脉诊客观化信息处理方法的研究
|
摘要
传统中医诊断的信息来源主要是望、闻、问、切,又称“四诊”。作为切诊的重要内容,对脉搏的诊断是获取病人健康状况信息的一种重要途径。但是传统中医脉诊过于依赖医生的主观评价,缺乏客观的定量标准。脉诊客观化研究正是力图建立起客观的诊断标准来解决这些问题。
本文通过总结前人的经验,结合当前脉诊客观化研究的新进展,以现代中医理论《金氏脉学》为理论依据,使用现代数字信号处理理论对脉诊客观化研究过程中的信息处理技术进行了探讨。
传统脉诊理论以大量诊断经验为基础,缺乏客观判据,对不同脉象进行判断的主观随意性较大,而基于计算机的脉诊研究依赖客观判据,这种矛盾极大地阻碍了脉诊客观化发展的进程。金氏脉学汲取了传统中医脉学整体观和辨证观的理论思想,通过数学手段对疾病基本做到定位、定性、定量诊断,在发展了传统脉学理论的同时与传统脉学理论又有根本的区别,为脉诊的客观化提供了可行性。
在脉搏信号采集方面,综合应用现代检测技术与信号处理理论,依据金氏脉学的分层取脉思想,设计了独特的脉搏自动分层测量系统。为了实现数字信号的自动采集,本系统使用PCI数据采集卡将压力传感器的模拟信号转换成数字信号,然后利用上层处理软件进行脉搏波的处理、分析与显示。
在脉搏波预处理方面,利用本文提出的基于经验模态分解的多带滤波器进行脉搏波的基线消除,并分别与形态滤波(Morphology)、有限冲击响应滤波(FIR)和样条估计这三种方法进行了比较,从仿真数据可以看出该方法取得了较好的滤波效果。
在脉搏信号的特征分析方面,从时域和频域两个方面对脉搏信号进行分析。另外把经验模态分解(EMD)、Hilbert-Huang变换和倒谱分析应用到脉搏波的特征提取中,具有创新性,并取得了初步的成功。
在前面脉象特征提取的基础上,选定9个能表征脉象实质的特征参数构成脉象识别的特征向量,使用基于改进型二叉树的支持向量机方法对7种基本脉象进行了分类识别。并与有向无环图SVM和神经网络方法进行了比较,正确识别率提高了3-6个百分点。
Traditional Chinese Medicine (TCM) diagnosis acquires pathological information through observing, smelling, asking and touching, which are also called "Four Diagnosis". As a major part of touching, pulse diagnosis becomes an important method to find out health status of patients. However, TCM, lack of quantitative standard, excessively relies on doctor's subjective judgment. So, objectivizing of TCM tries to establish diagnosis standard in order to solve these problems.
This paper summarizes from both success and defeat of our predecessors in this field. Based onlse Theory> as TCM principle, it utilizes advanced digital signal processing technique to make further research into information processing technique of Pulse Diagnosis Objectivization.
Mainly according to diagnosing experience, traditional pulse diagnosis is lack of objective standard, inconsistently, computer-based pulse diagnosis device, however, depends on the quantitative principles.lse Theory> provides a good solution for this inconsistency and makes TCM Objectivization possible and feasible. It not only assimilates integral viewpoint of TCM, but also makes quantitative diagnosis by mathematic method. More importantly, lse Theory> develops TCM theory; meanwhile, it makes a radical difference comparing to TCM.
Concerning about pulse signal collection, we apply modern Measurement Technique and signal processing theory, design unique pulse automatic and layered measuring system. In order to collect digital signal in real-time, this system utilizes PCI data collecting card to transform analog signals into digital signals, and then data processing program to carry out signal analysing and displaying.
In the aspect of pulse signal pre-processing, this paper proposes a new EMD (Empirical Module Decomposition) based filter to remove baseline wander. Additionally, we made simulated experiments and evaluated its validity by quantitatively comparing with morphology filter, time variant filter and spline Estimation. The results showed that the proposed algorithm is efficient in removing pulse baseline wander.
