基于舒张期心音信号分析与特征提取的冠心病无损诊断研究
|
摘要
冠心病是世界上严重危害人们身体健康的最重要的疾病之一。近10年来，随着生活水平的提高和平均寿命的延长，我国冠心病发病率正在逐年上升，而且还有年轻化的趋势。冠心病的危害具有严重性、广泛性、和复杂性，这给冠心病的诊断和治疗提出更高的要求，关键在于及时诊断、及时治疗。因此，积极广泛开展冠心病无损检测的研究并为大众提供方便可行的检测手段是十分急需的。心音信号是人体重要的生理信号之一，蕴含了人体心脏和血管中丰富的原始生理、病理信息，临床上的应用潜力很大。传统心音学与现代信号处理技术相结合，可能会给冠心病无损诊断技术带来突破性的进展。本文正是针对此展开的。
本文主要研究了基于舒张期心音分析及特征提取的冠心病无损诊断技术。在分析了冠状动脉堵塞与舒张期心音关系的基础上，首先研究了心音信号的预处理(消噪和分段)，对舒张期心音信号进行了定位；其次利用Hilbert Huang Transform(简称HHT)对舒张期心音信号进行分析研究，提取了冠心病病理特征；最后通过适用于小样本机器学习的支持向量机(Support Vector Machine，简称SVM)实现了冠心病的智能无损诊断，获得了较高的诊断率。
本文主要研究内容有：
研究了生物医学信号的去噪问题。建立了小波阈值消噪的广义框架：提出了广义阈值函数以及推导了广义阈值函数的阈值确定公式。推导出小波阈值消噪的偏差、方差以及风险与小波系数和阈值的关系式，从理论上研究了阈值函数及阈值的选择对消噪性能的影响。通过对不同特性的模拟信号的处理，得到了最优的小波阈值消噪方案。用此消噪方案对心音信号及心电信号进行了处理，取得了较好的效果。
在分析了目前存在的心音分段算法优缺点的基础上，提出了一种新的心音自动分段算法，给出了分段算法步骤及策略。考虑到心音信号的多样性及复杂性，用大量临床病例对此算法进行了验证，达到了很高的分段正确率。该算法无需额外信号做参考，正确率高，鲁棒性强。
对HHT进行了系统的研究。回顾了传统的信号分析方法；深入研究了多分
浙江大学博士学位论文
量信号的瞬时频率，从瞬时频率存在的条件出发引申出了内蕴模式函数的概念。
阐述了HHT的原理:IMF、EMD、Hi lbert谱和边界谱等。研究了影响HHT性
能的主要因素，并提出了相应的改善措施，采取的这些措施对HHT方法在舒张
期心音分析中的实际应用具有重要意义。最后用各种不同性质的信号表征了
HHT分析方法的优越时频分析性能。
将HHT引入心音信号的研究，建立了基于HHT的冠心病舒张期心音信号
分析及特征提取方法。设计了自适应增强器，提高舒张期心音信号信噪比。探讨
了舒张期心音信号的平稳性。利用HHT方法分析了冠心病病人以及非冠心病人
的舒张期心音的瞬时频率以及谱分布特性。提出了加权瞬时频率的概念，得到了
舒张期心音的瞬时频率变化规律。提出了基于舒张期心音的冠心病特征提取的新
方法，所提取的特征有效的揭示了冠状动脉堵塞的信息，刻画了冠状动脉阻塞时
舒张期心音的变化。表明HHT方法能有效的提取舒张期心音信号中隐含的关于
冠状动脉堵塞相关的病理信息，这对于冠心病的诊断有着重要的意义。
提出了基于支持向量机的冠心病诊断方法。介绍了统计学习理论以及SVM
的原理，构建了SVM分类器，将其应用于冠心病临床诊断，在有限的病例样本
情况下获得了很高的诊断率。同时与传统神经网络方法的诊断性能做了比较，结
果表明，基于支持向量机的冠心病诊断方法具有更高的诊断率和较好的推广性。
经过临床实践证明，本文所提出的基于舒张期心音F旧T分析、病理特征提
取和SVM模式识别的冠心病无损诊断方法取得了较高的诊断率，为冠心病的及
时治疗奠定了良好的基础。
Coronary Artery Disease (CAD) is one of the leading causes of death in the world. In recent 10 years, with the raising of life quantity and the extending of the average longevity, Morbidity for CAD is gradually increasing with the trend of patients being young. CAD is harmful with the characteristic of Severity popularity. and complexity. Seasonable diagnosis and cure are important. Developing the study of the noninvasive detection of CAD is essential. Detection of CAD is a most important medical research area. Heart sound is one of the most physiological signals of body. It provides a lot of valuable diagnostic and prognostic information concerning the heart and hemodynamics. It had important potentiality in clinical practice. Combination the traditional phonocrdiogrm (PCG) with the modern signal processing may bring the breakthrough in the noninvasive detection of CAD.
This paper mainly concerns the diagnosis of CAD automatically based on the analysis and features extraction of diastolic murmurs. On the basis of analyzing the relation between the coronary artery block and the diastolic murmurs, firstly this paper studied the preprocessing of PCG (denoising and segmentation), the diastolic periods were positioned; secondly the diastolic murmurs was analyzed by use of HHT, The features of CAD were acquired; In the end, the CAD was diagnosed automatically by use of Support Vector Machine (SVM), which was suitable in the situation of small samples and better diagnosis ratio was acquired.
The main contributions of this thesis are as follows:
The denoising of biomedical signal was studied. The generalized frame of wavelet shrinkage denoising was build. The generalized threshold function was proposed and the threshold value was also studied for the generalized threshold function. Efficient formulas for computing bias, variance and risk of generalized threshold function were derived. On the basis of this, the relation of bias, variance and risk of generalized threshold function with threshold value and wavelet coefficient were compared. These comparisons gave the performances of wavelet shrinkage denoising in finite sample situations. Kinds of signals with different features were considered to illustrate the performances of the different threshold functions and different threshold values. The optimal denoising scheme was achieved. . In end, the method was used to denoise the electrocardiogram signal and phonocardiogram signal, and the better performance was acquired.
On the basis of reviewing the virtues and defects of traditional PCG segmentation algorithms, a novel segmentation algorithm was proposed. The steps and strategies of segmentation were given. The algorithm was tested using a lot of clinic normal and abnormal heart sound data. Whereas the heart sound signals were intricate, the algorithm achieved a high detection rate. The correct detection rate was
very high by the segmentation algorithm and the algorithm was robust without other signal as reference.
HHT method was studied. Traditional signal processing methods were reviewed; the instantaneous frequency of multicomponent signal was further researched. The concept of intrinsic mode function was induced by the existing conditions of instantaneous frequency for multicomponent signal. The principles of HHT were introduced, including IMF, EMD Hilbert spectrum and marginal spectrum. Some factors related the performances of HHT were studied, and the methods were proposed to improve the performance. The methods were very important for the applications of HHT. In the end, some kinds of signals were analyzed by HHT; the result indicated the HHT method had better qualities.
