長久以來心律不整檢測和分類都是心電圖訊號處理的主要議題。在此研究中，我們開發出一種針對多類型心律不整的辨識系統，包含心房顫動、心房撲動、以及具有生命危險的心室過速、心室撲動與心室顫動。此心電圖訊號辨識系統可分為不同的特徵提取技術與分類器的應用。在Alpha穩定分佈中的高斯分佈與心律不整有相似的性質，像是尖銳的峰值與脈衝特性，相較於一般的訊號分佈有較好的預期結果。此外帶有心律不整的心電圖訊號在時域上看起來混亂且難以解讀，利用機率密度函數與累加分佈函數進行統計分析，將會是一個更具有潛力的辨識特徵方法，因此本論文提出一種基於Alpha穩定分佈估計心律不整訊號參數的新方法。由於心律不整具有多種不同的形式，我們基於多種機器學習演算法中的分類器來驗證此方法的可行性。本論文提出的系統架構能夠分類不同的心律不整疾病，並證明使用Alpha穩定分佈足以區分心電圖訊號的主要特徵。

Electrocardiogram (ECG) has been used as the media for detecting and recognizing cardiac arrhythmias. In this research, we develop a recognition system for a variety of arrhythmias such as atrial fibrillation (AFIB), atrial flutter (AFL), and life threatening ventricular tachycardia (VT), ventricular flutter (VFL), and ventricular fibrillation (VFIB). This ECG recognition system is developed based on several feature extraction techniques followed by neural network classifiers. Alpha-stable distribution, with a general form of Gaussian distribution, shares the same properties with various arrhythmias such as sharp spikes or occasional impulses of outlying observations than one would expect from normally distributed signals. Since some electrocardiograms with arrhythmias are chaotic and difficult to be modeled in the time domain, interpreting the syndromes with their statistical information would be an alternative for exploring underlying characteristics. In addressing this problem, a novel method of accurate parameter estimation of cardiac signal is proposed. In addition, based on various arrhythmia types, various classifiers with deep learning algorithms are designed to verify the usefulness of our approaches. The developed system has shown the potential for alpha stable distribution to distinguish the main features of the ECG signal and thereby enhance the classification scheme.

[1] M. G. Tsipouras, D. I. Fotiadis, and D. Sideris, “An arrhythmia classification system based on the RR-interval signal,” Artificial Intelligence in Medicine, vol. 33, no. 3, pp. 237-250, Mar. 2005.
[2] R. D. Throne, J. M. Jenkins, and L. A. DiCarlo, “A comparison of four new time-domain techniques for discriminating monomorphic ventricular tachycardia from sinus rhythm using ventricular waveform morphology,” IEEE Trans. Biomedical Engineering, vol. 38, no. 6, pp. 561-570, Jun. 1991.
[3] V. X. Afonso and W. J. Tompkins, “Detecting ventricular fibrillation,” IEEE Engineering in Medicine and Biology Maganize, vol. 14, no.2, pp. 152-159, Mar.-Apr. 1995.
[4] A. Amann, R. Tratnig , and K. Unterkofler, “Reliability of old and new ventricular fibrillation detection algorithms for automated external defibrillators,” BioMedical Engineering OnLine, vol. 4, no. 60, Jun. 1991.
[5] J. Park, S. Lee, and M. Jeon, “Atrial fibrillation detection by heart rate variability in Poincare plot,” BioMedical Engineering OnLine, vol. 8, no. 38,pp. 1-12, Dec. 2009.
[6] F. Yaghouby, A. Ayatollahi, R. Bahramali, M. Yaghouby, and A.H. Alavi, “Towards automatic detection of atrial fibrillation: A hybrid computational approach,” Comput Biomedical , vol. 40, no. 11-12, pp. 919-930, Nov. 2010.
[7] M.S. Islam, N. Ammour, N. Alajlan, and H. Aboalsamh, “Rhythm-based heartbeat duration normalization for atrial fibrillation detection,” Comput Biomedical, vol. 72, pp. 160-169, May 2016.