In the aspect of pulse characteristics extraction, we not only make comprehensive analysis from time and frequency field, but also creatively apply EMD, Hibert-Huang Transform and Cepstrum Analysis into pulse characteristics extraction. We can find out that these parameters are efficient in the following classification process.
Following the pulse characteristics extraction above, we choose 9 characteristics parameters to construct characteristics vector, and utilize improved Binomial Tree based SVM (Support Vector Machine) to execute classification of 7 typical kinds of pulse. Finally, we compare this algorithm with DAG (Directed Acyclic Graphs) SVM and Neural Network, and we find that right identification rate increases about 3-6 percent.
本文通过总结前人的经验,结合当前脉诊客观化研究的新进展,以现代中医理论《金氏脉学》为理论依据,使用现代数字信号处理理论对脉诊客观化研究过程中的信息处理技术进行了探讨。
传统脉诊理论以大量诊断经验为基础,缺乏客观判据,对不同脉象进行判断的主观随意性较大,而基于计算机的脉诊研究依赖客观判据,这种矛盾极大地阻碍了脉诊客观化发展的进程。金氏脉学汲取了传统中医脉学整体观和辨证观的理论思想,通过数学手段对疾病基本做到定位、定性、定量诊断,在发展了传统脉学理论的同时与传统脉学理论又有根本的区别,为脉诊的客观化提供了可行性。
在脉搏信号采集方面,综合应用现代检测技术与信号处理理论,依据金氏脉学的分层取脉思想,设计了独特的脉搏自动分层测量系统。为了实现数字信号的自动采集,本系统使用PCI数据采集卡将压力传感器的模拟信号转换成数字信号,然后利用上层处理软件进行脉搏波的处理、分析与显示。
在脉搏波预处理方面,利用本文提出的基于经验模态分解的多带滤波器进行脉搏波的基线消除,并分别与形态滤波(Morphology)、有限冲击响应滤波(FIR)和样条估计这三种方法进行了比较,从仿真数据可以看出该方法取得了较好的滤波效果。
在脉搏信号的特征分析方面,从时域和频域两个方面对脉搏信号进行分析。另外把经验模态分解(EMD)、Hilbert-Huang变换和倒谱分析应用到脉搏波的特征提取中,具有创新性,并取得了初步的成功。
在前面脉象特征提取的基础上,选定9个能表征脉象实质的特征参数构成脉象识别的特征向量,使用基于改进型二叉树的支持向量机方法对7种基本脉象进行了分类识别。并与有向无环图SVM和神经网络方法进行了比较,正确识别率提高了3-6个百分点。
Traditional Chinese Medicine (TCM) diagnosis acquires pathological information through observing, smelling, asking and touching, which are also called "Four Diagnosis". As a major part of touching, pulse diagnosis becomes an important method to find out health status of patients. However, TCM, lack of quantitative standard, excessively relies on doctor's subjective judgment. So, objectivizing of TCM tries to establish diagnosis standard in order to solve these problems.
This paper summarizes from both success and defeat of our predecessors in this field. Based on
Mainly according to diagnosing experience, traditional pulse diagnosis is lack of objective standard, inconsistently, computer-based pulse diagnosis device, however, depends on the quantitative principles.
Concerning about pulse signal collection, we apply modern Measurement Technique and signal processing theory, design unique pulse automatic and layered measuring system. In order to collect digital signal in real-time, this system utilizes PCI data collecting card to transform analog signals into digital signals, and then data processing program to carry out signal analysing and displaying.
In the aspect of pulse signal pre-processing, this paper proposes a new EMD (Empirical Module Decomposition) based filter to remove baseline wander. Additionally, we made simulated experiments and evaluated its validity by quantitatively comparing with morphology filter, time variant filter and spline Estimation. The results showed that the proposed algorithm is efficient in removing pulse baseline wander.
In the aspect of pulse characteristics extraction, we not only make comprehensive analysis from time and frequency field, but also creatively apply EMD, Hibert-Huang Transform and Cepstrum Analysis into pulse characteristics extraction. We can find out that these parameters are efficient in the following classification process.
