摘要
中医将脉象视为生命的语言,它蕴含了丰富的人体健康状况信息。但由于中医脉象在教学中难度很大,临床脉诊时分歧较多,使脉诊经验无法交流。脉诊的定性化和主观性大大影响了其精度和可行性,成为中医脉诊应用、发展和交流的制约因素。随着传感器技术和计算机处理技术的发展,人们开始致力于脉诊的客观化,希望用现代科学技术的方法和仪器,推进脉诊的科学性。
高阶统计量是研究非线性和非高斯信号的有效工具,它在信号检测、特征提取以及谐波恢复等方面具有特有的优越性。本文主要应用倒双谱和三阶倒谱熵对脉象信号进行特征提取及分类识别研究。
我们通过对脉图的形态分析,在频域脉搏图中提取特征信息以及采用模式识别系统进行分类识别等,在国内外已有不少报道,但算法还不够完善。本课题在总结前人工作的基础上,对脉象数据的特征提取,脉象的识别进行了研究。主要工作包括以下几个方面:
首先,在对国内外人体脉象客观化研究方法进行比较的基础上,针对以往脉象特征提取算法单一地从频域提取特征值存在一些缺点,本文提出了多种基于倒双谱的特征参数提取方法:倒双谱的对角切片的零分量值、倒双谱对角切片中m = 1, n=1时的分量值、特定区间倒双谱峰态系数值、特定区间内三阶倒谱熵值。虽然这几种方法各自的识别效果还是可以,但是运算量较大,识别有些复杂。
其次,鉴于模式识别方法既简单又易于实现的特点,特别是在建立脉象信号识别模型时能减少数据的计算量,因而能够获得到较好的识别精度及较快的响应速度,本文在深入研究脉象数据特征的基础上,构建了基于倒双谱和马氏距离的辨识系统。并用它们对正常健康人和吸毒病人两类脉象信号进行了成功识别,平均识别率可以达到87.5%,为以后临床实验提供参考。
实验表明,采用本文提出的基于倒谱提取的特征参数和马氏距离组成的模型进行的中医脉象信号分析识别时,识别正确率取得了一定效果。
本文的研究是针对不同人体中医脉象信号而提出的一种脉象特征提取与识别方法,这一研究对于脉象客观化、脉象模型识别和现代信号处理技术在医疗辅助诊断中的应用,推动传统医学现代化具有积极意义。
Pulse is called the language of life in Traditional Chinese Medicine (TCM), it contains a wealth of information about the status of human health. However, due to pulse at the teaching of Chinese medicine is very difficult, when the doctors have lots of difference in clinic, so the experience of pulse diagnosis can not be communicated. The qualitative and subjective pulse diagnosis greatly affects its accuracy and feasibility, and restricts the application, developing and communication of Traditional Chinese Medicine pulse diagnosis. With the development of sensor and computer technology, people hope to apply modern technology to human pulse diagnosis to reveal the essence and feature of pulse phenomena scientifically, which is the main research aspect in this paper.
Higher-order Statistics (HOS) is the primary analysis tool in analyzing non-Gaussian and non-linear signal. It possesses plenty of advantages in signal detection, feature extraction and harmonic retrieval. Based on the Bicepstrum, the features of Human Pulse Signal are extracted and classified in the paper.
There have been a lot of reports about extracting features in time domain by analyzing the characteristics of human pulse. There are also a lot of works focused on how to use neural network to classify and recognize the pulse manifestations. But these techniques are far from perfect. In this paper, the following works are reported.
Firstly, based on comparing different objective algorithms of human pulse manifestations considering that most traditional methods are apt to obtain the information only from time-domain and can not preserve all the original information of pulse, varieties of approaches feature extraction of human pulse signal based on Bicepstrum are developed, which include the value of zero diagonal slice of Bicepstrum, the value of diagonal slice of Bicepstrum when m = 1, n=1, the kurtosis of Bicepstrum within a specific range and the value of third-order Cepstrum entropy within a specific range. Although these methods can achieve respective effects, larger operations and complex identification can exist.
