Intelligence in Medicine 1999; 15: 215-234.

[8] Davey P; A new physiological method for heart rate correction of the QT interval; Heart (on line) 1999; 82: 183-186.

[9] McLernon DC, Jafarnia-Dabanloo N, Ayatollahi A, Johari-Majd V; A new nonlinear model for generating RR tachograms; Computer in Cardiology, conference proceeding 2004: 481-484.

[10] Park J, Sandberg JW; Universal approximation using radial basis functions network; Neural Computation 1991; 3: 246-257.