نوع مقاله : مقاله کامل پژوهشی
نویسندگان
1 مربی دانشگاه آزاد اسلامی، واحد سبزوار
2 استادیار دانشگاه آزاد اسلامی، واحد گناباد
چکیده
در این مقاله یک الگوریتم جدید ومؤثر جهت طبقه‌بندی آریتمی‌های مهم قلبی با استفاده از سیگنال تغییرات ضربان قلب HRV که دارای مشخصه‌های آشوبگونه بهتری نسبت به ECG ست پیشنهاد شده است. در مرحله استخراج ویژگی، علاوه بر ویژگی‌های متداول خطی زمانی و فرکانسی، ویژگی‌های غیرخطی (آشوبگون) نیز بررسی شده‌اند. برای تسهیل در تعلیم و افزایش دقت طبقه‌بندی‌کننده، از دو تکنیک استفاده شده است: الف) تعداد ویژگی‌های استخراج شده توسط تکنیک آنالیز تمایزی تعمیم‌یافته GDA کاهش یافته است بدون آنکه این کاهش محتوای اطلاعات موجود را تقلیل دهد. ب) به کمک یک نگاشت خودسازمانده SOM برای هر گروه از داده‌ها، داده‌هایی برای تعلیم انتخاب شده‌اند که بیشترین محتوای اطلاعات را در مورد آن گروه داشته باشند. بررسی نتایج نشان می‌دهد که ویژگی‌های آشوبگونه نقش موثری در افزایش دقت سیستم تشخیص آریتمی قلبی دارد بنحوی که دقت کلی روش از حدود 92٪ به 97٪ افزایش یافته است. همچنین این نتایج موید اهمیت بکارگیری تکنیک‌های GDA و SOM به نحو پیش‌گفته است.در مرحله طبقه‌بندی طبقه‌بندهای MLP و SVM و PNN مورد استفاده قرار گرفته و نتایج مقایسه شده است. در این مقاله7 نوع آریتمی مختلف VT, VF, LBBB, CHB, AF, AFL, PVC و نیز گروه ضربانهای طبیعی (NSR) با دقت کلی 97.4 درصد شناسایی و طبقه‌بندی شده‌اند.
کلیدواژه‌ها
- آریتمی قلبی
- سیگنال ECG
- سیگنال HRV
- شبکه عصبی مصنوعی
- ماشینهای بردار پشتیبان SVM
- تحلیل تمایزی تعمیم‌یافته GDA
- نگاشت خودسازمانده SOM
موضوعات
عنوان مقاله [English]
Heart arrhythmia diagnosis by neural networks using chaotic features of HRV signal and generalized discriminant analysis
نویسندگان [English]
- Reza Soleimani 1
- Seyed Mpjtaba Rouhani 2
1 Lecturer, Islamic Azad University of Sabzevar
2 Assistant Professor, Islamic Azad University of Gonabad
چکیده [English]
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear (chaotic) features are examined, too. To increase classification accuracy and facilitate learning, two techniques are used: a) extracted features are reduced by generalized discriminant analysis (GDA) and b) by a self organizing map (SOM), the most informant data are selected. Chaotic features help to improve diagnosis accuracy from 92% up to 97%. The results indicate the importance of GDA and SOM in efficiency of proposed algorithm. MLP, SVM and PNN classifiers are examined and compared. The proposed algorithm was able to diagnose 7 arrhythmias PVC, AFL, AF, CHB, LBBB, VF, VT and normal sinus rhythm (NSR) with 97.4% accuracy.
کلیدواژه‌ها [English]
- Heart arrhythmia
- Electrocardiography (ECG)
- Heart rate variability (HRV)
- Neural Networks
- Support vector machines (SVM)
- self organizing maps (SOM)
- generalized discriminant analysis (GDA)
[1] Wang Y., Zhu Y.S., Thakor N.V. and Xu Y.H., “A short-time multifractal approach for arrhythmia detection based on fuzzy neural network,” IEEE Transactions on Biomedical Engineering, Vol. 48, No. 9, pp 989–995, Sep. 2001.
[2] AI_Fahoum_ A.S.,_ Howitt_ I.,_ “Combined_ wavelet_ transformation_ and_ radial_ basis_ neural networks for classifying life threatening cardiac arrhythmias,” Med. Biol. Eng. Computer, Vol. 37, No. 5, pp 566-573, 1999.