Secondly, Pattern Recognition technique is simple, effective and reliable. Especially, it can greatly decrease the computational load and memory. This technique obtains ideal results with high precision of recognition and rapid response rate. By analyzing the pulse signal, the recognition systems based on Bicepstrum and Mahalanobis distance have been constructed. Using the system, the pulse signals of the normal and drug addicts have been successful recognized, and the average recognition rate is about 87.5%. By comparing the result, the system optimization is introduced for clinical experiment in future.
The experiment results show that the extracted parameter values based on the above methods as the feature vector using Mahalanobis distance is effective and correct.
As the algorithm implemented in this paper is in accordance with characteristics acquisition and recognition of Traditional Chinese Medicine syndrome types, it could be used as reference in objective research and real clinics. It also has much significance to develop the study of Traditional Chinese Medicine.
引文
[1]张坤艳.脉象特征信息的提取与识别方法研究[D].山东科技大学硕士学位论文,2007.
[2]杨福生,高上凯.生物医学信号处理[M].高等教育出版社,1989,5.
[3]陈雪峰.脉搏波特征提取算法及其应用研究[D].大连理工大学硕士学位论文,2006.
[4]黄旭,蔡骏,周昌乐,张志枫.中医脉象信息分析与识别方法的研究进展[J].福建电脑,2007,3.
[5]李锡杰,师硕,王旭.生物电信号的滤波与现代分析方法研究[J].医学信息学,2005,18(12).
[6]许瑞庆,行鸿彦.基于Hilbert-Huang变换的脉搏信号分析[J].中国组织工程研究与临床康复,2008,12(4).
[7]张贤达.时间序列分析———高阶统计量方法[M] .北京:清华大学出版社,1996.
[8]燕海霞,王忆勤,李福凤.脉象信号分析方法的研究与应用新解[J].中医药学刊,2005,23(1).
[9]李景唐.中医脉象的客观检测和描述[M].医疗装备,2005,5
[10] Akan,A.; Artan,R.B.U. Time-varying bispectral analysis of nonstationary signals[J]. Signal Processing and Its Applications,2003. Proceedings. Seventh International Symposium on Volume 1, 1-4 July 2003 Page(s):569 - 572 vol.1.
[11]韩济生. 21世纪的神经科学:高度分析基础上的高度结合[J].北京大学学报(医学版).
[12]孙秉毅,于春泉,王巍,付于,夏天.中医脉诊客观化的研究进展[J].河北中医药学报,2003,l8 (3).
[13]邓原成,王新.脉象图的参数模型及其应用研究[J].北京生物医学工程,1994,13 (1) :1~9.
[14]刘梅,郝小梅,陈群,罗益宽.中医脉诊客观化研究新探[J].中医函授通讯,2000,19(2).
[15]余伶俐.中医脉诊客观化与数字化研究[J].辽宁中医杂志,2006,33(2).
[16]杨福生,吕杨生主编.生物医学信号的处理与识别[M].天津科技翻译出版公司,1997.
[17]姚天任,孙洪.现代信号处理[M].华中科技大学出版社. 1999.
[18]程广涛,戴卫国,李茂宽.高阶统计量在水下目标识别中的应用[J].青岛大学学报.,2004,17(4).
[19]杨宇山,刘天佑,王法刚,李媛媛.高阶统计量弱信号识别方法在识别地质孔洞中的应用[J].长江科学院院报.2005,22(4).
[20] Chandran,V. Elgar,S.; Nguyen,A. Detection of mines in acoustic images using higher order spectral features[J]. Oceanic Engineering,IEEE Journal of Volume 27,Issue 3,July 2002 Page(s):610– 618.
[21] De la Rosa,J.G.; Lloret,I.; Moreno,A.; Piotrkowski,R.; Ruzzante,J.; Puntonet,C.G.; Gorriz,J.M. Higher-order spectra and independent component analysis used for identification and SNRenhancement of acoustic emission signals[J]. Electrotechnical Conference,2006. MELECON 2006. IEEEE Mediterranean 16-19 May 2006 Page(s):490– 493.
