نوع مقاله: مقاله کامل پژوهشی

نویسندگان

1 استادیار، گروه مهندسی سیستم و مکاترونیک، دانشکده علوم و فنون نوین، دانشگاه تهران، تهران

2 دانشجوی کارشناسی ارشد، گروه بیوالکتریک، دانشکده مهندسی پزشکی، دانشگاه آزاد تبریز، تبریز

10.22041/ijbme.2017.61639.1206

چکیده

در مقاله حال حاضر، با آنالیز سیگنال­های صوتی قلب به طراحی الگوریتمی ترکیبی پرداخته شده که متشکل از استخراج ویژگی بر اساس تکنیک آشوب، کاهش ابعاد توسط آنالیز اجزای اصلی و دسته بندی خروجی­ها با اتکاء بر شبکه­های عصبی-فازی تطبیقی می­باشد. عدم قطعیت و خطای بالا در تشخیص روزنه بین بطنی از عدیده مشکلات روش­های پیشین است که در این زمینه مطرح بوده و به سبب اهمیت تشخیص خودکار این عارضه قلبی، نیاز است تا طراحی وفقی و به دور از بروز خطا باشد.  انتقال فضای ویژگی­ها با نگاشت آنها توسط الگوریتم آنالیز اجزای اصلی در دو گام، با انتخاب تعداد 18 تا 25 ویژگی از میان حدود 50 ویژگی استخراج شده، ورودی طبقه­بندی پیشنهادی را می­سازد. طبقه بند پیشنهادی، سیستم شبکه عصبی فازی تطبیقی با امکان پیش­بینی بروز بیماری قلبی است که با ورود داده­ها، در تعداد تکرارهای محدود در سطح قابل قبولی خروجی­ها را پیش­بینی می­نماید. داده­ها از پایگاه دادهUmichدانشگاهمیشیگاندریافت شده و شامل نمونه­های از بیماری روزنه بین بطنی است. نسبت تقسیم داده­ها در مرحله یادگیری و آزمایش، 9/0 به 1/0 (ارزیابی متقاطع) است و از شیوه اعتبارسنجی K-fold استفاده شده است. محاسبه معیارهایی چون دقت، حساسیت و نیز عدم قطعیت توسط مفهوم آنتروپی در الگوریتم ترکیبی حاکی از عملکرد مناسب روش پیشنهادی است. 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Adaptive Detection of Defects in the Ventricular Heart Disease: A Model with the Possibility of Automatic Analysis of Audio Signals through the Heart

نویسندگان [English]

  • Alireza Rezaei 1
  • Sara Belbasi 2

1 Assistant Professor, System and Mechatronic Group, Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran

2 M.Sc. Student, Biomedical Engineering, Islamic Azad University, Tabriz, Iran

چکیده [English]

In this paper, a hybrid algorithm has been developed by analyzing the audio signals of the heart, that consists of extracting features based on chaos technique, reducing dimensions and analyzing the main components and classifying outputs by relying on comparative neuro-fuzzy networks. Uncertainty and high error in the diagnosis of inter-ventricular openings are one of the common problems with the previous methods. Due to the importance of the auto-diagnosis of this heart condition, it is necessary to be well-designed and far from error. Transmission of feature spaces to their mapping by the main component analysis algorithm is made by two steps, selecting the number of 18 to 25 attributes among about 50 extracted attributes that these informations are input of the class. The proposed classification classifies the adaptive fuzzy neural network system with the possibility of predicting the incidence of heart disease, which predicts the number of repetitions at the acceptable level of outputs by entering the data. The data are from the Umich database at the University of Michigan and include samples from the ventricular aperture. The ratio of data split in the learning and testing phase is from 0.9 to 0.1 (cross-check), and the K-fold validation method is used. Calculation of criteria such as accuracy, sensitivity and uncertainty by the concept of entropy in a hybrid algorithm suggests the proper performance of the proposed method.

کلیدواژه‌ها [English]

  • Disease between ventricular aperture
  • automatic detection
  • chaos characteristics
  • principal component analysis and adaptive fuzzy neural network system

[1] Garcia, R. U., Aggarwal, S., & Natarajan, G. (2016). Parental perception of functional status and impact on the family of children with congenital heart surgery.Early human development, 96, 45-51.

[2] Mavroudis, C. (2015). Ventricular septal defect.In Atlas of Pediatric Cardiac Surgery (pp. 99-115).Springer London.

[3] Li, D., Ji, L., Liu, L., Liu, Y., Hou, H., Yu, K., & Zhao, Z. (2014). Characterization of circulating microRNA expression in patients with a ventricular septal defect.PloS one, 9(8), e106318.

[4] American Heart Association Statistical Fact Sheet, International Cardiovascular Disease Statistics, Update 2012, Available from: http://www.heart.org/downloadable/heart/1236204012112INTL.pdf.

[5] World Health Organization Fact sheet N˚317, Cardiovascular diseases, Updated September 2012, Available from: http://www.who.int/mediacentre/factsheets/fs317/en/print.html.

[6] Javed, F., Venkatachalam, P. A., & MH, A. F. (2006). A signal processing module for the analysis of heart sounds and heart murmurs. In Journal of Physics: Conference Series (Vol. 34, No. 1, p. 1098). IOP Publishing.

[7] Penny, D. J., & Vick, G. W. (2011). Ventricular septal defect. The Lancet, 377(9771), 1103-1112.