[3] Song M.H., Lee J., Cho S.P., Lee K.J. and Yoo S.K., “Support vector machine based arrhythmia classification using reduced features,” International Journal of Control, Automation and Systems, Vol. 3, No. 4, pp 571-579, Dec. 2005.
[4] Kadbi M.H., Hashemi J., Mohseni H.R. and Maghsoudi A., “Classification of ECG arrhythmias based on statistical and time-frequency features,” IEE Advances in Medical, Signal and Information Processing, pp 1-4, July 2006.
[5] Gharaviri A., Dehghan F., Teshnelab M., Moghaddam H.A., “Comparison of neural network, ANFIS, and SVM classifiers for PVC arrhythmia detection,” IEEE, Proceedings of the Seventh International Conference on Machine Learning and Cybernetics, Vol. 2, pp 750-755, 2008.
[6] Kara S., Okandan M., “Atrial fibrillation classification with artificial neural networks,” Elsevier Pattern Recognition Society, Vol. 40, No. 11, pp 2967-2973, 2007.
[7] Minami K.I., Nakajima H. and Toyoshima T., “Realtime discrimination of ventricular tachyarrhythmia with Fourier transform neural network,” IEEE Transactions on Biomedical Engineering, Vol. 46, No. 2, pp 179-185, 1999.
[8] Khadra L., AI-Fahoum A.S., AI-Nashash H., “Detection of life-threatening cardiac arrhythmias using the wavelet transformation,” Med. Biol. Eng. Comp., Vol. 35, No. 6, pp 626-632, 1997.
[9] Owis M.I., Abou-Zied A.H., Youssef A.M. and Kadah Y.M., “Study of features based on nonlinear dynamical modeling in ECG arrhythmia detection and classification,” IEEE Transactions on Biomedical Engineering, Vol. 49, No. 7, pp 733-736, 2002.
[10] Jovic A., Bogunovic N., “Analysis of ECG records using ECG chaos extractor platform and weka system,” IEEE Proceedings of conf. on information technology interfaces, pp 347-352,June 2008.
[11] Acharya R., Kumar A., Bhat P.S., Lim C.M., Iyengar S.S., Kannathal N., Krishnan S.M., “Classification of cardiac abnormalities using heart rate signals,” Med. Biol. Eng. Comp., Vol. 42, No. 3, pp 288-293, 2004.
[12] Anuradha B. and Veera Reddy V.C., “ANN for classification of cardiac arrhythmias,” ARPN Journal of Engineering and Applied Sciences, Vol. 3, No. 3, pp 1- 6, 2008.
[13] Acharyaa U.R., Bhat P.S., Iyengar S.S., Rao A., Dua S., “Classification of heart rate data using artificial neural network and fuzzy equivalence relation”, Elsevier Pattern Recognition Society, Vol. 36, No. 1, pp 61–68, 2003.
[14] Tsipouras M.G., Fotiadis D.I., “Automatic arrhythmia detection based on time and time-frequency analysis of heart rate variability,” Elsevier Computer Methods and Programs in Biomedicine, Vol. 74, No. 2, pp 95-108, 2004.
[15] Ghodrati A., Murray B., Marinello S., “RR Interval analysis for detection of atrial fibrillation in ECG monitors,” 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2008., pp 601-604 , Aug. 2008.
[16] Ince, T.; Kiranyaz, S.; Gabbouj, M.; "A Generic and Robust System for Automated Patient-Specific Classification of ECG Signals," IEEE Transactions on Biomedical Engineering, Vol.56, No.5, pp.1415-1426, May 2009.
[17] Faezipour, M.; Saeed, A.; Bulusu, S.C.; Nourani, M.; Minn, H.; Tamil, L.; "A Patient-Adaptive Profiling Scheme for ECG Beat Classification," Information Technology in Biomedicine, IEEE Transactions on , Vol.14, No.5, pp.1153-1165, Sept. 2010.
[18] Llamedo, M.; Martínez, J.P.; "Heartbeat Classification Using Feature Selection Driven by Database Generalization Criteria," IEEE Transactions on Biomedical Engineering, Vol.58, No.3, pp 616-625, March 2011.
[19] Rouhani, M.; Soleymani, R.; "Neural Networks Based Diagnosis of Heart Arrhythmias Using Chaotic and Nonlinear Features of HRV Signals," Computer Science and Information Technology - Spring Conference, IACSITSC '09, pp 545-549, 17-20 April, Singapore, 2009.