Following the pulse characteristics extraction above, we choose 9 characteristics parameters to construct characteristics vector, and utilize improved Binomial Tree based SVM (Support Vector Machine) to execute classification of 7 typical kinds of pulse. Finally, we compare this algorithm with DAG (Directed Acyclic Graphs) SVM and Neural Network, and we find that right identification rate increases about 3-6 percent.
引文
[1]李景唐.全国中西医结合第二届四诊研究学术会议纪要[J].中西医结合杂志,1988,8(4):254-256
[2]牛欣.论脉诊的“位、形、势”的属性[J].北京中医学院学报,1990,13(6):14-16
[3]牛欣.脉诊位、数、形、势变化的心血管生理学探讨[J].北京中医学院学报,1992,15(1):30-32
[4]荆炳忠,肖行贯,白波等.多功能微机脉图信号的采集和处理系统[J].电脑应用时代,1991,37(4):27-29
[5]袁肇凯.国外脉诊研究概况[J].浙江中医杂志,1989,10(7):329-331
[6]朱筱玮,朱新亚.腕带式脉搏计的研制[J].西安丁业学院学报,2001,21(4):349-351
[7]凌志远,杨大本.一种新型脉搏换能器的研制[J].华南理工大学学报(自然科学版),1992,20(3):79-85
[8]黄献平,李冰星.BYS-14型心电脉象仪与MX-8l1型脉象仪的比较[J].湖南中医学院学报,1999,19(1):66-67
[9]黄贤武,郑筱霞.传感器原理与应用[M].成都:电子科技大学出版社,1995
[10]吴长生,王毅,任国喜等.光电式数字脉搏计的研制[J].中国医疗器械杂志,1993,17(2):76-79
[11]梁中庆,阮晓声.光闸式桡动脉搏传感器的研制[J].中国医学物理学杂志,1996,13(1):55-57
[12]康健.采用脉冲调制的红外光电传感器[J].电子技术,1989,15(5):43
[13]姜凤岐,申弦京,张铁强等.光纤探头脉象仪的实验研究[J].吉林工业大学学报,1993,3:56-59
[14]王炳和,杨颓,相敬林.脉搏声信号检测系统实验设计及功率谱特征[J].中华物理医学杂志,1998,20(3):158-161
[15]田家玮,李如萍.三维血管超声研究的进展[J].中国医学影像技术,1999,15(5):398-399
[16]柳文仪,赖仲平.彩色脉冲多普勒超声仪对高血压病弦脉与非弦脉的研究[J].中医杂志,1993,34(11):684-685
[17]李敏,吕维新,燕红.细脉客观化研究[J].辽宁中医杂志,1992,11:1-3
[18]李国刚,雍丽,徐建国.虚实辩证的脉图判别式及其特征值参数研究[J].贵阳中医学报,1997,19(4):60-61
[19]Wang Lin,Chang SL,Wu Ye,et al.Resonance-The missing phenomenon in hemodynamics[J].Circ Res,1991:69-246
[20]Wang WK,Lo YY,Chiang Y,et al.Resonance of organs with the heart.In:Advance in Biomedical Engineering.Young WJ,(ed),Hemisphere,Washington,DC,1989:259-268
[21]Wang WK,Wang Lin YY,Hsu TL,et al.The relation between meridian and energy distribution from the pulse study[C].Proc.1~(st)International Conference on Bioenergeitc Med.-past,present and future,1989:302-319
[22]Young SO,Wang WK,Chang LS,et al.The filter properties of the arterial beds of organs in rats.Acta Physiol Scand,1992:145-401
[23]Young ST,Wang WK,Chang LS,et al.Specific frequency properties of renal and superior mesenteric arterial beds in rats.Cardiovasc Res 1989:23-465
[24]张修诚,王唯工,董猛三.针刺陷骨穴时脉波频谱的影响[J].中医药学报,1993,8(3):7-8
[25]Wang WK,Chen HL,Hsu TL,et al.Alterations of pulse in human subjects by three Chinese herbs.Am J Chin Med 1994:22(2):197
[26]Wang WK,Hsu TL,Chang HC,et al.Effect of acupuncture at tsu-san-li(st-36)on the pulse spectrum.Am J Chinese Med 1995:23(2):121
[27]柳兆荣.心血管流体力学[M].上海:复旦大学出版社,1986
[28]刁颖敏.生物力学的原理与应用[M].上海:同济大学出版社,1991