[8] S. W. Chen, P. Clarkson, and Q. Fan, “A robust sequential detection algorithm for cardiac arrhythmia classification,” IEEE Trans. Biomedical Engineering, vol. 43, no. 11, pp. 1120-1124, Aug. 2002.
[9] I. Jekova and V. Krasteva, “Real time detection of ventricular fibrillation and tachycardia,” Physiol Measurement, vol. 25, no. 5, pp. 1167-1178, Oct. 2004.
[10] E. M. Anas, S. Y. Lee, and M. K. Hasan, “Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions,” BioMedical Engineering OnLine, vol. 9, no. 1,pp. 1-22, 2010.
[11] M. A. Arafat, J. Sieed, and M. K. Hasan, “Detection of ventricular fibrillation using empirical mode decomposition and Bayes decision theory,” Computers in Biology and Medicine, vol. 39, no. 11, pp. 1051-1057, Nov. 2009.
[12] R. Alcaraz and J. J. Rieta, “Wavelet bidomain sample entropy analysis to predict spontaneous termination of atrial fibrillation,” Physiol Measurement, vol. 29, no. 1, pp. 65-80, Jan. 2008.
[13] Q. Li, C. Rajagopalan, and G. D. Clifford, “Ventricular fibrillation and tachycardia classification using a machine learning approach,” IEEE Trans. Biomedical Engineering, vol. 61, no. 6, pp. 1607-1613, Jun. 2014.
[14] D. A. Coast, R. M. Stern, G. G. Cano, and S. A. Briller, “An approach to cardiac arrhythmia analysis using hidden Markov models,” IEEE Trans. Biomedical Engineering, vol. 37, no. 9, pp. 826-836, Sep. 1990.
[15] Y. Wang, Y. S. Zhu, N. V. Thakor, and Y. H. Xu, “A short-time multifractal approach for arrhythmia detection based on fuzzy neural network,” IEEE Trans. Biomedical Engineering, vol. 48, no. 9, pp. 989-995, Sep. 2001.
[16] L. Khadra, A. S. Al-Fahoum, and H. Al-Nashash, “Detection of life-threatening cardiac arrhythmias using the wavelet transformation,” Medical and Biological Engineering and Computing, vol. 35, no. 6, pp. 626-632, Nov. 1997.
[17] S. W. Chen, “A two-stage discrimination of cardiac arrhythmias using a total least squares-based prony modeling algorithm,” IEEE Trans. Biomedical Engineering, vol. 47, no. 10, pp. 1317-1327, Oct. 2000.
[18] L. Khadra, A. S. Al-Fahoum, and S. Binajjaj, “A quantitative analysis approach for cardiac arrhythmia classification using higher order spectral techniques,” IEEE Trans. Biomedical Engineering, vol. 52, no. 11, pp. 1840-1845, Nov. 2005.
[19] X. S. Zhang, Y. S. Zhu, N. V. Thakor, and Z. Z. Wang, “Detecting ventricular tachycardia and fibrillation by complexity measure,” IEEE Trans. Biomedical Engineering, vol. 46, no. 5, pp. 548-555, May 1999.
[20] A. Orozco-Duque, F. J. Martinez-Tabares, J. Gallego, C. A. Rodriguez, I. D. Mora, G. Castellanos-Dominguez, and J. Bustamante, “Classification of premature ventricular contraction based on discrete wavelet transform for real time applications,” in Proc. of IEEE Intl. Conf. Pan American Health Care Exchanges, pp. 1-5, Apr.-May 2013.
[21] R. J. Martis, C. Chakrabort, and A. K. Ray, Wavelet-based Machine Learning Techniques for ECG Signal Analysis, Springer, 2014.
[22] Q. Zhao and L. Zhang, “ECG feature extraction and classification using wavelet transform and support vector machines,” in Proc. of Intl. Conf. on Neural Networks and Brain, vol. 2, pp. 1089-1092, Oct. 2005.