[20] Baudat G., Anouar F., “Generalized discriminant analysis using a kernel approach,” Neural Comput., Vol. 12, No. 10, pp 2385-2404, 2002.
[21] Hamilton P., Tompkins W., “Quantitative investigation of QRS detection rules using the MIT/BIH arrhythmia database,” IEEE Transactions on Biomedical Engineering, Vol. 33, No. 12, pp 1157-1165, 1986.
[22] Pan J., Tompkins W.J., “A real time QRS detection algorithm,” IEEE Transactions on Biomedical Engineering, Vol. 32, No. 3, pp 230-236, 1985.
[23] Acharya R., Kannathal N., Krishnan S., “Comprehensive analysis of cardiac health using heart rate signals,” Physiol. Meas., Vol. 25, No. 5, pp 1139- 1151, 2004.
[24] Acharya R., Kumar A., Bhat P.S., Lim C.M., Iyengar S., Kannathal N., “Classification of cardiac abnormalities using heart rate signals,” Medicine and Biology Engineering Comput., Vol. 42, No. 3, pp 288-293, 2004.
[25] Kantz H., Schreiber T., Nonlinear time series analysis, Cambridge, UK: Cambridge University Press; 1997.
[26] Grassberger P. and Prcaccia I., “Characterization of strange attractors,” Phys. Rev. Lett., Vol. 50, No. 5, pp 346–349, 1983.
[27] Takens F., “Detecting Strange Attractors in Tubrulence,” Lecture Notes in Mathematics 898, Springer-Verlag, Berlin, 1980.
[28] Kurths J., Herzel H., “An Attractor in a solar time Series,” Physical Department, Vol. 25, No. 1-3, pp 165- 172, 1987.
[29] Osaka M., Saito H., Someya T., Hayakawa H., Cohen R.J., “Detection of nonlinearity in temporal patterns of ventricular premature beats,” Computer in Cardiology, pp 349-352, Sep. 1995.
[30] Wolf A., Swift J.B., Swinney H.L., Vastano J.A., “Determining Lyapunov exponents from a time series,” Physica, Vol. 16, pp 285-317, 1985.
[31] Rosenstein M., Collins J. and De Luca C., “A practical method for calculating largest Lyapunov exponents from small data sets,” NeuroMuscular Research Center and Department of Biomedical Engineering, Boston University, November 20, 1992.
[32] Parker T.S. and Chua L.O., Practical numerical algorithms for chaotic systems, New York, NY, Springer-verlag, 1997.
[33] Fusheng Y., Bo H. and Qingyu T., “Approximate entropy and its application in biosignal analysis,” IEEE Nonlinear Biomedical Signal Processing: Dynamic Analysis and Modeling, Vol. II, Chap. 3, pp 72–91, 2001.
[34] Richman J.A. and Moorman J.R., “Physiological timeseries analysis using approximate entropy and sample entropy,” Amer. J Physiol., Vol. 278, pp 2039–2049, 2000.
[35] Lake D.E., Richman J.S., Griffin M.P. and Moorman J.R., “Sample entropy analysis of neonatal heart rate variability,” Amer. J Physiol., Vol. 283, pp 789–797, Sep. 2002.
[36] Brennan M., Palaniswami M. and Kamen P., “Do existing measures of Poincar´e plot geometry reflect nonlinear features of heart rate variability?,” IEEE Transactions Biomedical Engineering, Vol. 48, No. 11, pp 1342–1347, Nov. 2001.
[37] Liu Y.H., Huang H.P., Weng C.H., “Recognition of electromyographic signals using cascaded kernel learning machine,” IEEE/ASME Trans. Mechatron, Vol. 12, No. 3, pp 253-264, 2007.
[38] MIT-BIH Arrhythmia Database, http://www.physionet.org/physiobank/database/mitdb/
[39] Goldberger A. L., Amaral L. A. N., Glass L., Hausdorff J. M., Ivanov P. C., Mark R. G., Mietus J. E., Moody G. B., Peng C.-K., and Stanley H. E., “PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals,” Circulation Vol. 101, No. 23, pp 215-220, 2000.
[40] Haykin S., Neural Networks and learning machines, Third ed., Pearson Prentice Hall, 2009.
)