The diastolic murmurs was analyzed by HHT. The methods of analyzing diastolic murmurs and the features obtained by HHT were presented. The adaptive linear enhancer was designed to improve the signal noise ration of diastolic murmurs. The stationarity of diastolic murmurs was analyzed. The instantaneous frequency and Hilbert spectrum and marginal spectrum of diastolic murmurs for CAD
本文主要研究了基于舒张期心音分析及特征提取的冠心病无损诊断技术。在分析了冠状动脉堵塞与舒张期心音关系的基础上，首先研究了心音信号的预处理(消噪和分段)，对舒张期心音信号进行了定位；其次利用Hilbert Huang Transform(简称HHT)对舒张期心音信号进行分析研究，提取了冠心病病理特征；最后通过适用于小样本机器学习的支持向量机(Support Vector Machine，简称SVM)实现了冠心病的智能无损诊断，获得了较高的诊断率。
本文主要研究内容有：
研究了生物医学信号的去噪问题。建立了小波阈值消噪的广义框架：提出了广义阈值函数以及推导了广义阈值函数的阈值确定公式。推导出小波阈值消噪的偏差、方差以及风险与小波系数和阈值的关系式，从理论上研究了阈值函数及阈值的选择对消噪性能的影响。通过对不同特性的模拟信号的处理，得到了最优的小波阈值消噪方案。用此消噪方案对心音信号及心电信号进行了处理，取得了较好的效果。
在分析了目前存在的心音分段算法优缺点的基础上，提出了一种新的心音自动分段算法，给出了分段算法步骤及策略。考虑到心音信号的多样性及复杂性，用大量临床病例对此算法进行了验证，达到了很高的分段正确率。该算法无需额外信号做参考，正确率高，鲁棒性强。
对HHT进行了系统的研究。回顾了传统的信号分析方法；深入研究了多分
浙江大学博士学位论文
量信号的瞬时频率，从瞬时频率存在的条件出发引申出了内蕴模式函数的概念。
阐述了HHT的原理:IMF、EMD、Hi lbert谱和边界谱等。研究了影响HHT性
能的主要因素，并提出了相应的改善措施，采取的这些措施对HHT方法在舒张
期心音分析中的实际应用具有重要意义。最后用各种不同性质的信号表征了
HHT分析方法的优越时频分析性能。
将HHT引入心音信号的研究，建立了基于HHT的冠心病舒张期心音信号
分析及特征提取方法。设计了自适应增强器，提高舒张期心音信号信噪比。探讨
了舒张期心音信号的平稳性。利用HHT方法分析了冠心病病人以及非冠心病人
的舒张期心音的瞬时频率以及谱分布特性。提出了加权瞬时频率的概念，得到了
舒张期心音的瞬时频率变化规律。提出了基于舒张期心音的冠心病特征提取的新
方法，所提取的特征有效的揭示了冠状动脉堵塞的信息，刻画了冠状动脉阻塞时
舒张期心音的变化。表明HHT方法能有效的提取舒张期心音信号中隐含的关于
冠状动脉堵塞相关的病理信息，这对于冠心病的诊断有着重要的意义。
提出了基于支持向量机的冠心病诊断方法。介绍了统计学习理论以及SVM
的原理，构建了SVM分类器，将其应用于冠心病临床诊断，在有限的病例样本
情况下获得了很高的诊断率。同时与传统神经网络方法的诊断性能做了比较，结
果表明，基于支持向量机的冠心病诊断方法具有更高的诊断率和较好的推广性。
经过临床实践证明，本文所提出的基于舒张期心音F旧T分析、病理特征提
取和SVM模式识别的冠心病无损诊断方法取得了较高的诊断率，为冠心病的及
时治疗奠定了良好的基础。
Coronary Artery Disease (CAD) is one of the leading causes of death in the world. In recent 10 years, with the raising of life quantity and the extending of the average longevity, Morbidity for CAD is gradually increasing with the trend of patients being young. CAD is harmful with the characteristic of Severity popularity. and complexity. Seasonable diagnosis and cure are important. Developing the study of the noninvasive detection of CAD is essential. Detection of CAD is a most important medical research area. Heart sound is one of the most physiological signals of body. It provides a lot of valuable diagnostic and prognostic information concerning the heart and hemodynamics. It had important potentiality in clinical practice. Combination the traditional phonocrdiogrm (PCG) with the modern signal processing may bring the breakthrough in the noninvasive detection of CAD.
This paper mainly concerns the diagnosis of CAD automatically based on the analysis and features extraction of diastolic murmurs. On the basis of analyzing the relation between the coronary artery block and the diastolic murmurs, firstly this paper studied the preprocessing of PCG (denoising and segmentation), the diastolic periods were positioned; secondly the diastolic murmurs was analyzed by use of HHT, The features of CAD were acquired; In the end, the CAD was diagnosed automatically by use of Support Vector Machine (SVM), which was suitable in the situation of small samples and better diagnosis ratio was acquired.
The main contributions of this thesis are as follows:
The denoising of biomedical signal was studied. The generalized frame of wavelet shrinkage denoising was build. The generalized threshold function was proposed and the threshold value was also studied for the generalized threshold function. Efficient formulas for computing bias, variance and risk of generalized threshold function were derived. On the basis of this, the relation of bias, variance and risk of generalized threshold function with threshold value and wavelet coefficient were compared. These comparisons gave the performances of wavelet shrinkage denoising in finite sample situations. Kinds of signals with different features were considered to illustrate the performances of the different threshold functions and different threshold values. The optimal denoising scheme was achieved. . In end, the method was used to denoise the electrocardiogram signal and phonocardiogram signal, and the better performance was acquired.
On the basis of reviewing the virtues and defects of traditional PCG segmentation algorithms, a novel segmentation algorithm was proposed. The steps and strategies of segmentation were given. The algorithm was tested using a lot of clinic normal and abnormal heart sound data. Whereas the heart sound signals were intricate, the algorithm achieved a high detection rate. The correct detection rate was
very high by the segmentation algorithm and the algorithm was robust without other signal as reference.
HHT method was studied. Traditional signal processing methods were reviewed; the instantaneous frequency of multicomponent signal was further researched. The concept of intrinsic mode function was induced by the existing conditions of instantaneous frequency for multicomponent signal. The principles of HHT were introduced, including IMF, EMD Hilbert spectrum and marginal spectrum. Some factors related the performances of HHT were studied, and the methods were proposed to improve the performance. The methods were very important for the applications of HHT. In the end, some kinds of signals were analyzed by HHT; the result indicated the HHT method had better qualities.
The diastolic murmurs was analyzed by HHT. The methods of analyzing diastolic murmurs and the features obtained by HHT were presented. The adaptive linear enhancer was designed to improve the signal noise ration of diastolic murmurs. The stationarity of diastolic murmurs was analyzed. The instantaneous frequency and Hilbert spectrum and marginal spectrum of diastolic murmurs for CAD
引文
[1] 石毓澎，张鸿修主编．冠心病．天津科学技术出版社，1981年6月．
[2] 中国卫生年鉴．人民卫生出版社．
[3] Cestelli, WP. Epidemiology of coronary heart disease:the Framingham study. Am J Med, 1984
[4] 陈在嘉，徐义枢主编．临床冠心病学．人民军医出版社，1994．
[5] 胡旭东，于秀章主编．心脏听诊与心音图．人民卫生出版社，1981．
[6] 徐成斌 编著．心音图学．科学出版社，1982．
[7] 吴延军，徐泾平．心音的产生与传导机制．生物医学工程学杂志，1996，13(3)，280～288．
[8] 王卓琳，刘贞诤，李英杰编著．无创伤心功能检查．黑龙江科学技术出版社，1984．
[9] Willim Dock MD, SmilZonerich. A diastolic murmur arising in a stenosed coronary artery, Vol. 42,April 1967.
[10] Sangster JF, Oakley CM. Diastolic murmur of coronary artery stenosis. Brit. Heart J. 1973, 840-844.
[11] 冯元祯著．生物动力学血液循环．湖南科学技术出版社，1986．
[12] Jin-Zhao,Wang, Bing Tie, et al.Modeling sound genertion in stenosed coronary arteries,IEEE Tranctions on biomedical engineering. Vo137,No 11,1990
[13] Cheng TO. Diastolic murmur caused by coronary artery stenosis, Ann. Int. Med, 1970,72:543-546
[14] John R.Burg, Kathleen A,Weaver et al. Disappearance of coronary artery stenosis murMur alter aortovoronary bypass.CHEST, Vol.63,No.3,1973.
[15] Fredberg. Origin and character of vascular murmur:model studies.J Acoust Soc.Am. Vol.61,No.4, 1977.
[16] Semmlow JL, Welkowitz W.Coronary artery disease-correlates between diastolic auditory characteristic and coronary artery stenoses. IEEE BME, Vol BME-30,No.2,1983.
[17] Akay YM, Akay M, et al. Noninvasive detection of severity of occlusions associated with coronary artery disease. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1991,13:2101～2102.
[18] Akay YM, Akay M, et al. Noninvasive detection of coronary artery disease Using Neural Networks, Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1991,13:1434～1435.