[29]Womersley J.R.,Osilletory Motion of a Viscous Liquid in a Thin-Walled Elastic Tube,1.The Linear Approximation for Long Wave,Phil.Mag.,1955,46:199-221
[30]McDonald D.A.,柳兆荣等译,动脉中的血液流[M].北京:科学出版社,1982
[31]柳兆荣,黄林,李惜惜.关于人体平均血压的估算[J].中国生物医学工程学报,1986,5(2)
[32]罗志昌等.由脉搏波计算人体心输出量的方法及在临床中的应用[M].北京工业大学学报,1988,14(2):13-20
[33]刘忠权等.心血关动力学常数分析[J].科学通报,1983,19:1208-1211 Shankar R.,Webster J.C.,"Noninvasive measurement of compliance of human leg arteries',IEEE Transon Bme,1991,38(1):62-67
[34]陶祖莱.生物流体力学[M].北京:科学出版社,1984
[35]Ling Y.W.,Peter C.,Frequency distribution of human pulse spectra[C].IEEE Trans.BME,1985,32(3):245-247
[36]Lee C.C.,Mark R.G,Analysis of Arterial Waves by the Single-Pulse-Response Method[C].IEEE Trans.BME,1993,40(8):833-836
[37]Simone Pola.Estimation of the power spectral density in nonstationary cardiovascular time series:Assessing the role of the time-frequency representations(FTR)[C].IEEE Trans BME,1996,43(1):46-58
[38]刘广斌等.两种滑脉患者与健康妇女指端容积脉搏波的谱分析[J].西安医科大学学报,1990,11(3):201-205
[39]张镜人等.脉象图频域指标和时域指标的典型相关分析[J].辽宁中医,1995,22(9):393-395
[40]王贞洁.常见中医脉象的计量诊断方法[C].全国中西医结合四诊研究学术会议资料,1983
[41]金伟.金氏脉学[M].济南:山东科学技术出版社,2000
[42]金伟.金氏实用脉学[M].济南:山东科学技术出版社,1993
[43]薛均义,张彦斌.MCS-51/96系列单片机微型计算机及应用[M].西安:西安交通大学出版社,1997
[44]于英民,莫玮,于佳.计算机接口技术[M].北京:电子工业出版社,1990
[45]李华.MCS-51系列单片机实用接口技术[M].北京:北京航空航天大学出版社,1993
[46]赵捷,华玫.一种滤除ECG基线漂移和交流干扰的简单算法[J].中国医疗器械,1991,15:262-263
[47]周静.心电信号中工频干扰的消除[J].生物医学工程研究,2003,22(4):61-64
[48]Sornmo L.Time-varying filtering for removal of baseline wander in exercise ECGs[C].Computers in Cardiology Proceedings,1991:145-148
[49]Boucheham B.,Ferdi Y.,Batouche M.C.Piecewise linear correction of ECG baseline wander:a curve simplification approach[J].Computer Methods and Programs in Biomedicine,2005,78(1):1-10
[50]王鹏,魏守水,黄青华.基于小波变换的自适应滤波器消除脉搏波基线漂移[J].中国医学物理学杂志,2004,21(5):296-299
[51]Chiu C.C.,Yeh S.J.A tentative approach based on Wiener filter for the reduction of respiratory effect in pulse signals[C].Proceedings-19th International Conference.Chicago:IEEE/EMBS,1997:1394-1397
[52]Huang N.E.,Shen Z.,Long S.R.,et al.The empirical mode decomposition and Hilbert spectrum for nonlinear and nonstationary time series analysis[C].Proceedings of the Royal Society of London,London,1998:903-995
[53]Liang H.,Lin Q.H.,Chen J.D.Z.Application of the empirical mode decomposition to the analysis of esophageal manometric data in gastro esophageal reflux disease[J].IEEE Trans.Biomed.Eng.,2005,52(10):1692-1701
[54]孙仁,沈海东,鲁传敬,等.HHT方法在脉搏波信号分析中的应用[J].医用生物力学,2006,21(2):87-93
[55]杨福生,高上凯.生物医学信号处理[M].北京:高等教育出版社,1989:1-2