[22] Colas,M.; Gelle,G.; Galy,J.; Delaunay,G. A multitime-frequency approach for detection and classification of noisy frequency modulations[J]. Statistical Signal and Array Processing,2000. Proceedings of the Tenth IEEE Workshop on 14-16 Aug. 2000 Page(s):655 - 659 .
[23]孙骏,陈淑珍,邹炼.Wigner高阶矩谱在分析相控阵探地雷达数据中的应用[J].武汉大学学报,2004, 50 (5 )理学版.
[24]丁建江,张贤达.复AR双谱及在常规雷达目标分类中的应用.信号处理.2002,18(6).
[25]刘东红,张永顺,陈志杰,程俊斌.基于时域双谱的超宽带雷达目标特征提取[J].
[26]蔡忠伟,李建东.基于双谱的通信辐射源个体识别[J].通信学报.2007,28(2).
[27]朱家富,杨浩.基于高阶复杂性测度的心率变异信号分析[J].生物物理学报.2004,20(3).
[28]何莹,吴效明,岑人经,周静.基于高阶统计量的心音信号分析[J].模式识别.2007,23(2-1).
[29] Ying-Hsiang Chen and Sung-Nien Yu.”Subband Features Based on Higher Order Statistics for ECG Beat Classification”[J],Proceedings of the 29th Annual International Conference of the IEEE EMBS CitéInternationale,Lyon,France August 23-26,2007.
[30]朱海军,万明习,王素品,赵守国.不同种类肺音信号的双谱分析[J].仪器仪表学报.2001,22(5).
[31] Messina,A.R.; Vittal,V. Assessment of nonlinear interaction between nonlinearly coupled modes using higher order spectra[J]. Power Systems,IEEE Transactions onVolume 20,Issue 1, Feb 2005 Page(s):375– 383.
[32]王利英,夏兆旺,董建宁.高阶统计量在故障诊断中的应用研究[J].现代机械,2005,6.
[33]胡军辉.基于谱熵的故障特征提取与数据挖掘技术研究[D].西北工业大学硕士学位论文.2007.
[34]李宏坤,张志新,马孝江,王珍.基于Hilbert谱熵的柴油机故障诊断方法研究[J].大连理工大学学报.2008,48(2).
[35] Acar,T.; Yu,Y. Petropulu,A.P. Blind MIMO System Estimation Based on PARAFAC Decomposition of Higher Order Output[J] Tensors.Signal Processing,IEEE Transactions on [see also Acoustics,Speech,and Signal Processing,IEEE Transactions on] Volume 54, Issue 11, Nov. 2006 Page(s):4156– 4168.
[36]何海平.基于高阶统计量的信号分析与处理[J].机电工程.2003.No.5:85-86
[37]张义军.基于高阶统计量的舰船辐射噪声特征提取及分类识别研究[D].西北工业大学硕士学位论文.2001.
[38]黄镭.高阶倒谱估计在脉象信号分析中的应用[D].重庆大学硕士学位论文.2007.
[39]刘峰.中医脉象描述特点及全方位脉象仪器检测研究[D].北京中医药大学博士研究生学位论文.2007.
[40]周霞.中医脉象信号的时频分析[D].重庆大学硕士学位论文,2003.
[41]费兆馥主编.现代中医脉诊学[M].北京:人民卫生出版社,2003,9一n.
[42]朱英华.阵列式脉搏传感器的研制及小波变换在脉搏信息分析中的应用[D].重庆大学硕士学位论文,2000.
[43] Nikias,C.L.,and A.P.Petroplus. Higher-order Spectra Analysis[M]. Prentice Hall, Englewood Cliffs,1993.
[44] John G. Proakis.统计信号处理算法[M].清华大学出版社.2006.
[45]韦晓东,胡光锐,任晓林.应用倒谱特征的带噪语音端点检测方法[J].上海交通大学学报.2000,34 (2 ).
[46]熊军,李凤英,沈玉娣.基于高阶倒谱熵的齿轮故障诊断[J].机械传动.2005.