[19] Akay YM, Akay M, et al. A Comparative study of advanced signal processing techniques for
detection of coronary Artery Disease. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1991,13:2139～2140.
[20] Akay YM, Akay M, et al. Time-frequency analysis of the turbulent sounds caused by femoral artery stenosis in dogs using wavelet transform. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE,1992,14: 2590～2591.
[21] Akay YM, Akay M, et al. Neural networks for the diagnosis of coronary artery disease. International Joint Conference on Neural Networks, 1992,2:419～424.
[22] Akay YM, Akay M, et al. Automated noninvasive detection of coronary artery disease using wavelet-based neural networks. Engineering in Medicine and Biology Society, Proceedings of the 16th Annual International Conference of the IEEE,1994,1:A12～A13.
[23] Akay M, Bauer M, et al. Analysis of diastolic heart sounds before and after angioplasty. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1988,1:257～259.
[24] Akay M, Bauer M, et al. Autoregressive modeling of diastolic heart sounds. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1988,1:172～174.
[25] Akay M, Semmlow JL, Parametric modeling of diastolic heart sounds before and after angioplasty. Engineering in Medicine and Biology Society, Images of the Twenty-First Century, Proceedings of the Annual International Conference of the IEEE, 1989,1:51～52.
[26] Akay Metin, Harmonic decomposition of diastolic heart sounds associated with coronary artery disease, Signal Processing, 1995,41(1):79～90.
[27] Akay M, Semmlow JL, et al. Noninvasive detection of coronary stenoses before and after angioplasty using eigenvector methods, IEEE Transactions on Biomedical Engineering,1990,37(11): 1095～1104.
[28] Akay M, Semmlow JL, et al. Detection of coronary occlusions using autoregressive modeling of diastolic heart sounds, IEEE Transactions on Biomedical Engineering,1990,37(4): 366～373.
[29] 聂冠群，齐俊瑞等．心音频谱的诊断价值．中国生物医学工程学报．Vol．14，No．1，1995，66～70．
[30] Fu Jing, Wang Xuemin, Wang Mingshi. Noninvasive acoustic alanalysis system of coronary heart disease. Proceedings of the Fifteenth Southern on Bio. Eng. 1997,239～241.
[31] Haghighi-Mood,Torry JN. Time varying filtering of the first and second sounds. 18th IEEE EMBS Conference, 1996,950～951.
[32] Tianti, Bouzerdoum. Modified adaptive line enhancement filter and application to heart sound noise cancellation. ISSPA96, Vol.2, 815～818.
[33] Messer S, Abbott D, Agzarian J. Optimal wavelet denoising for smart biomonitor systems. Proceedings of SPIE: Smart Electronics and MEMS 2000, 66～78.
[34] Messer, Sheila R, Agzarian John, Abbott, Derek. Optimal wavelet denoising for phonocardiogram. Microelectronics Journal ,Vol.32, Issue: 12, 2001, 931～941.
[35] 元秀华，谢定，吴承德．心音信号测量中的噪音干扰分析与滤除方法．中国现代医学杂志，Vol．9，No．6，1999，65～66．
[36] Lehner RJ, Rangayyan RM. A three-channel microcomputer system for segmentation and characterization of the phonocardiogram. IEEE Trans. Biomedical Eng, Vol. BME-34, 1987, 485～489.
[37] Iwata A, et al. Algorithm for detecting the first and the second heart sounds by spectral tracking. Met. Biol. Eng. And comput, 1980,18:19～26.
[38] Sara H, Durand LC. Automatic detection of cardiac cycle based on an adaptive time-frequency analysis of the phonocardiogram. 19th Annual International Conference of the IEEE-EMBS, Vol .3, 1997,1316～1319.
[39] Liang Huiying, Sakari L, Iifo H, A heart sound segmentation algorithm using wavelet decomposition and reconstruction. The 19th Annual International Conference of the IEEE -EMBS, Vol. 4, 1997,1630～1633.
[40] Sava H, Durand LG. Automatic detection of cardiac cycle based on an adaptive time frequency analysis of the phonocardiogram, Engineering in Medicine and Biology Society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1316～1319.
[41] Durand LG, Pibarot P. Digital signal processing of the phonocardiogram: review of the most recent advancements. Critical Reviews in Biomedical Engineering, 1995, 163～219.
[42] Nandagopal, Bogner, Mazumdar. Spectral analysis of second heart sound using linear prediction coding. Proceedings of second international conference on mechanics in medicine and biology, 1980, 102～103.
[43] Nandagopal, Mazumdar. A study of temporal variation in heart sound frequency spectra using fast fourier transform.. Australasian physical and engineering sciences in medicine, 1981,4(2).47～50.
[44] Nandagopal, Bogner, Mazumdar. Spectral analysis of second heart sound in normal children by selective linear prediction coding. Medical and biological engineering and computing. 1984,22:229～239.
[45] Durand LG, Guo z, Sabban HN. Comparison of spectral techniques for computer-assisted
classification of spectra of heart sounds in patients with porcine bioprosthetie valves. Med Biomed Eng Comput, 1993,31(3):229～236.
[46] 吴延军，徐泾平等．心音信号处理与识别冲国医疗器械杂志，1996，20(5)：292～298．
[47] 王海滨，陈欣根．心音信号的特征矢量辨识分析．第四军医大学学报，1993，14(3)：186～188．
[48] 沈民奋，沈凤麟．心音信号的非高斯AR模型双谱分析．中国生物医学工程学报，2000，19(1)，72～77．
[49] Akay M, Semmlow JL, et al. Noninvasive detection of coronary stenoses before and after angioplasty using eigenvector methods.IEEE Transactions on Biomedical Engineering,1990,37(11): 1095～1104.
[50] Minfen Shen, Lisha Sun. The analysis and classification of phonocardiogram based on high-order spectra. Proceedings of the IEEE Signal Processing Workshop on higher order statistics, 1997:29～33.
[51] Burhan Ergen, Yetkin Tatar. The analysis of heart sounds based on linear and high order statistical methods. Proceeding of the 23rd Annual IEEE-EMBS,2001,2139～2140.
[52] Jamous, Durand LC, et al. Optimal time window duration for computing time-frequency representations of normal phonocardiogram in dogs. Vol30, 1992,503～507.
[53] Wood JC, Barry DT. Time-frequency analysis of the first heart sound. IEEE Eng.in Med. and Bio.. 1995.
[54] Ahmd Zuri. The general interference characteristics of the wigner-ville distribution and its effect on the time frequency representation of a signal ICEMSP, 1999.
[55] Bentley PM. Classification of native heart valve sounds using the choi-williams time-frequency distribution. CD-ROM, Proc 17th IEEE-EMBS, 1995,125～128.
[56] Chen D, Durand LG. Time frequency analysis of the heart sound. Medical &biological& Computing, 1997,306～310.
[57] Chen D, Durand LG. Estimation of pulmonary artery pressure by spectral analysis of the second heart sound .The American Journal of Cardiology, Vol.78, Issue7, 1996, 785～789.
[58] Djebbari A, Bereksi Reguig, Short-time Fourier transform analysis of the phonocardiogram signal. The 7th IEEE International Conference on Electronics, Circuits and Systems, 2000,2:844～847.
[59] Bentley PM, Mcdonnel. Analysis of heart sounds using the wavelet transform. Proe 16th IEEE-EMBS, 1994,1282～1283.
[60] Khadr L, Matalgah M, et al. The wavelet transform and its applications to phonocardiogram signal analysis. Medical informatics,Vol. 16, No.3,1991,221～227.
[61] Jandre FC, Souza MN. Wavelet analysis of phonocardiograms: differences between normal and abnormal heart sounds. Engineering in Medicine and Biology Society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1642～1644.
[62] El-Asir B, Khadra L, et al. Multiresolution analysis of heart sounds, Proceedings of the third IEEE International Conference on Electronics, Circuits, and Systems 1996,2:1084-1087.
[63] Xu Shilin, Hu Min, Zhang Diancheng. The time-frequency representation of PCG. Proceedings of the IEEE International Conference on Industrial Technology, 1994,679～681.