[56]姚泰.生理学[M].北京:人民卫生出版社,2003
[57]Freisen G.,M.,Jannett T.C.,Djadallah M.A.,et al.A comparison of noise sensitivity of nine QRS detection algorithms[J].IEEE Trans.Biomed.Eng.1990,37(1):85-98
[58]张贤达,保铮.非平稳信号分析与处理[M].北京:国防工业出版社,1998:1-3
[59]Mallat S.A Wavelet Tour of signal Processing[M].Boston:Academic Press,1998
[60]赵恩俭.中医脉诊学[M].天津:天津科学技术出版社,1990:11-13
[61]Huang N.E.,Shen Z.,Long S.R.,et al.A new view of nonlinear water waves:the Hilbert spectrum[J].Ann Rev Fluid Mech,1999,31:417-457
[62]周百新,梁忠诚,赵阳,等.EMD及其在脑电分析中的应用研究[J].南京师范大学学报(工程技术版),2007,7(1):14-19
[63]李彬彬,袁中凡,杨春生.改进HHT算法及在心音信号分析中的应用[J].四川大学学报(工程科学版),2007,39(4):163-166
[64]胡航.语音信号处理[M].哈尔滨:哈尔滨工业大学出版社,2000:50-51
[65]李锦,何培宇.一种改进的基于小波去噪HMM非特定人语音识别算法[J].四川大学学报(自然科学版),2007,44(1):69-72
[66]北京医学院生理教研室.几种脉象的初步探讨[J].上海中医药杂志,1982,(2):8-10
[67]上海脉象协作组编.中医脉象脉图诊断研究.上海.1985:32-123
[68]王爱民,田志芬.利用模糊属性文法对中医脉图的分类研究[C].北京:中国生物医学工程学会年会论文集,1987:333-334
[69]Vapnik V.The nature of statistical learning theory[M].New York:Springer Verlag,1995:4280
[70]Vapnik V.,Golowich S.,Smola A.Support vector method for function approximation,regression estimation,and signal processing[J].Advances in Neural Information Processing Systems,1996,9:281-287
[71]Bottou L.,Cortes C.,Denker,et al.Comparison of Classifier Methods:A Case Study in Handwriting Digit Recognition[C].International Conference on Pattern Recognition.IEEE Computer Society Press,1994:77-87
[72]Friedman J.H.Another Approach to Polychotomous Classification[R].Technical report,Department of Statistics,Stanford Univeristy,1997
[73]Krebel U.Pairwise Classification and Support Vector Machines[M].Cambridge:The MIT Press,1999:255-268
[74]Platt J.C.,Cristianini N.,Shawe-Taylor J.Large Margin DAGs for Multi-class Classification[M].Cambridge:The MIT Press,2000:547-553
[75]Dietterich T.G,Bakiri G.Solving Multi-class Learning Problem via Error-Correcting Output Codes[J].Journal of Artificial Intelligence Research,1995,2:263-286
[76]Jorg Kindermann,Edda Leopold,Gerhard Paass.Multi-class Classification with Error Correcting Codes[C].E Leopold,M Kirsten eds.Treffen der GI-Fachgruppe 1.1.3,Maschinelles Lernen,2000 GMD Report 114
[77]夏建涛.基于机器学习的高维多光谱数据分类[D].西安:西北工业大学电路与系统,2002
[78]Azimi-Sadjadi M.R.,Zekavat S.A.Cloud Classification Using Support Vector Machines[C].Proc of the 2000 IEEE Geoscience and Remote Sensing Symposium,Honolulu,Hawaii,2000,7(2):669-671
[79]Takahash F,Abe S.Decision-Tree-Based Multi-class Support Vector Machine[J].Neural Information Processing,Proceeding the 9~(th)International Conference,2002:1408-1422