[8] Rudolph, A. M. (2009). Ventricular septal defect. Congenital Diseases of the Heart: Clinical-Physiological Considerations, Third Edition, 148-178.

[9] Wang, P., Kim, Y., Ling, L. H., &Soh, C. B. (2006, January). First heart sound detection for phonocardiogram segmentation.In 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference (pp. 5519-5522).IEEE.

[10] Chebil, J., & Al-Nabulsi, J. (2007). Classification of heart sound signals using discrete wavelet analysis. International Journal of Soft Computing, 2(1), 37-41.

[11] Liang, H., &Nartimo, I. (1998, October). A feature extraction algorithm based on wavelet packet decomposition for heart sound signals. In Time-Frequency and Time-Scale Analysis, 1998. Proceedings of the IEEE-SP International Symposium on (pp. 93-96). IEEE.

[12] Chung, Y. J. (2007, June). Classification of continuous heart sound signals using the ergodic hidden Markov model.In Iberian Conference on Pattern Recognition and Image Analysis (pp. 563-570).Springer Berlin Heidelberg. Chicago.

[13] Maglogiannis, I., Loukis, E., Zafiropoulos, E., & Stasis, A. (2009). Support vectors machine-based identification of heart valve diseases using heart sounds. Computer methods and programs in biomedicine, 95(1), 47-61.

[14] Dokur, Z., &Ölmez, T. (2009). Feature determination for heart sounds based on divergence analysis. Digital Signal Processing, 19(3), 521-531.

[15] Yan, Z., Jiang, Z., Miyamoto, A., & Wei, Y. (2010). The moment segmentation analysis of heart sound pattern.Computer methods and programs in biomedicine, 98(2), 140-150.

[16] Amit, G., Gavriely, N., &Intrator, N. (2009). Cluster analysis and classification of heart sounds. Biomedical Signal Processing and Control, 4(1), 26-36.

[17] Naseri, H., &Homaeinezhad, M. R. (2013). Detection and boundary identification of phonocardiogram sounds using an expert frequency-energy based metric. Annals of biomedical engineering, 41(2), 279-292.

[18] Wang, Y., Li, W., Zhou, J., Li, X., & Pu, Y. (2014). Identification of the normal and abnormal heart sounds using wavelet-time entropy features based on OMS-WPD. Future Generation Computer Systems, 37, 488-495.

[19] Elgendi, M., Bobhate, P., Jain, S., Guo, L., Rutledge, J., Coe, Y., ...&Adatia, I. (2014). Spectral analysis of the heart sounds in children with and without pulmonary artery hypertension. International journal of cardiology, 173(1), 92-99.

[20] Hassani, K., Bajelani, K., Navidbakhsh, M., & Doyle, J. (2014). Detection and identification of S1 and S2 heart sounds using wavelet decomposition and reconstruction.In XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013 (pp. 509-514).Springer International Publishing. Chicago.

[21] Golpaygani, A. T., Abolpour, N., Hassani, K., Bajelani, K., & Doyle, D. J. (2015). Detection and identification of S1 and S2 heart sounds using wavelet decomposition method.International Journal of Biomathematics, 8(06), 1550078.

[22] Shamsi, H., &Ozbek, I. Y. (2015). A robust method for online heart sound localization in respiratory sound based on temporal fuzzy c-means.Medical & biological engineering & computing, 53(1), 45-56.

[23] Reed, T. R., Reed, N. E., &Fritzson, P. (2004). Heart sound analysis for symptom detection and computer-aided diagnosis.Simulation Modelling Practice and Theory, 12(2), 129-146.

[24] Noponen, A. L., Lukkarinen, S., Angerla, A., &Sepponen, R. (2007). Phono-spectrographic analysis of heart murmur in children.BMC pediatrics, 7(1), 1.

[25] Akbari, M. A., Hassani, K., Doyle, J. D., Navidbakhsh, M., Sangargir, M., Bajelani, K., & Ahmadi, Z. S. (2011). Digital Subtraction Phonocardiography (DSP) applied to the detection and characterization of heart murmurs. Biomedical engineering online, 10(1), 1.

[26] Frank, J. E., &Jacobe, K. M. (2011). Evaluation and management of heart murmurs in children.American family physician, 84(7), 793.

 [27] Patidar, S., Pachori, R. B., & Garg, N. (2015). Automatic diagnosis of septal defects based on tunable-Q wavelet transform of cardiac sound signals. Expert Systems with Applications, 42(7), 3315-3326.

[28] Ezeiza, A., de Ipiña, K. L., Hernández, C., & Barroso, N. (2013). Enhancing the feature extraction process for automatic speech recognition with fractal dimensions. Cognitive Computation, 5(4), 545-550.

[29] Xu, J., Durand, L., &Pibarot, P. (2000). Nonlinear transient chirp signal modeling of the aortic and pulmonary components of the second heart sound. IEEE Transactions on Biomedical Engineering, 47(10), 1328-1335.

[30] Choi, S., & Jiang, Z. (2010). Cardiac sound murmurs classification with autoregressive spectral analysis and multi-support vector machine technique. Computers in biology and medicine, 40(1), 8-20.

[31]Yan Z, Jiang Z, Miyamoto A, Wei Y. The moment segmentation analysis of heart sound pattern. Computer methods and programs in biomedicine. 2010;98(2):140-50.

[32] Amit G, Gavriely N, Intrator N. Cluster analysis and classification of heart sounds. Biomedical Signal Processing and Control. 2009;4(1):26-36.