[64] Shino H, Yoshida, et al. Phonocardiogram classification using time-frequency representation. Engineering in Medicine and Biology society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1636～1637.
[65] Jung Jun Lee, Sang Min Lee, et al. Comparison between short time Fourier and wavelet transform for feature extraction of heart sound. TENCON 99. Proceedings of the IEEE Region 10 Conference, 1999,2:1547～1550.
[66] Tinati MA, Bouzerdoum A. Time-frequency analysis of heart sounds before and after angio-Plasty. 13th International Conference on Digital Signal Processing Proceedings, 1997. 75～78.
[67] Yoshida H, Shino H. Instantaneous frequency analysis of systolic murmur for phonocardiogram. Engineering in Medicine and Biology society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1645～1647.
[68] Shino H., Yoshida, et al. Detection and elassification of systolic murmur for phonocardiogram screening, Engineering in Medicine and Biology Society, Bridging Disciplines for Biomedicine. Proceedings of the 18th Annual International Conference of the IEEE, 1996, 1:123～124.
[69] White PR, Colllis WB, Salmon AP. Analyzing the heart murmurs using time-frequency methods. Proceeding of IEEE-SP international symposium, 1996,385～388.
[70] Xuan Zhang, Durand LG et al. Application of the matching pursuit method for the analysis and synthesis of the phonocardiogram, Engineering in Medicine and Biology Society, Proceedings of the 18th Annual International Conference of the IEEE. 1996,3:1035～1036.
[71] Durand LG, Xuan Zhang et al. Application of the matching pursuit method for the time-scale transformation of the phonocardiogram. Engineering in Medicine and Biology Society, Proceedings of the 18th Annual International Conference of the IEEE, 1996,3:1033～1034.
[72] 郑玲，宋长宏．采用模糊函数消除维格纳分布的交叉项其在心音信号分析中的应用．航天医学与医学工程，1995，8(1)，15～22．
[73] 吴延军，徐泾平，程敬之．三种时频表示方法在心音信号分析中的研究应用冲国医疗器械
杂志，1996，20(1)，11～17．
[74] 王衍文，王海滨，程敬之．心音信号分析的新方法—联合时频分析．国外医学：生物医学工程分册，1997，20(2)，80～85．
[75] 王衍文，王海滨，程敬之．心音信号的时频分析．生物医学工程学杂志1998．01期．
[76] 高小榕，陈奎孕．基于模糊函数的人工神经元网络在心音分类中的应用，航天医学与医学工程，1997，10(5)，353～357．
[77] 王衍文，王海滨，程敬之．基于广义指数分布的心音信号时频特性分析．数据采集与处理，1998，13(2)，191～195．
[78] 李桥，朱兴雷等．应用小波变换进行心音三维时频分析的研究．中国医学物理学杂志，2001，18(2)．110～112．
[79] 李勇，高小榕，郭爱雯．基于连续小波变化的心音信号时频分析．清华大学学报，2001，41(3)：77～80．
[80] Jiro Sudoh, et al. Detection and classification of systolic murmur using a neural network. Bio.Eng. Conference on Fifteenth Southern 1996,365～366.
[81] Leung TS, White PR, et al. Classification of heart sounds using time-frequency method and artificial neural networks. Engineering in Medicine and Biology Society, Proceedings of the 22nd Annual International Conference of the IEEE, 2002,2:988～991.
[82] Turkoglu I, Arslan A. An intelligent pattern recognition system based on neural network and wavelet decomposition for interpretation of heart sounds. Engineering in Medicine and Biology Society, Proceedings of the 23rd Annual International Conference of the IEEE, 2001,2:1547～1550.
[83] Olmez, Dokur. Classification of heart sounds using an artificial neural network. Pattern Recognition Letters, Vol.24, Issue: 1-3, 2003, 617～629.
[84] Jain R, Mazumdar J, Moran W. A comparative study of artificial intelligent techniques in the detection of coronary artery disease. Electronic Technology Directions to the Year 2000, 1995,113～120.
[85] Groselj C, Kukar M, et al. Machine learning improves the accuracy of coronary artery disease diagnostic methods. Computers in Cardiology, 1997,57～60.
[86] 王欣等著．离散信号的滤波．电子工业出版社，2002．
[87] Donoho DL, Johnstone IM, Kerkacharian G Wavelet shrinkage: Asymptopia? Joy.Statist. Soe.Ser.B.,1995,301～369.
[88] 崔锦泰著，陈正兴译．小波分析导论．西安交通大学出版社，1995．
[89] 陈逢时著．子波变换理论极其在信号处理中的应用．国防工业出版社，1998．
[90] 赵松年，熊小芸．子波变换与子波分析．电子工业出版社，1996．
[91] 杨福生著．小波变换工程分析与应用．科学出版社，1999．
[92] Daubechies I. Ten lectures on wavelet. Society for Industrial and Applied Mathematics SIAM,1992.
[93] Mallat, S. A theory for multiresolution signal decomposition:the wavelet representation. IEEE Trans.on PAMI, 1989,Vol. 11, No.7:674～693.
[94] Mallat.S 著，杨力华，戴道清等译．信号处理的小波导引．机械工业出版社，2002．
[95] Donoho DL, Johnstone. Ideal spatial adaptation by wavelet shrinkage. Biometrika,1994, 81(3),425～455.
[96] Donoho DL. De-noising by soft-thresholding. IEEE Trans.Inform Theory, 1995,vol. 41, no .3, 612～627.
[97] Donoho DL, Johnstone. Adapting to unknown smoothness via wavelet shrinkage, Journal of the American Statistical Association, 1995,90, 1200～1224.
[98] Gao HY, Bruce AG. WaveShrink with Semisoft Shrinkage. Tech. Rep.39, StatSci Division of MathSoft, Inc. 1995.
[99] Gao HY, Bruce AG. WaveShrink:shrinkage functions and thresholds. SPIE, 1995,2569: 270-281.
[100] Gao HY, Bruce AG. Understanding waveshrink: variance and bias estimation. Biometrika, 1996,83(4),727～745.
[101] Breiman L. Better subset regression using the nonnegative garrote. Technormetrics,37, 1995,373～384.
[102] Gao HY. Wavelet shrinkage denoising using the non negative garrote. J. Comput. Graph. Statist. 1998, 7, 469～488.
[103] Marron JS, Adak S. Exact risk analysis of wavelet regression. J. Comput. Graph. Statist. 1998,7,278～309.
[104] Jansen M. Asymptotic behavior of the minimum mean squared error threshold for noisy wavelet coefficients of piecewise smooth signals. IEEE Trans. on Signal Proc, 2001, 49(6), 1113～1118.
[105] Stein C. Estimation of the mean of a multivariate normal distribution Annuals of statics, 1981,Vol.9, No.6,1135～1151.
[106] Nason.GP.. Wavelet shrinkage using cross-validatiun. J. R. Statist. Soc. B, 1996,58: 463～479.
[107] Jansen M. Noise reduction by wavelet thresholding. Springer Verlag, Lecture notes in Statistics, 2001.
[108] Gabor. Theory of Communication. IEE,Vol.93, 1946,429～457.
[109] Huang,N.E.,et al.The empirical mode composition and the Hilbert spectrum for nonlinear and non-stationary time series analysis.Proc R.Soc.Lond.A, Vol .454,1998,903～995.
[110] Huang,N.E.,et al. A new view of nonlinear water waves: the Hilbert spectrum. Annu.Rev.Fluid Mech, 1999.31:417～457.
[111] 张贤达 编著．现代信号处理．清华大学出版社，1995．
[112] 科恩著，白居宪译．时频分析：理论与应用．西安交通大学出版社，1998．
[113] 丁玉美等编著．数字信号处理．西安电子科技大学出版社，2002．
[114] Mallat, S, Zhang Z. Matching pursuits with time—frequency dictionaries. IEEE Transactions on Signal Processing, 1993, 3397～3415.
[115] Phillips SC, Gledhill RJ. Application of the Hilbert-Huang Transform to the Analysis of Molecular Dynamics. Simulations.Journal of Physical Chemistry A, American Chemical Society, 2003.10.