[80]Bennett K.,Cristianini N.,Shawe-Taylor J.,et al.Enlarging the Margin in Perceptron Decision Trees[J].Machine Learning,2000,41:295-313
[81]唐发明,王仲东,陈绵云.支持向量机多类分类算法研究[J].控制与决策,2005,20(7):746-749
[82]李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2):302-304
[2]牛欣.论脉诊的“位、形、势”的属性[J].北京中医学院学报,1990,13(6):14-16
[3]牛欣.脉诊位、数、形、势变化的心血管生理学探讨[J].北京中医学院学报,1992,15(1):30-32
[4]荆炳忠,肖行贯,白波等.多功能微机脉图信号的采集和处理系统[J].电脑应用时代,1991,37(4):27-29
[5]袁肇凯.国外脉诊研究概况[J].浙江中医杂志,1989,10(7):329-331
[6]朱筱玮,朱新亚.腕带式脉搏计的研制[J].西安丁业学院学报,2001,21(4):349-351
[7]凌志远,杨大本.一种新型脉搏换能器的研制[J].华南理工大学学报(自然科学版),1992,20(3):79-85
[8]黄献平,李冰星.BYS-14型心电脉象仪与MX-8l1型脉象仪的比较[J].湖南中医学院学报,1999,19(1):66-67
[9]黄贤武,郑筱霞.传感器原理与应用[M].成都:电子科技大学出版社,1995
[10]吴长生,王毅,任国喜等.光电式数字脉搏计的研制[J].中国医疗器械杂志,1993,17(2):76-79
[11]梁中庆,阮晓声.光闸式桡动脉搏传感器的研制[J].中国医学物理学杂志,1996,13(1):55-57
[12]康健.采用脉冲调制的红外光电传感器[J].电子技术,1989,15(5):43
[13]姜凤岐,申弦京,张铁强等.光纤探头脉象仪的实验研究[J].吉林工业大学学报,1993,3:56-59
[14]王炳和,杨颓,相敬林.脉搏声信号检测系统实验设计及功率谱特征[J].中华物理医学杂志,1998,20(3):158-161
[15]田家玮,李如萍.三维血管超声研究的进展[J].中国医学影像技术,1999,15(5):398-399
[16]柳文仪,赖仲平.彩色脉冲多普勒超声仪对高血压病弦脉与非弦脉的研究[J].中医杂志,1993,34(11):684-685
[17]李敏,吕维新,燕红.细脉客观化研究[J].辽宁中医杂志,1992,11:1-3
[18]李国刚,雍丽,徐建国.虚实辩证的脉图判别式及其特征值参数研究[J].贵阳中医学报,1997,19(4):60-61
[19]Wang Lin,Chang SL,Wu Ye,et al.Resonance-The missing phenomenon in hemodynamics[J].Circ Res,1991:69-246
[20]Wang WK,Lo YY,Chiang Y,et al.Resonance of organs with the heart.In:Advance in Biomedical Engineering.Young WJ,(ed),Hemisphere,Washington,DC,1989:259-268
[21]Wang WK,Wang Lin YY,Hsu TL,et al.The relation between meridian and energy distribution from the pulse study[C].Proc.1~(st)International Conference on Bioenergeitc Med.-past,present and future,1989:302-319
[22]Young SO,Wang WK,Chang LS,et al.The filter properties of the arterial beds of organs in rats.Acta Physiol Scand,1992:145-401
[23]Young ST,Wang WK,Chang LS,et al.Specific frequency properties of renal and superior mesenteric arterial beds in rats.Cardiovasc Res 1989:23-465
[24]张修诚,王唯工,董猛三.针刺陷骨穴时脉波频谱的影响[J].中医药学报,1993,8(3):7-8
[25]Wang WK,Chen HL,Hsu TL,et al.Alterations of pulse in human subjects by three Chinese herbs.Am J Chin Med 1994:22(2):197
[26]Wang WK,Hsu TL,Chang HC,et al.Effect of acupuncture at tsu-san-li(st-36)on the pulse spectrum.Am J Chinese Med 1995:23(2):121
[27]柳兆荣.心血管流体力学[M].上海:复旦大学出版社,1986
[28]刁颖敏.生物力学的原理与应用[M].上海:同济大学出版社,1991
[29]Womersley J.R.,Osilletory Motion of a Viscous Liquid in a Thin-Walled Elastic Tube,1.The Linear Approximation for Long Wave,Phil.Mag.,1955,46:199-221
[30]McDonald D.A.,柳兆荣等译,动脉中的血液流[M].北京:科学出版社,1982
[31]柳兆荣,黄林,李惜惜.关于人体平均血压的估算[J].中国生物医学工程学报,1986,5(2)
