ECG Signals Classification Based on Wavelet Transform and Probabilistic Neural Networks

Majlesi Journal of Electrical Engineering

مقاله 4، دوره 3، شماره 3، خرداد 2009، صفحه 33-40   

نوع مقاله: Review Article

شناسه دیجیتال (DOI): 10.1234/mjee.v3i3.245

نویسندگان

Iman Moazen^* ؛ Mohamadreza Ahmadzadeh

چکیده

 In this paper a very intelligent tool with low computational complexity is presented for Electroencephalogram (ECG) signal classification. The proposed classifier is based on Discrete Wavelet Transform (DWT) and Probabilistic Neural Network (PNN). The novelty of this approach is that signal statistics, morphological analysis and DWT of the histogram of signal (density estimation)altogether have been used to achieve a higher recognition rate. ECG signals and their density estimation are decomposed into sub-classes using DWT. A PNN is used to classify ECG signals using statistical discriminating features which are extracted from ECG and its sub-classes. Experimental results on five classes of ECG signals from MIT-BIH arrhythmia database show that the proposed method learns very fast, low computational complexity, and a very high performance compared to the previous methods.

کلیدواژه‌ها

Electrocardiogram؛ en؛ Discrete Wavelet transform؛ Probabilistic neural network؛ Histogram

مراجع

[1]

J. L.Talmon, “Pattern Recognition of the ECG”. Berlin, Germany: Akademisch Proefscrift, 1983.

[2]

Y. H. Hu ,S. Palreddy, and W. J. Tompkins. “A patient-adaptable ECG beat classifier using a mixture of experts approach” IEEE Trans.on Biomed.Eng. Vol.44,pp. 891–900,1997.

[3]

M. Lagerholm ,C. Peterson, G. Braccini, L. Edenbrandt, and L. Sornmo.”Clustering ECG complexes using hermite functions and self-organizing maps” IEEE Trans. On Biomed. Eng, Vol.47,pp. 838–848, 2000.

[4]

R.E .Charllis, R.I. Kittney. “Biomedical signal processing ” (in four parts). Part 1: time domain methods. Med. Biog. Eng. Comput. 509–524 , 1990..

[5]

Y.H. Hu, S. Palreddy and W. Tompkins “A patient adaptable ECG beat classifier using a mixture of experts approach” IEEE Trans.on Biomed. Eng. Vol.44, pp.891–900, 1997.

[6]

J.C.T.B. Moraes, M.O. Seixas, F.N.Vilani and E.V. Costa “A real time QRS complex classification method using Mahalanobis distance” Comput. Cardiol., 201–204, 2002.

[7]

P.D.Chazal and R.B.Reilly “Automatic classification of ECG beats using waveform shape and heart beat interval features”. in Proceedings of the IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP’03), Hong Kong, China, pp. 269–272, 2003.

[8]

K. Minami , H. Nakajima and T. Toyoshima “Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network” IEEE Trans.on Biomed. Eng. No.46, pp.179–185, 1999.

[9]

J.S. Sahabi , S.N.Tandon and R.K.P.Bhatt ”DSP Based ST-Segment Analysis:The wavelet Approach” in: Biomedical Engineering Conference. pp.455-457, Apr 1997 .

[10] Li Shi , Cenyu Yang , Jinying Zhang and HUI Li ”Recognition of ST segment of electrocardiogram based on wavelet transform” Life Science Journal ,vol.4, No.2 January 2007.

[11] C.Alvarado , J.Arregui , J.Ramos and R.Pallas-Areny ”Automatic Detection of ECG ventricular Activity Waves using Continuous Spline” in: 2nd International Conference Electrical and Electronics Engineering, pp.189-192, Sept. 2005.

[12] H.Gholam Hosseini, D.Luo , K.J. Reynolds “The comparison of different feed forward neural network architedtures for ECG signal diagnosis” Medical Engineering & Physics. pp.372-378, 2006.

[13] P.S. Addison, J.N. Watson , G.R. Clegg, M.Holzer, F. Sterz and C.E. Robertson “Evaluating arrhythmias in ECG signals usingwavelet transforms” IEEE Eng. on Med. Biol. No.19 ,p.p 104–109, 2000.

[14] A.S. Al-Fahoum and I. Howitt “Combined wavelet transformation and radial basis neural networks for classifying life-threatening cardiac arrhythmias” on Med. Biol. Eng. Comput , 566–573, 1999.

[15] G.K. Prasad and J.S. Sahambi “Classification of ECG arrhythmiasusing multi-resolution analysis and neural networks” In: IEEE Conference on Convergent Technologies, Bangalore, India, vol. 1, pp. 227–231, 2003.

[16] S. Osowski and T.H. Linh “ECG beat recognition using fuzzy hybrid neural network” IEEE Trans. on Biomed. Eng. No.48, pp. 1265–1271, 2001.

[17] M. Engin "ECG beat classification using neuro-fuzzy network" Pattern Recognition Letters , pp. 1715–1722, 2004.

[18] I. Guler and E.D. Ubeyli “ ECG beat classifier designed by combined neural network model” Pattern Recognit No.38 , pp. 199–208 , 2005.

[19] P.D. Wasserman “Advanced Methods in Neural Computing” VNR Press, pp. 35-55 , 1992.

[20] S.N.Yu and Y.H.Chen “Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network” Pattern Recognition Letters No.28 , pp.1142-1150, 2007.

[21] C.H. Lin , Y.C.Du and T.Chen “Adaptive wavelet network for multiple cardiac arrhythmias recognition” Expert Systems with Applications. No.34. pp. 2601-2611 2008.

[22] J.F. Scholl , J.R. Agre , L.P. Clare and M.C. Gill “A low power impulse signal classifier using the Haar wavelet transform” Proc. SPIE ,Sensors, 136–145, 1999.

[23] L. Rutkowski “Adaptive probabilistic neural networks for pattern classification in time-varying environment” IEEE Trans. on Neural Networks. No.15, pp.811–827, 2004.

[24] I.Guler and, E.D. Ubeyli “A modified mixture of experts network structure for ECG beats classification with diverse features” Eng. Appl. on Artificial Intell., pp. 845–856, 2005.

[25] G. E. Oien , N.A.Bertelsen , T.Eftestol and J.H.Husoy. “ECG rhythm classification using artificial neural networks” In: IEEE Digital Signal Processing Workshop, pp. 514–517, 1996.

[26] Physiobank Archieve Index, MIT-BIH Arrhythmia Database