[116] Huang W, Shen Z et al. Engineering Analysis of Intrinsic Mode and Indicial Response in Biology: the Transient Response of Pulmonary Blood Pressure to Step Hypoxia and Step Recovery. Proceedings of the National Academy of Science, USA 95, 1998,12766～12771.
[117] Huang W, Shen Z et al. Nonlinear Indicial Response of Complex Nonstationary Oscillations as Pulmonary Hypertension Responding to Step Hypoxia. Proceedings of the National Academy of Sciences,USA 96,1999, 1834～1839.
[118] Gloerson, Norden E. Huang. Comparison of Interannual Intrinsic Modes in Hemispheric Sea Ice Covers and Other Geophysical Parameters. IEEE Transactions on Geoscience and Remote Sensing, 41, 2003,1～14.
[119] Chin-Hsiung Loh, Tsu-Chiu Wu, Norden E. Huang. Application of EMD-HHT Method to Identify Near-Fault Ground Motion Characteristics and Structural Responses. Bulletin of the Seismological Society of America, 2001, 91, 1339～1357.
[120] Norden E. Huang, Shen Z, Long SR, Huang MJ. A new method for nonlinear and nonstationary time seres analysis Stochastic Structural Analysis. Ed. B. F. Spencer, E. A. Johnson, Balkema, Rotterdam, 1999,559～564.
[121] Norden E. Huang, Chem CC,et al. Spectral Anysis of the Chi-Chi Earthquake Data: Station TUC129, Taiwan, September 21. Bulletin of the Seismological Society of America, 91, 2001,1310～1338.
[122] Boashash. Estimating and Interpreting the Instantaneous Frequency- Part 1: Fundamentals.. Proceedings of the IEEE, vol. 80(4), IEEE, 1992, 520～538.
[123] Oliveira, Barroso. Definitions of Instantaneous Frequency under physical constraints.. Journal of The Franklin Institute, Vol. 337, Issue 4, 2000, 303～316.
[124] Loughlin ,PJ, Tacer. Instantaneous frequency and the conditional mean frequency of a signal. Signal Processing, Vol.60, Issue 2, 1997,153～162.
[125] Boashash B. Estimating and interpreting the instantaneous frequency of a signal. Part 2. Algorithms and applications. Proc. IEEE 1992, 539～568.
[126] Oliveira, Barroso. Instantaneous frequency of multicomponent signal. IEEE Signal Processing Letters, Vol.6, lqo.4,1999,81～83.
[127] Loughlin,PJ,Tacer.Comments of the interpretation of instantaneous frequency. IEEE Signal Processing Letters, Vol.4, No.5, 1997,123～125.
[128] Oliveira, Barroso. Instantaneous frequency of mono and multicomponent signals. IEEE time-frequency and time scale analysis symposum, 1998,105～108.
[129] Bedrosian. A product theorem for Hilbert transform. Proc IEEE, Vol.51,1963,686～689.
[130] 盖强，马孝江等．一种消除局域波法中边界效应的新方法．大连理工大学学报，Vol．42，No．1，2002，115～117．
[131] 张郁山，梁建文，胡聿贤．应用自回归模型处理EMD方法中的边界问题．自然科学进展，Vol．13，No，10，2003，1054～1059．
[132] 邓拥军等．EMD方法及Hilbert变换中边界问题的处理．科学通报，Vol．46，No．3，2001，257～263．
[133] 钟佑明，秦树人，汤宝平．一种振动信号新变换法的研究．振动工程学报，Vol．15，No．2，2002，233～238．
[134] 钟佑明，秦树人，汤宝平．Hilbert-Huang变换中的理论研究．振动与冲击，Vol．21，No．4，2002，13～19．
[135] 张海勇．基于局域波法的非平稳随机信号分析中若干问题的研究．大连理工大学博士论文．2001。
[136] 于德介，程军圣，杨宇．Hilbert能量谱及其在齿轮故障诊断中的应用．湖南大学学报(自然科学版)，Vol．30，No．4，2003，47～50．
[137] 吴水才，林家瑞，邓东云．增强心室晚电位信号的自适应．生物医学工程学杂志，Vol．20，No．2，2003，299～302．
[138] 沈福民编著．自适应信号处理．西安电子科技大学出版社，2001．
[139] Widrow B, Steams SD. Adaptive signal processing. Prenticehll, 1985.
[140] 蔡强．基于心音的多类心脏病的诊断．浙江大学硕士学位论文．1999．
[141] 董筠．心音的非线性时间序列分析．浙江大学硕士学位论文．2003．
[142] Vapnik V. Nature of Statistical Learning Theory. John Wiley and Sons,Inc.,New York,1995.
[143] 边肇祺，张学工 编著．模式识别．清华大学出版社，2000．
[144] Burges JC. A Tutorial on Support Vector Machines for Pattern Recognition. Bell
Laboratories, Lucent Technologies. 1997.
[145] Vapnik V. An overview of Statistical Learning Theory. lEEE Transaction on Neural n etworks. Vol. 10, No.5, 1999,988～999.
[146] Chen Dadong et al. Comprison of support vector machine and neural networks for text texture verification. IDIAP-RR, 2002,02～19.
[147] Basu A, Wtters C, Shepherd M. Support vector machines for text categorization. Proceeding of the 36th annual Hawaii intentional conference,2003,103-109.
[148] Osuna ER, et al. Training support vector machines: an application to face detection. Proceeding of CVPR'97,1997.
[149] Samanta B, A1-Balushi KR, AI-Araimi SA. Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection. Engineering Applications of Artificial Intelligence, Vol.16, Issue: 7-8, 2003, 657～665.
[150] stadia AJ, Schlkopf B. A tutorial on support vector regression. Neuro COLT Technical Report NC-TR-98-030, Royal Holloway College, University of London, UK, 1998.
[151] Niranjan M. Support vector machines: a tutorial overview and critical appraisal. IEE Colloquium on Applied Statistical Pattern Recognition, 1999.
[152] 牟廉明．统计学习与支持向量机．内江师范学院院报，Vol．17,No．6，2002，3～7．
[153] 王国胜，钟义信．支持向量机的若干新进展．电子学报，Vol．29，No．10，2001，1397～1400．
[154] Klaus Robert Muller et al. An introduction to kernel based learning algorithm. IEEE Transctions on Neural Networks,Vol. 12,No.2,2001,181～194.
[155] Colin Cmpell. Kernel methods: a survey of current Techniques.Neurocomputing,48,2002, 63～84.
[156] Vapnik V著，张学工译．统计学习的理论本质．清华大学出版社，2000．
[157] Hilke Rosier. A study on the empirical mode decomposition. Master thesis,University of Amsterdam,December,2002.
[158] Simon Hykin著，叶世伟，史忠植译．神经网络原理(第2版)．机械工业出版社，2004．
[159] 闻新、周露、王丹力、熊晓英，MATLAB神经网络应用设计，科学出版社，2001．5．
[2] 中国卫生年鉴．人民卫生出版社．
[3] Cestelli, WP. Epidemiology of coronary heart disease:the Framingham study. Am J Med, 1984
[4] 陈在嘉，徐义枢主编．临床冠心病学．人民军医出版社，1994．
[5] 胡旭东，于秀章主编．心脏听诊与心音图．人民卫生出版社，1981．
[6] 徐成斌 编著．心音图学．科学出版社，1982．
[7] 吴延军，徐泾平．心音的产生与传导机制．生物医学工程学杂志，1996，13(3)，280～288．
[8] 王卓琳，刘贞诤，李英杰编著．无创伤心功能检查．黑龙江科学技术出版社，1984．
[9] Willim Dock MD, SmilZonerich. A diastolic murmur arising in a stenosed coronary artery, Vol. 42,April 1967.
[10] Sangster JF, Oakley CM. Diastolic murmur of coronary artery stenosis. Brit. Heart J. 1973, 840-844.