[32]罗志昌等.由脉搏波计算人体心输出量的方法及在临床中的应用[M].北京工业大学学报,1988,14(2):13-20
[33]刘忠权等.心血关动力学常数分析[J].科学通报,1983,19:1208-1211 Shankar R.,Webster J.C.,"Noninvasive measurement of compliance of human leg arteries',IEEE Transon Bme,1991,38(1):62-67
[34]陶祖莱.生物流体力学[M].北京:科学出版社,1984
[35]Ling Y.W.,Peter C.,Frequency distribution of human pulse spectra[C].IEEE Trans.BME,1985,32(3):245-247
[36]Lee C.C.,Mark R.G,Analysis of Arterial Waves by the Single-Pulse-Response Method[C].IEEE Trans.BME,1993,40(8):833-836
[37]Simone Pola.Estimation of the power spectral density in nonstationary cardiovascular time series:Assessing the role of the time-frequency representations(FTR)[C].IEEE Trans BME,1996,43(1):46-58
[38]刘广斌等.两种滑脉患者与健康妇女指端容积脉搏波的谱分析[J].西安医科大学学报,1990,11(3):201-205
[39]张镜人等.脉象图频域指标和时域指标的典型相关分析[J].辽宁中医,1995,22(9):393-395
[40]王贞洁.常见中医脉象的计量诊断方法[C].全国中西医结合四诊研究学术会议资料,1983
[41]金伟.金氏脉学[M].济南:山东科学技术出版社,2000
[42]金伟.金氏实用脉学[M].济南:山东科学技术出版社,1993
[43]薛均义,张彦斌.MCS-51/96系列单片机微型计算机及应用[M].西安:西安交通大学出版社,1997
[44]于英民,莫玮,于佳.计算机接口技术[M].北京:电子工业出版社,1990
[45]李华.MCS-51系列单片机实用接口技术[M].北京:北京航空航天大学出版社,1993
[46]赵捷,华玫.一种滤除ECG基线漂移和交流干扰的简单算法[J].中国医疗器械,1991,15:262-263
[47]周静.心电信号中工频干扰的消除[J].生物医学工程研究,2003,22(4):61-64
[48]Sornmo L.Time-varying filtering for removal of baseline wander in exercise ECGs[C].Computers in Cardiology Proceedings,1991:145-148
[49]Boucheham B.,Ferdi Y.,Batouche M.C.Piecewise linear correction of ECG baseline wander:a curve simplification approach[J].Computer Methods and Programs in Biomedicine,2005,78(1):1-10
[50]王鹏,魏守水,黄青华.基于小波变换的自适应滤波器消除脉搏波基线漂移[J].中国医学物理学杂志,2004,21(5):296-299
[51]Chiu C.C.,Yeh S.J.A tentative approach based on Wiener filter for the reduction of respiratory effect in pulse signals[C].Proceedings-19th International Conference.Chicago:IEEE/EMBS,1997:1394-1397
[52]Huang N.E.,Shen Z.,Long S.R.,et al.The empirical mode decomposition and Hilbert spectrum for nonlinear and nonstationary time series analysis[C].Proceedings of the Royal Society of London,London,1998:903-995
[53]Liang H.,Lin Q.H.,Chen J.D.Z.Application of the empirical mode decomposition to the analysis of esophageal manometric data in gastro esophageal reflux disease[J].IEEE Trans.Biomed.Eng.,2005,52(10):1692-1701
[54]孙仁,沈海东,鲁传敬,等.HHT方法在脉搏波信号分析中的应用[J].医用生物力学,2006,21(2):87-93
[55]杨福生,高上凯.生物医学信号处理[M].北京:高等教育出版社,1989:1-2
[56]姚泰.生理学[M].北京:人民卫生出版社,2003
[57]Freisen G.,M.,Jannett T.C.,Djadallah M.A.,et al.A comparison of noise sensitivity of nine QRS detection algorithms[J].IEEE Trans.Biomed.Eng.1990,37(1):85-98
[58]张贤达,保铮.非平稳信号分析与处理[M].北京:国防工业出版社,1998:1-3