[47]徐东,彭圆,孔艳霞,李雪耀.倒谱在水中目标分类中的应用[J].2002,29 (11).
[48] Pan,R.and Nikias,C.L, "The Complex Cepstrum of Higher Order Cumulants and Nonminimum Phase System Identification[J]",IEEE Transactions on Acoustics,speech,and Signal Processing,VOL. 36,NO. 2,pp. 186-205,FEB. 1988.
[49]黄镭,刘宗行,蔡坤宝.倒双谱估计在海洛因吸毒者脉象信号检测中的应用[J].重庆工学院学报(自然科学版).2007,21(7).
[50]贾俊平编著.统计学[M].清华大学出版社.2004.
[51]边肇祺.模式识别[M].清华大学出版社.2000.
[52]孙即祥等编著.现代模式识别[M].国防科技大学出版社.2002.
[53]朱忠奎,孔凡让,王建平,李晓峰,刘维来,刘志刚.循环双谱及其在齿轮箱故障识别中的应用研究[J].振动工程学报.2004,17(2).
[54]曹向海,刘宏伟,吴顺君.基于零相位谱的雷达目标识别[J].现代雷达.2007,29(9).
[55]王瑛,程汉文,吴乐南.基于谱相关特征的信号调制方式识别[J].信息技术.2006,12.
[56]彭涛.脉象信号分析与中医脉象证型识别研究[D].苏州大学硕士学位论文. 2008.
[57]李圣君.呼吸音特征提取与分类识别方法研究[D].山东大学硕士学位论文.2006.
[58]杨淑莹著.模式识别与智能计算——Matlab技术实现[M].电子工业出版社.2008.
[59]赵治栋,赵知劲,张嵩,潘敏,陈裕泉.心音自动分段算法研究[J].航天医学与医学工程.2004,17(6).
[60]樊养余,李平安,孙进才,尚久浩.基于双谱的谐波信号相位重构[J].信号处理.2000,16(1).
[61]谢桂生,石玉梅.基于高阶谱的高分辨率处理[J].石油地球物理勘探.2000,35(6).
[62]周德鑫,冯大政,赵梦.利用高阶累积量的盲多输入多输出系统辨识[J].2005,27(11).
[63]李长柏,王海燕,赵妮.倒双谱的降维谱在舰船推进系统中的仿真研究[J].计算机仿真
[64]柳亦兵,崔彦彬.峰态因数指标在齿轮故障振动诊断中的应用[J].华北电力大学学报.2001,28(3).
[65] Colas,M. Gelle,G.. A multitime-frequency approach for detection and classification of neighboring instantaneous frequency laws in a noisy environment[J]. Signal Processing Letters,IEEE Volume 11,Issue2 Part 1, Feb. 2004 Page(s):71– 74.
[66] Le Roux,J. Icart,S. System frequency response phase estimation based on skewness or kurtosis maximization[J]. Acoustics,Speech,and Signal Processing , 2000.ICASSP”00. Proceedings. 2000 IEEE International Conference on”Volume 1, 5-9 June 2000 Page(s):564 - 567 vol.1 .
[67] John G. Proakis等著.汤俊等译.统计信号处理算法[M].北京:清华大学出版社.2006.
[68]罗志昌,张松,杨文鸣等.脉搏波波形特征信息的研究[J].北京工业大学报,1996,22(1) :71~79.
[69]安雪岚,安丽娅,安雪梅,张丹,刘卫星,文安丽.吸毒者48例心电图异常特征分析[J].武警医学.2004,15(7).
[70]陈明杰,蔡坤宝,石永智,王永东.吸毒者脉象异常的现代谱分析法[J] .重庆大学学报.2001,24(4).
[71]沈民奋,沈凤麟,许崇涛,朱国平.不同状态下脑电信号的双谱分析[J].生物物理学报.1998,14(1)
[72]王炳和,张效民,相敬林,职利琴.倒谱与解卷积技术在人体脉搏系统分析中的应用[J].西北工业大学学报.2000,18(4)