[11] 冯元祯著．生物动力学血液循环．湖南科学技术出版社，1986．
[12] Jin-Zhao,Wang, Bing Tie, et al.Modeling sound genertion in stenosed coronary arteries,IEEE Tranctions on biomedical engineering. Vo137,No 11,1990
[13] Cheng TO. Diastolic murmur caused by coronary artery stenosis, Ann. Int. Med, 1970,72:543-546
[14] John R.Burg, Kathleen A,Weaver et al. Disappearance of coronary artery stenosis murMur alter aortovoronary bypass.CHEST, Vol.63,No.3,1973.
[15] Fredberg. Origin and character of vascular murmur:model studies.J Acoust Soc.Am. Vol.61,No.4, 1977.
[16] Semmlow JL, Welkowitz W.Coronary artery disease-correlates between diastolic auditory characteristic and coronary artery stenoses. IEEE BME, Vol BME-30,No.2,1983.
[17] Akay YM, Akay M, et al. Noninvasive detection of severity of occlusions associated with coronary artery disease. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1991,13:2101～2102.
[18] Akay YM, Akay M, et al. Noninvasive detection of coronary artery disease Using Neural Networks, Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1991,13:1434～1435.
[19] Akay YM, Akay M, et al. A Comparative study of advanced signal processing techniques for
detection of coronary Artery Disease. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1991,13:2139～2140.
[20] Akay YM, Akay M, et al. Time-frequency analysis of the turbulent sounds caused by femoral artery stenosis in dogs using wavelet transform. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE,1992,14: 2590～2591.
[21] Akay YM, Akay M, et al. Neural networks for the diagnosis of coronary artery disease. International Joint Conference on Neural Networks, 1992,2:419～424.
[22] Akay YM, Akay M, et al. Automated noninvasive detection of coronary artery disease using wavelet-based neural networks. Engineering in Medicine and Biology Society, Proceedings of the 16th Annual International Conference of the IEEE,1994,1:A12～A13.
[23] Akay M, Bauer M, et al. Analysis of diastolic heart sounds before and after angioplasty. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1988,1:257～259.
[24] Akay M, Bauer M, et al. Autoregressive modeling of diastolic heart sounds. Engineering in Medicine and Biology Society, Proceedings of the Annual International Conference of the IEEE, 1988,1:172～174.
[25] Akay M, Semmlow JL, Parametric modeling of diastolic heart sounds before and after angioplasty. Engineering in Medicine and Biology Society, Images of the Twenty-First Century, Proceedings of the Annual International Conference of the IEEE, 1989,1:51～52.
[26] Akay Metin, Harmonic decomposition of diastolic heart sounds associated with coronary artery disease, Signal Processing, 1995,41(1):79～90.
[27] Akay M, Semmlow JL, et al. Noninvasive detection of coronary stenoses before and after angioplasty using eigenvector methods, IEEE Transactions on Biomedical Engineering,1990,37(11): 1095～1104.
[28] Akay M, Semmlow JL, et al. Detection of coronary occlusions using autoregressive modeling of diastolic heart sounds, IEEE Transactions on Biomedical Engineering,1990,37(4): 366～373.
[29] 聂冠群，齐俊瑞等．心音频谱的诊断价值．中国生物医学工程学报．Vol．14，No．1，1995，66～70．
[30] Fu Jing, Wang Xuemin, Wang Mingshi. Noninvasive acoustic alanalysis system of coronary heart disease. Proceedings of the Fifteenth Southern on Bio. Eng. 1997,239～241.
[31] Haghighi-Mood,Torry JN. Time varying filtering of the first and second sounds. 18th IEEE EMBS Conference, 1996,950～951.
[32] Tianti, Bouzerdoum. Modified adaptive line enhancement filter and application to heart sound noise cancellation. ISSPA96, Vol.2, 815～818.
[33] Messer S, Abbott D, Agzarian J. Optimal wavelet denoising for smart biomonitor systems. Proceedings of SPIE: Smart Electronics and MEMS 2000, 66～78.
[34] Messer, Sheila R, Agzarian John, Abbott, Derek. Optimal wavelet denoising for phonocardiogram. Microelectronics Journal ,Vol.32, Issue: 12, 2001, 931～941.
[35] 元秀华，谢定，吴承德．心音信号测量中的噪音干扰分析与滤除方法．中国现代医学杂志，Vol．9，No．6，1999，65～66．
[36] Lehner RJ, Rangayyan RM. A three-channel microcomputer system for segmentation and characterization of the phonocardiogram. IEEE Trans. Biomedical Eng, Vol. BME-34, 1987, 485～489.
[37] Iwata A, et al. Algorithm for detecting the first and the second heart sounds by spectral tracking. Met. Biol. Eng. And comput, 1980,18:19～26.
[38] Sara H, Durand LC. Automatic detection of cardiac cycle based on an adaptive time-frequency analysis of the phonocardiogram. 19th Annual International Conference of the IEEE-EMBS, Vol .3, 1997,1316～1319.
[39] Liang Huiying, Sakari L, Iifo H, A heart sound segmentation algorithm using wavelet decomposition and reconstruction. The 19th Annual International Conference of the IEEE -EMBS, Vol. 4, 1997,1630～1633.
[40] Sava H, Durand LG. Automatic detection of cardiac cycle based on an adaptive time frequency analysis of the phonocardiogram, Engineering in Medicine and Biology Society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1316～1319.
[41] Durand LG, Pibarot P. Digital signal processing of the phonocardiogram: review of the most recent advancements. Critical Reviews in Biomedical Engineering, 1995, 163～219.
[42] Nandagopal, Bogner, Mazumdar. Spectral analysis of second heart sound using linear prediction coding. Proceedings of second international conference on mechanics in medicine and biology, 1980, 102～103.
[43] Nandagopal, Mazumdar. A study of temporal variation in heart sound frequency spectra using fast fourier transform.. Australasian physical and engineering sciences in medicine, 1981,4(2).47～50.
[44] Nandagopal, Bogner, Mazumdar. Spectral analysis of second heart sound in normal children by selective linear prediction coding. Medical and biological engineering and computing. 1984,22:229～239.
[45] Durand LG, Guo z, Sabban HN. Comparison of spectral techniques for computer-assisted
classification of spectra of heart sounds in patients with porcine bioprosthetie valves. Med Biomed Eng Comput, 1993,31(3):229～236.
[46] 吴延军，徐泾平等．心音信号处理与识别冲国医疗器械杂志，1996，20(5)：292～298．
[47] 王海滨，陈欣根．心音信号的特征矢量辨识分析．第四军医大学学报，1993，14(3)：186～188．
[48] 沈民奋，沈凤麟．心音信号的非高斯AR模型双谱分析．中国生物医学工程学报，2000，19(1)，72～77．
[49] Akay M, Semmlow JL, et al. Noninvasive detection of coronary stenoses before and after angioplasty using eigenvector methods.IEEE Transactions on Biomedical Engineering,1990,37(11): 1095～1104.
[50] Minfen Shen, Lisha Sun. The analysis and classification of phonocardiogram based on high-order spectra. Proceedings of the IEEE Signal Processing Workshop on higher order statistics, 1997:29～33.
[51] Burhan Ergen, Yetkin Tatar. The analysis of heart sounds based on linear and high order statistical methods. Proceeding of the 23rd Annual IEEE-EMBS,2001,2139～2140.
[52] Jamous, Durand LC, et al. Optimal time window duration for computing time-frequency representations of normal phonocardiogram in dogs. Vol30, 1992,503～507.
[53] Wood JC, Barry DT. Time-frequency analysis of the first heart sound. IEEE Eng.in Med. and Bio.. 1995.
[54] Ahmd Zuri. The general interference characteristics of the wigner-ville distribution and its effect on the time frequency representation of a signal ICEMSP, 1999.
[55] Bentley PM. Classification of native heart valve sounds using the choi-williams time-frequency distribution. CD-ROM, Proc 17th IEEE-EMBS, 1995,125～128.
[56] Chen D, Durand LG. Time frequency analysis of the heart sound. Medical &biological& Computing, 1997,306～310.
[57] Chen D, Durand LG. Estimation of pulmonary artery pressure by spectral analysis of the second heart sound .The American Journal of Cardiology, Vol.78, Issue7, 1996, 785～789.
