心臟疾病已成為國人第二大死因，大多數心臟疾病是由心瓣膜的不正常所造成。人的耳朵可經由電子聽診器聽取心音探查心臟疾病的類型，但解釋心音是一個非常特殊的技巧，必須要接受嚴格的訓練才能做正確的心音聽診。由於這個原因，自動心音分析的電腦系統將對醫務人員會有很大的幫助。本文提出了一種完整的心音分析系統涵蓋從分割心臟週期到最後確定心臟疾病的類型。心臟週期的分割與識別是根據短時傅立葉變換(STFT)和支持向量機(SVM)。實驗過程中，心音資料來源是來至德州心臟學會公開的心音資料，並非常有希望達到不錯的辨識率。

The heart disease has become the second cause of death, and most of heart diseases result from heart valve disorders. skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretation of heart sounds is a very special skill which is quite difficult to teach in a structured way. Because of this reason, automatic heart sound analysis in computer systems would be very helpful for medical staff. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. The kernels of heart beat cycle segmentation and recognition are based on autocorrelation, short-time Fourier transform, and support vector machines. The experiments are done with a public heart sound database released by Texas Heart Institute, with very promising recognition rate achieved.

[1]陳保羅，認識心血管疾病-老年人心臟血管保健預防，天佑智訊有限公司，2008。
[2]L. A. Geddes, “Birth of the stethoscope,” IEEE Engineering in Medicine and Biology Magazine, vol. 24, Issue. 1, pp. 84-86, 2005.
[3]蔡秉翔，建立於隨身聽的數位式電子聽診器，國立中央大學電機工程學系碩士論文，2006。
[4]陳偉昕，心音圖壓縮與辨認系統設計，國立台灣師範大學工業教育學系碩士論文，2006。
[5]葉美玲、陳興夏和陳靜修，急性心血管疾病之護理，五南圖書出版股份有限公司，2006。
[6]Joseph S. Alpert, Cardiology for the Primary Care Physician Second Edition, Current Medicine, Inc. , 2001.
[7]B. Karnath, and W. Thornton, “Auscultation of the heart,” Hospital Physician, pp.39–43, 2002.
[8]E. M. Brown, W. Collis, T. Leung and A. P. Salmon, Heart Sounds Made Easy, Elsevier Pte Ltd, 2003.
[9]http://solutions.3m.com/wps/portal/3M/en_US/Littmann/stethoscope/education/tech-auscultation/
[10]http://www.xinhuanet.com/health/index.htm
[11]http://www.texasheart.org/education/cme/explore/events/eventdetail_5469.cfm
[12]Alan V. Oppenheim, Ronald W. Schafer and John R. Buck, Discrete-Time Signal Processing Second Edition, Pearson Prentice Hall, 2005.
[13]Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing Second Edition, Pearson Prentice Hall, 2007.
[14]Z. Jiang, S. Choi, H. Wang, “A new approach on heart murmurs classification with SVM technique,” in Proc. IEEE International Symposium on Information Technology Convergence, 2007, pp. 240– 244.
[15]C. W. Hsu and C. J. Lin, “A comparison of methods for multi-class support vector machines,” Nat. Taiwan Univ. , Taiwan. [Online] Available: http://www.csie.ntu.edu.tw/~cjlin.
[16]C. J. Lin, “A Formal Analysis of Stopping Criteria of Decomposition Methods for Support Vector Machines,” IEEE Trans. Neural Network, vol.13, no.5, pp.1045-1052, Sep. 2002.
[17]C. J. Lin, “On the Convergence of the Decomposition Method for Support Vector Machines,” IEEE Trans. Neural Network, vol.12, no.6, pp. 1288-1298, Nov. 2001.
[18]H Liang, S Lukkarinen, I Hartimo, “Heart Sound Segmentation Algorithm Based on Heart Sound Envelolgram,” IEEE Computers in Cardiology, Vol24, pp. 105-108, 1997.
[19]T. R. Reed, N. E. Reed, and P. Fritzson, “Heart sound analysis for symptom detection and computer-aided diagnosis,” Simulation Modelling Practice and Theory, vol. 12, pp. 129-146, May. 2004.
[20]C. N. Gupta, R. Palaniappan, S. Swaminathan, and S. M. Krishnan, “Neural network classification of homomorphic segmented heart sounds,” Applied Soft Computing Journal, vol. 7, pp. 286-297, Jan. 2007.
[21]Francesco Beritelli and Salvatore Serrano, “Biometric Identification Based on Frequency Analysis of Cardiac Sounds," IEEE Trans. on Information Forensics and Security, vol. 2, no. 3, Sep. 2007.
[22]王小川，語音訊號處理，全華圖書股份有限公司，2007。
[23]Koksoon Phua, Jianfeng Chen, Tran Huy Dat and Louis Shue, “Heart sound as a biometric,” The Journal of the Pattern Recognition Society, vol. 41, pp. 906-919, 2008.
[24]Z. Sysd, D. Leed, D. Curtis, “A framework for analysis of acoustical cardiac signals,” IEEE Trans. on Biomedical Engineering, vol. 54, no. 4, pp. 651-662, Apr. 2007.
[25]S. Chauhan, P. Wang, C. S. Lim, and V. Anantharaman, “A computer-adided MFCC-based HMM system for automatic auscultation,” Computer in Biology and Medicine, vol. 38, pp. 221-233, 2008.
[26]S. M. Debbal and F. Bereksi-Reguig, “Automatic measure of the split in the second cardiac sound by using the wavelet transform technique,” Computer in Biology and Medicine, vol. 37, pp. 269-276, 2007.
[27]X.Y Jing and D. Zhang, “A face and palmprint recognition approach based on discriminant DCT feature extraction,” IEEE Trans. on Systems, Man, and Cybernetics, Part B, Vol.34, No.2, pp.2405-2415, Dec. 2004.
[28]Guy Amit, Noam Gavriely, Nathan Intrator, “Cluster analysis and classification of heart sounds,” Biomedical Signal Processing and Control, no.4, pp.26-36, 2009.
[29]H. Shino, H. Yoshida, H. Mizuta, and K. Yana, “Phonocardiogram classification using time–frequency representation,” in Proc. IEEE Eng. in Med. and Biol. Soc. , vol. 4, 1997, pp. 1636–1637.
[30]J. J. Lee, S. M. Lee, I. Y. Kim, H. K. Min, and S. H. Hong, “Comparison between short time Fourier and wavelet transform for feature extraction of heart sound,” in Proc. IEEE TENCON, vol. 2, 1999, pp. 1547–1550.
[31]S. Choi, “Detection of valvular heart disorders using wavelet packet decomposition and support vector machine,” Expert Systems with Application, vol. 35, no.4, pp. 1679-1687, 2008.
[32]S. Choi, Z. Jiang, “Comparison of envelope extraction algorithms for cardiac sound signal segmentation,” Expert Systems with Application, vol. 34, no.2, pp. 1056-1069, 2008.