[59]Mallat S.A Wavelet Tour of signal Processing[M].Boston:Academic Press,1998
[60]赵恩俭.中医脉诊学[M].天津:天津科学技术出版社,1990:11-13
[61]Huang N.E.,Shen Z.,Long S.R.,et al.A new view of nonlinear water waves:the Hilbert spectrum[J].Ann Rev Fluid Mech,1999,31:417-457
[62]周百新,梁忠诚,赵阳,等.EMD及其在脑电分析中的应用研究[J].南京师范大学学报(工程技术版),2007,7(1):14-19
[63]李彬彬,袁中凡,杨春生.改进HHT算法及在心音信号分析中的应用[J].四川大学学报(工程科学版),2007,39(4):163-166
[64]胡航.语音信号处理[M].哈尔滨:哈尔滨工业大学出版社,2000:50-51
[65]李锦,何培宇.一种改进的基于小波去噪HMM非特定人语音识别算法[J].四川大学学报(自然科学版),2007,44(1):69-72
[66]北京医学院生理教研室.几种脉象的初步探讨[J].上海中医药杂志,1982,(2):8-10
[67]上海脉象协作组编.中医脉象脉图诊断研究.上海.1985:32-123
[68]王爱民,田志芬.利用模糊属性文法对中医脉图的分类研究[C].北京:中国生物医学工程学会年会论文集,1987:333-334
[69]Vapnik V.The nature of statistical learning theory[M].New York:Springer Verlag,1995:4280
[70]Vapnik V.,Golowich S.,Smola A.Support vector method for function approximation,regression estimation,and signal processing[J].Advances in Neural Information Processing Systems,1996,9:281-287
[71]Bottou L.,Cortes C.,Denker,et al.Comparison of Classifier Methods:A Case Study in Handwriting Digit Recognition[C].International Conference on Pattern Recognition.IEEE Computer Society Press,1994:77-87
[72]Friedman J.H.Another Approach to Polychotomous Classification[R].Technical report,Department of Statistics,Stanford Univeristy,1997
[73]Krebel U.Pairwise Classification and Support Vector Machines[M].Cambridge:The MIT Press,1999:255-268
[74]Platt J.C.,Cristianini N.,Shawe-Taylor J.Large Margin DAGs for Multi-class Classification[M].Cambridge:The MIT Press,2000:547-553
[75]Dietterich T.G,Bakiri G.Solving Multi-class Learning Problem via Error-Correcting Output Codes[J].Journal of Artificial Intelligence Research,1995,2:263-286
[76]Jorg Kindermann,Edda Leopold,Gerhard Paass.Multi-class Classification with Error Correcting Codes[C].E Leopold,M Kirsten eds.Treffen der GI-Fachgruppe 1.1.3,Maschinelles Lernen,2000 GMD Report 114
[77]夏建涛.基于机器学习的高维多光谱数据分类[D].西安:西北工业大学电路与系统,2002
[78]Azimi-Sadjadi M.R.,Zekavat S.A.Cloud Classification Using Support Vector Machines[C].Proc of the 2000 IEEE Geoscience and Remote Sensing Symposium,Honolulu,Hawaii,2000,7(2):669-671
[79]Takahash F,Abe S.Decision-Tree-Based Multi-class Support Vector Machine[J].Neural Information Processing,Proceeding the 9~(th)International Conference,2002:1408-1422
[80]Bennett K.,Cristianini N.,Shawe-Taylor J.,et al.Enlarging the Margin in Perceptron Decision Trees[J].Machine Learning,2000,41:295-313
[81]唐发明,王仲东,陈绵云.支持向量机多类分类算法研究[J].控制与决策,2005,20(7):746-749
[82]李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2):302-304