[58] Djebbari A, Bereksi Reguig, Short-time Fourier transform analysis of the phonocardiogram signal. The 7th IEEE International Conference on Electronics, Circuits and Systems, 2000,2:844～847.
[59] Bentley PM, Mcdonnel. Analysis of heart sounds using the wavelet transform. Proe 16th IEEE-EMBS, 1994,1282～1283.
[60] Khadr L, Matalgah M, et al. The wavelet transform and its applications to phonocardiogram signal analysis. Medical informatics,Vol. 16, No.3,1991,221～227.
[61] Jandre FC, Souza MN. Wavelet analysis of phonocardiograms: differences between normal and abnormal heart sounds. Engineering in Medicine and Biology Society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1642～1644.
[62] El-Asir B, Khadra L, et al. Multiresolution analysis of heart sounds, Proceedings of the third IEEE International Conference on Electronics, Circuits, and Systems 1996,2:1084-1087.
[63] Xu Shilin, Hu Min, Zhang Diancheng. The time-frequency representation of PCG. Proceedings of the IEEE International Conference on Industrial Technology, 1994,679～681.
[64] Shino H, Yoshida, et al. Phonocardiogram classification using time-frequency representation. Engineering in Medicine and Biology society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1636～1637.
[65] Jung Jun Lee, Sang Min Lee, et al. Comparison between short time Fourier and wavelet transform for feature extraction of heart sound. TENCON 99. Proceedings of the IEEE Region 10 Conference, 1999,2:1547～1550.
[66] Tinati MA, Bouzerdoum A. Time-frequency analysis of heart sounds before and after angio-Plasty. 13th International Conference on Digital Signal Processing Proceedings, 1997. 75～78.
[67] Yoshida H, Shino H. Instantaneous frequency analysis of systolic murmur for phonocardiogram. Engineering in Medicine and Biology society, Proceedings of the 19th Annual International Conference of the IEEE, 1997,4:1645～1647.
[68] Shino H., Yoshida, et al. Detection and elassification of systolic murmur for phonocardiogram screening, Engineering in Medicine and Biology Society, Bridging Disciplines for Biomedicine. Proceedings of the 18th Annual International Conference of the IEEE, 1996, 1:123～124.
[69] White PR, Colllis WB, Salmon AP. Analyzing the heart murmurs using time-frequency methods. Proceeding of IEEE-SP international symposium, 1996,385～388.
[70] Xuan Zhang, Durand LG et al. Application of the matching pursuit method for the analysis and synthesis of the phonocardiogram, Engineering in Medicine and Biology Society, Proceedings of the 18th Annual International Conference of the IEEE. 1996,3:1035～1036.
[71] Durand LG, Xuan Zhang et al. Application of the matching pursuit method for the time-scale transformation of the phonocardiogram. Engineering in Medicine and Biology Society, Proceedings of the 18th Annual International Conference of the IEEE, 1996,3:1033～1034.
[72] 郑玲，宋长宏．采用模糊函数消除维格纳分布的交叉项其在心音信号分析中的应用．航天医学与医学工程，1995，8(1)，15～22．
[73] 吴延军，徐泾平，程敬之．三种时频表示方法在心音信号分析中的研究应用冲国医疗器械
杂志，1996，20(1)，11～17．
[74] 王衍文，王海滨，程敬之．心音信号分析的新方法—联合时频分析．国外医学：生物医学工程分册，1997，20(2)，80～85．
[75] 王衍文，王海滨，程敬之．心音信号的时频分析．生物医学工程学杂志1998．01期．
[76] 高小榕，陈奎孕．基于模糊函数的人工神经元网络在心音分类中的应用，航天医学与医学工程，1997，10(5)，353～357．
[77] 王衍文，王海滨，程敬之．基于广义指数分布的心音信号时频特性分析．数据采集与处理，1998，13(2)，191～195．
[78] 李桥，朱兴雷等．应用小波变换进行心音三维时频分析的研究．中国医学物理学杂志，2001，18(2)．110～112．
[79] 李勇，高小榕，郭爱雯．基于连续小波变化的心音信号时频分析．清华大学学报，2001，41(3)：77～80．
[80] Jiro Sudoh, et al. Detection and classification of systolic murmur using a neural network. Bio.Eng. Conference on Fifteenth Southern 1996,365～366.
[81] Leung TS, White PR, et al. Classification of heart sounds using time-frequency method and artificial neural networks. Engineering in Medicine and Biology Society, Proceedings of the 22nd Annual International Conference of the IEEE, 2002,2:988～991.
[82] Turkoglu I, Arslan A. An intelligent pattern recognition system based on neural network and wavelet decomposition for interpretation of heart sounds. Engineering in Medicine and Biology Society, Proceedings of the 23rd Annual International Conference of the IEEE, 2001,2:1547～1550.
[83] Olmez, Dokur. Classification of heart sounds using an artificial neural network. Pattern Recognition Letters, Vol.24, Issue: 1-3, 2003, 617～629.
[84] Jain R, Mazumdar J, Moran W. A comparative study of artificial intelligent techniques in the detection of coronary artery disease. Electronic Technology Directions to the Year 2000, 1995,113～120.
[85] Groselj C, Kukar M, et al. Machine learning improves the accuracy of coronary artery disease diagnostic methods. Computers in Cardiology, 1997,57～60.
[86] 王欣等著．离散信号的滤波．电子工业出版社，2002．
[87] Donoho DL, Johnstone IM, Kerkacharian G Wavelet shrinkage: Asymptopia? Joy.Statist. Soe.Ser.B.,1995,301～369.
[88] 崔锦泰著，陈正兴译．小波分析导论．西安交通大学出版社，1995．
[89] 陈逢时著．子波变换理论极其在信号处理中的应用．国防工业出版社，1998．
[90] 赵松年，熊小芸．子波变换与子波分析．电子工业出版社，1996．
[91] 杨福生著．小波变换工程分析与应用．科学出版社，1999．
[92] Daubechies I. Ten lectures on wavelet. Society for Industrial and Applied Mathematics SIAM,1992.
[93] Mallat, S. A theory for multiresolution signal decomposition:the wavelet representation. IEEE Trans.on PAMI, 1989,Vol. 11, No.7:674～693.
[94] Mallat.S 著，杨力华，戴道清等译．信号处理的小波导引．机械工业出版社，2002．
[95] Donoho DL, Johnstone. Ideal spatial adaptation by wavelet shrinkage. Biometrika,1994, 81(3),425～455.
[96] Donoho DL. De-noising by soft-thresholding. IEEE Trans.Inform Theory, 1995,vol. 41, no .3, 612～627.
[97] Donoho DL, Johnstone. Adapting to unknown smoothness via wavelet shrinkage, Journal of the American Statistical Association, 1995,90, 1200～1224.
[98] Gao HY, Bruce AG. WaveShrink with Semisoft Shrinkage. Tech. Rep.39, StatSci Division of MathSoft, Inc. 1995.
[99] Gao HY, Bruce AG. WaveShrink:shrinkage functions and thresholds. SPIE, 1995,2569: 270-281.
[100] Gao HY, Bruce AG. Understanding waveshrink: variance and bias estimation. Biometrika, 1996,83(4),727～745.
[101] Breiman L. Better subset regression using the nonnegative garrote. Technormetrics,37, 1995,373～384.
[102] Gao HY. Wavelet shrinkage denoising using the non negative garrote. J. Comput. Graph. Statist. 1998, 7, 469～488.
[103] Marron JS, Adak S. Exact risk analysis of wavelet regression. J. Comput. Graph. Statist. 1998,7,278～309.
[104] Jansen M. Asymptotic behavior of the minimum mean squared error threshold for noisy wavelet coefficients of piecewise smooth signals. IEEE Trans. on Signal Proc, 2001, 49(6), 1113～1118.
[105] Stein C. Estimation of the mean of a multivariate normal distribution Annuals of statics, 1981,Vol.9, No.6,1135～1151.
[106] Nason.GP.. Wavelet shrinkage using cross-validatiun. J. R. Statist. Soc. B, 1996,58: 463～479.