[23] S. Faziludeen and P. V. Sabiq, “ECG beat classification using wavelets and SVM,” in Proc. of IEEE Conf. on Information and Communication Technologies, pp. 815-818, Apr. 2013.
[24] G. Selvakumar, K. B. Bagan, and B. Chidambarajan, “Wavelet Decomposition for Detection and Classification of Critical ECG Arrhythmias,” in Proc. of Conf. on Mathematics and Computers in Biology and Chemistry, pp. 80-84, Jan. 2007.
[25] M. S. Billah, T. B. Mahmud, F. S. Snigdha, and M. A. Arafat, “A novel method to model ECG beats using Gaussian functions,” in Proc. of Intl. Conf. Biomedical Engineering and Informatics, pp. 612-616, Oct. 2011.
[26] Y. Lu, J. Y. Yan, and Y. Yam, “A generalized ECG dynamical model with asymmetric Gaussians and its application in model-based ECG denoising,” in Proc. of Intl. Conf. on Biomedical Engineering and Informatics, pp. 1-5, Oct. 2009.
[27] R. Adler, R. E. Feldman, and M. S. Taqqu, A Practical Guide to Heavy Tails: Statistical Techniques and Applications, Springer Science and Business Media, 1998.
[28] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” Computational Learning Theory, pp. 144-152, 1992.
[29] D. H. Hubel and T. N. Wiesel, “Receptive fields, binocular interaction and functional architecture in the cat's visual cortex,” Journal of Physiology, vol. 160, no. 1, pp. 106-154, Jan. 1962.
[30] K. Fukushima, “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,” Biological Cybernetics, vol. 36, no. 4, pp. 193-202, Apr. 1980.
[31] R. Jozefowicz, W. Zaremba, and I. Sutskever, “An empirical exploration of recurrent network architectures,” in Proc. of Intl. Conf. on Machine Learning, Jul. 2015.
[32] P. Smolensky, Information Processing in Dynamical Systems: Foundations of harmony theory, MIT Press, 1986.
[33] M. Á. Carreira-Perpiñán and G. E. Hinton, “On contrastive divergence learning,” in Proc. of Intl. Conf. on Artificial Intelligence and Statistics, pp. 33-40, Apr. 2005.
[34] P. G. Georgiou, P. Tsakalides, and C. Kyriakais, “Alpha-stable modeling of noise and robust time-delay estimation in the presence of impulsive noise,” IEEE Trans. Multimedia, vol. 1, no. 3, pp. 291-301, Sep. 1999.
[35] C. L. Nikias and M. Shao, Signal Processing with Alpha-Stable Distributions and Applications, John Wiley & Sons, Wiley-Interscience, 1995.
[36] I. A. Koutrouvelis, “Rregression-type estimation of the parameters of stable laws,” Journal of the American Statistical Association, vol. 75, no. 372, pp. 918-928, Dec. 1980.
[37] J. H. McCulloch, “Simple consistent estimators of stable distribution parameters,” Communications in Statistics - Simulation and Computation, vol. 15, no. 4, pp. 1109-1136, 1986.
[38] S. Mittnnik and T.Doganoglu, “Computing the probability density function of the stable Paretian distribution,” Mathematical and Computer Modelling, vol. 29, no. 10-12, pp. 235-240, May-Jun. 1999.
[39] J. P. Nolan, “An algorithm for evaluating stable densities in Zolotarev's (M) parameterization,” Mathematical and Computer Modelling, vol. 29, no. 10-12, pp. 229-233, 1999.
[40] G. B. Moody and R. G. Mark, “The MIT-BIH arrhythmia database on CD-ROM and software for use with it,” Computers in Cardiology, vol. 17, pp. 185-188, Sep. 1990.
[41] J. Pan, W. J. Tompkins, “A real-time QRS detection algorithm,” IEEE Trans. Biomed. Eng., vol. BME-32, no. 3, pp. 230-236, Mar. 1985.