[107] Jansen M. Noise reduction by wavelet thresholding. Springer Verlag, Lecture notes in Statistics, 2001.
[108] Gabor. Theory of Communication. IEE,Vol.93, 1946,429～457.
[109] Huang,N.E.,et al.The empirical mode composition and the Hilbert spectrum for nonlinear and non-stationary time series analysis.Proc R.Soc.Lond.A, Vol .454,1998,903～995.
[110] Huang,N.E.,et al. A new view of nonlinear water waves: the Hilbert spectrum. Annu.Rev.Fluid Mech, 1999.31:417～457.
[111] 张贤达 编著．现代信号处理．清华大学出版社，1995．
[112] 科恩著，白居宪译．时频分析：理论与应用．西安交通大学出版社，1998．
[113] 丁玉美等编著．数字信号处理．西安电子科技大学出版社，2002．
[114] Mallat, S, Zhang Z. Matching pursuits with time—frequency dictionaries. IEEE Transactions on Signal Processing, 1993, 3397～3415.
[115] Phillips SC, Gledhill RJ. Application of the Hilbert-Huang Transform to the Analysis of Molecular Dynamics. Simulations.Journal of Physical Chemistry A, American Chemical Society, 2003.10.
[116] Huang W, Shen Z et al. Engineering Analysis of Intrinsic Mode and Indicial Response in Biology: the Transient Response of Pulmonary Blood Pressure to Step Hypoxia and Step Recovery. Proceedings of the National Academy of Science, USA 95, 1998,12766～12771.
[117] Huang W, Shen Z et al. Nonlinear Indicial Response of Complex Nonstationary Oscillations as Pulmonary Hypertension Responding to Step Hypoxia. Proceedings of the National Academy of Sciences,USA 96,1999, 1834～1839.
[118] Gloerson, Norden E. Huang. Comparison of Interannual Intrinsic Modes in Hemispheric Sea Ice Covers and Other Geophysical Parameters. IEEE Transactions on Geoscience and Remote Sensing, 41, 2003,1～14.
[119] Chin-Hsiung Loh, Tsu-Chiu Wu, Norden E. Huang. Application of EMD-HHT Method to Identify Near-Fault Ground Motion Characteristics and Structural Responses. Bulletin of the Seismological Society of America, 2001, 91, 1339～1357.
[120] Norden E. Huang, Shen Z, Long SR, Huang MJ. A new method for nonlinear and nonstationary time seres analysis Stochastic Structural Analysis. Ed. B. F. Spencer, E. A. Johnson, Balkema, Rotterdam, 1999,559～564.
[121] Norden E. Huang, Chem CC,et al. Spectral Anysis of the Chi-Chi Earthquake Data: Station TUC129, Taiwan, September 21. Bulletin of the Seismological Society of America, 91, 2001,1310～1338.
[122] Boashash. Estimating and Interpreting the Instantaneous Frequency- Part 1: Fundamentals.. Proceedings of the IEEE, vol. 80(4), IEEE, 1992, 520～538.
[123] Oliveira, Barroso. Definitions of Instantaneous Frequency under physical constraints.. Journal of The Franklin Institute, Vol. 337, Issue 4, 2000, 303～316.
[124] Loughlin ,PJ, Tacer. Instantaneous frequency and the conditional mean frequency of a signal. Signal Processing, Vol.60, Issue 2, 1997,153～162.
[125] Boashash B. Estimating and interpreting the instantaneous frequency of a signal. Part 2. Algorithms and applications. Proc. IEEE 1992, 539～568.
[126] Oliveira, Barroso. Instantaneous frequency of multicomponent signal. IEEE Signal Processing Letters, Vol.6, lqo.4,1999,81～83.
[127] Loughlin,PJ,Tacer.Comments of the interpretation of instantaneous frequency. IEEE Signal Processing Letters, Vol.4, No.5, 1997,123～125.
[128] Oliveira, Barroso. Instantaneous frequency of mono and multicomponent signals. IEEE time-frequency and time scale analysis symposum, 1998,105～108.
[129] Bedrosian. A product theorem for Hilbert transform. Proc IEEE, Vol.51,1963,686～689.
[130] 盖强，马孝江等．一种消除局域波法中边界效应的新方法．大连理工大学学报，Vol．42，No．1，2002，115～117．
[131] 张郁山，梁建文，胡聿贤．应用自回归模型处理EMD方法中的边界问题．自然科学进展，Vol．13，No，10，2003，1054～1059．
[132] 邓拥军等．EMD方法及Hilbert变换中边界问题的处理．科学通报，Vol．46，No．3，2001，257～263．
[133] 钟佑明，秦树人，汤宝平．一种振动信号新变换法的研究．振动工程学报，Vol．15，No．2，2002，233～238．
[134] 钟佑明，秦树人，汤宝平．Hilbert-Huang变换中的理论研究．振动与冲击，Vol．21，No．4，2002，13～19．
[135] 张海勇．基于局域波法的非平稳随机信号分析中若干问题的研究．大连理工大学博士论文．2001。
[136] 于德介，程军圣，杨宇．Hilbert能量谱及其在齿轮故障诊断中的应用．湖南大学学报(自然科学版)，Vol．30，No．4，2003，47～50．
[137] 吴水才，林家瑞，邓东云．增强心室晚电位信号的自适应．生物医学工程学杂志，Vol．20，No．2，2003，299～302．
[138] 沈福民编著．自适应信号处理．西安电子科技大学出版社，2001．
[139] Widrow B, Steams SD. Adaptive signal processing. Prenticehll, 1985.
[140] 蔡强．基于心音的多类心脏病的诊断．浙江大学硕士学位论文．1999．
[141] 董筠．心音的非线性时间序列分析．浙江大学硕士学位论文．2003．
[142] Vapnik V. Nature of Statistical Learning Theory. John Wiley and Sons,Inc.,New York,1995.
[143] 边肇祺，张学工 编著．模式识别．清华大学出版社，2000．
[144] Burges JC. A Tutorial on Support Vector Machines for Pattern Recognition. Bell
Laboratories, Lucent Technologies. 1997.
[145] Vapnik V. An overview of Statistical Learning Theory. lEEE Transaction on Neural n etworks. Vol. 10, No.5, 1999,988～999.
[146] Chen Dadong et al. Comprison of support vector machine and neural networks for text texture verification. IDIAP-RR, 2002,02～19.
[147] Basu A, Wtters C, Shepherd M. Support vector machines for text categorization. Proceeding of the 36th annual Hawaii intentional conference,2003,103-109.
[148] Osuna ER, et al. Training support vector machines: an application to face detection. Proceeding of CVPR'97,1997.
[149] Samanta B, A1-Balushi KR, AI-Araimi SA. Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection. Engineering Applications of Artificial Intelligence, Vol.16, Issue: 7-8, 2003, 657～665.
[150] stadia AJ, Schlkopf B. A tutorial on support vector regression. Neuro COLT Technical Report NC-TR-98-030, Royal Holloway College, University of London, UK, 1998.
[151] Niranjan M. Support vector machines: a tutorial overview and critical appraisal. IEE Colloquium on Applied Statistical Pattern Recognition, 1999.
[152] 牟廉明．统计学习与支持向量机．内江师范学院院报，Vol．17,No．6，2002，3～7．
[153] 王国胜，钟义信．支持向量机的若干新进展．电子学报，Vol．29，No．10，2001，1397～1400．
[154] Klaus Robert Muller et al. An introduction to kernel based learning algorithm. IEEE Transctions on Neural Networks,Vol. 12,No.2,2001,181～194.
[155] Colin Cmpell. Kernel methods: a survey of current Techniques.Neurocomputing,48,2002, 63～84.
[156] Vapnik V著，张学工译．统计学习的理论本质．清华大学出版社，2000．
[157] Hilke Rosier. A study on the empirical mode decomposition. Master thesis,University of Amsterdam,December,2002.
[158] Simon Hykin著，叶世伟，史忠植译．神经网络原理(第2版)．机械工业出版社，2004．
[159] 闻新、周露、王丹力、熊晓英，MATLAB神经网络应用设计，科学出版社，2001．5．
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |