小波变换和概率神经网络在脉象信号分析中的应用
|
摘要
中医独特的诊断方法及治病的疗效是有目共睹的。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研究,希望用现代科学技术的方法和仪器,推进中医脉诊的现代化,这也是本文进行研究的目的。
本论文着重对小波分析的基本概念和基本理论进行了详细的阐述,并探讨了其物理意义,在利用多分辨率分析脉象信号时,对算法进行了推导、验证和应用,且给出了多分辨率分析的矩阵表达方式,着重分析了小波系数和尺度系数的具体含义,为脉象信号的多分辨率分析奠定了坚实的基础。
本论文还对神经网络的基本概念和基本理论进行了详细的阐述,突出探讨了概率神经网络的算法探讨和分析,为模式识别提高了扎实的理论依据。
小波分析是一种在时域和频域均具有良好局域性的分析方法,尤其适用于非平稳信号的处理。本文应用小波分析的多分辨率分析算法分析了15例海洛因吸毒者和22例正常人脉象信号。通过提取小波系数和尺度系数,找出了海洛因吸毒者与正常人脉象信号之间的显著差异,初步提出了用于划分吸毒者和正常人的判据,根据该判据,22例正常人全被检测出来,而吸毒者B13被误检为正常人。
本文还在对脉象信号进行多分辨率分析的基础上,利用概率神经网络优良的聚类效应,对37例脉象信号样本(15例海洛因吸毒者和22例正常人脉象信号)进行模式分类,结果把15例吸毒者的脉象信号识别出来,没有一个误判。
Traditional Chinese medicine all along receives publicity for its unique diagnostic method and particularly curative effects. With the development of sensor and computer technology, people hope to apply modern technology to human pulse diagnosis to reveal the essence and features of pulse phenomena scientifically, which is the main research aspect in this paper.
This paper deduced the theorems and formulas of the wavelet transform, and discussed the physics meaning of them, applied and proved them in the processing of the pulse signals. At the same time, multiresolution analysis in matrix form is given to get the clear idea of the wavelet coefficients and the scalar coefficients, which lays the foundation in the processing of the pulse signals.
This paper also deduced the theorems and formulas of the neural networks, and gave especial research on algorithm of the probabilistic neural network, which is much helpful for the model recognition.
Wavelet transform is a good analytical method both in the time and the frequency domains, especially applicable for non-stationary signal processing. In this paper we analyze pulse signals of 15 heroin addicts and 15 healthy persons using the multiresolution analysis of wavelet transform. By means of the wavelet coefficients and scalar coefficients of the wavelet transform, we found the significant difference between the heroin addicts and the healthy persons, a primary criterion for measuring off the heroin addicts and the healthy persons was obtained. Based on this criterion, the 15 healthy persons were identified and 1 heroin addicts were misjudged.
After analyzing the pulse signals using the multiresolution method, this paper also uses the probabilistic neural network to identify the 30 pulse signals. Because of the good recognition behavior of the probabilistic neural network, the 15 pulse signals from the heroin addicts are well picked up, with excellent results to the end.
本论文着重对小波分析的基本概念和基本理论进行了详细的阐述,并探讨了其物理意义,在利用多分辨率分析脉象信号时,对算法进行了推导、验证和应用,且给出了多分辨率分析的矩阵表达方式,着重分析了小波系数和尺度系数的具体含义,为脉象信号的多分辨率分析奠定了坚实的基础。
本论文还对神经网络的基本概念和基本理论进行了详细的阐述,突出探讨了概率神经网络的算法探讨和分析,为模式识别提高了扎实的理论依据。
小波分析是一种在时域和频域均具有良好局域性的分析方法,尤其适用于非平稳信号的处理。本文应用小波分析的多分辨率分析算法分析了15例海洛因吸毒者和22例正常人脉象信号。通过提取小波系数和尺度系数,找出了海洛因吸毒者与正常人脉象信号之间的显著差异,初步提出了用于划分吸毒者和正常人的判据,根据该判据,22例正常人全被检测出来,而吸毒者B13被误检为正常人。
本文还在对脉象信号进行多分辨率分析的基础上,利用概率神经网络优良的聚类效应,对37例脉象信号样本(15例海洛因吸毒者和22例正常人脉象信号)进行模式分类,结果把15例吸毒者的脉象信号识别出来,没有一个误判。
Traditional Chinese medicine all along receives publicity for its unique diagnostic method and particularly curative effects. With the development of sensor and computer technology, people hope to apply modern technology to human pulse diagnosis to reveal the essence and features of pulse phenomena scientifically, which is the main research aspect in this paper.
This paper deduced the theorems and formulas of the wavelet transform, and discussed the physics meaning of them, applied and proved them in the processing of the pulse signals. At the same time, multiresolution analysis in matrix form is given to get the clear idea of the wavelet coefficients and the scalar coefficients, which lays the foundation in the processing of the pulse signals.
This paper also deduced the theorems and formulas of the neural networks, and gave especial research on algorithm of the probabilistic neural network, which is much helpful for the model recognition.
Wavelet transform is a good analytical method both in the time and the frequency domains, especially applicable for non-stationary signal processing. In this paper we analyze pulse signals of 15 heroin addicts and 15 healthy persons using the multiresolution analysis of wavelet transform. By means of the wavelet coefficients and scalar coefficients of the wavelet transform, we found the significant difference between the heroin addicts and the healthy persons, a primary criterion for measuring off the heroin addicts and the healthy persons was obtained. Based on this criterion, the 15 healthy persons were identified and 1 heroin addicts were misjudged.
After analyzing the pulse signals using the multiresolution method, this paper also uses the probabilistic neural network to identify the 30 pulse signals. Because of the good recognition behavior of the probabilistic neural network, the 15 pulse signals from the heroin addicts are well picked up, with excellent results to the end.
引文
[1] 梁学章等. 小波分析. 国防工业出版社 2005
[2] 飞思科技产品研发中心编著. 小波分析理论与实现. 电子工业出版社. 2005
[3] 费兆馥,张志枫.中医脉诊的图像化和定量化.自然杂志,1995,Vol.17, No.5:269-274.
[4] 王丽勤.中医诊寸口脉的历史和体会.北京医科大学学报,1994, Vol.26, No.1:55-57.
[5] 杨福生,高上凯.生物医学信号处理.高等教育出版社,1989.
[6] 唐晓初.小波分析及其应用.重庆大学光电工程学院,2003..
[7] 许东.基于 MATLAB6.X 的系统分析与设计—神经网络 西安电子科技大学出版社 2002
[8] Simmon Haykin Neural networks China Machine Press 2004.
[9] 张力.脉诊研究进展.山东中医学院学报,1995,Vol.19, No.4:281-284.
[10] 王崇骏.人工智能理论研究及测控技术在中医脉象辨识中的应用.河海大学硕士论文,2001.
[11] 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. 重庆大学硕士学位论文,2000.
[12] 冯月明.基于小波分析的海量图像管理与发布方法及其系统实现.西安电子科技大学硕士论文,2003.
[13] 王颖东. 基于小波分析的电路故障诊断技术研究,华中科技大学硕士论文,2003
[14] 徐凌.基于小波分析的网络业务的研究,天津大学硕士论文,2003
[15] 许刚.基于小波分析的视频图象编码研究,中国科学院软件研究所博士后论文,1999
[16] 曹茂森.基于动力指纹小波分析的结构损伤特征提取与辨识基本问题研究,河海大学博士论文,2005
[17] 赵温波.径向基概率神经网络研究,中国科技大学博士论文,2003
[18] 徐旺林.概率神经网络及其在地球物理勘探中的应用,兰州大学硕士论文,2003
[19] 杨晓楠.基于概率神经网络与小波变换的结构检测方法研究,沈阳建筑大学硕士论文,2004
[20] 张卫东.基于概率神经网络的鲁棒性云检测研究,青岛海洋大学博士论文,2001
[21] Donald B.Percival Wavelet Methods for Time Series Analysis China Machine Press 2004
[22] D Veitch, M S Taqqu, P Abry. Meaningful MRA initialization for discrete time series. Signal Processing 80,2000:1971-1983.
[23] D Labata, R Ababoua, A Manginb. Rainfall–runoff relations for karstic springs. Part II: continuous wavelet and discrete orthogonal multiresolution analyses, Journal of Hydrology 238,2000:149-178.
[24] J.Martinez-Alajarin, Wavelet and Wavelet Packet Compression of Phonocardiograms,ELECTRONICS LETTERS 19th August 2004 Vol.40 No.17.
[25] D K Hoffman, D J Kouri. Shannon–Gabor wavelet distributed approximating functional. Chemical Physics Letters 287,1998:119–124.
[26] W.P.Sweeney Jr. PROBABILISTIC NEURAL NETWORK AS CHROMOSOME CLASSIFIER, Proceeding of 1993 International Joint Conference on Neural Networks.
[27] Stephane G Mallat. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,1989,VOL.II,NO.7:674-693.
[28] M.T.Musavi, IMPROVING THE PERFORMANCE OF PROBABILISTIC NEURAL NETWORKS,0-7803-0559-0/92 $3.00@1992 IEEE.
[29] M Maslen, P Abbott. Automation of the lifting factorisation of wavelet transforms. Computer Physics Communications 127,2000:309–326
[30] 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.重庆大学硕士学位论文,2000.
[31] R G Lueck,F R Driscoll,M Nahon. A wavelet for predicting the time-domain response of vertically tethered systems. Ocean Engineering 27,2000: 1441–1453.
[32] Umberto Amato, Claudia Angelini, Carmine Serio. Compression of AVHRR images by wavelet packets. Environmental Modelling & Software 15,2000:127–138.
[33] L-K.Shark and D.Qi, Approach to Wavelet Transform Implementation: Wavelet-like filter banks, ELECTRONICS LETTERS 20th November 1997 Vol.33 No.24
[34] Leszek Rutkowski,Adaptive Probabilistic Neural Networks for Pattern Classification in Time-Varying Environment, 1045-9227/04$20.00@2004 IEEE.
[35] Fabio Ancona, Anna Marai Colla, Implementing Probabilistic Neural Networks, Neural Computing&Applic(1997)5:152~159.
[36] Donald F.specht Probabilistic Neural Network for Classification, Mapping, or Associative Memory, Digital Object Identifier 10.1109ACNN.1988.23887.
[37] Anthony Zaknich, A Modified Probabilistic Neural Network for Nonlinear Time Series Analysis, CH 3065-0/91/0000-1530$1.00@IEEE.
[38] L. Anagnostopoulos, Classifying Web pages employing a probabilistic neural network, IEEE, 2004.
[39] 余丙星, 小波分析在海洛因吸毒者脉象信号中的应用, 重庆大学硕士学位论文, 2006.
[40] 胡光强, 浅析脉象产生机制及其解剖生理学基础, 现代中西医结合杂志, 2004 年 7 月.
[41] 王明三, 论脉象的绝对性与相对性, 山东中医药大学学报, 2004 年 7 月.
[42] 李景唐, 中医脉象的客观检测和描述, 医疗设备 2005 第 5 期.
[43] 张丽琼, 基于小波变换的脉象信号特征提取方法, 数据采集与处理, 2004 年 9 月.
[44] 杨丽娟, 脉象信号的特征提取, 黑龙江医药, VOL.18 NO.6, 2005.
[45] 岳沛平, 基于小波变换的中医脉象信号的特征提取与分析, 医疗卫生装备, 2006 年第 27卷第一期.
[46] 杨丽娟等, 基于小波包分析和 BP 神经网络的中医脉象识别方法, 计算机应用研究, 2006年
[47] 王燕等, 基于小波模极大原理的脉象特征提取研究, 航天医学与医学工程, 第 19 卷第 1期, 2006 年 2 月.
[48] 柯学尧等, 用驻波观点研究脉和脉象的产生机制, 中国中医药信息杂志, 2006年6月第13卷第 6 期.
[49] 岳沛平等, 小波变换在中医脉象信号特征分析中的应用, 南京中医药大学学报 2005 年 11月第 21 卷第 6 期.
[50] 程荣朵, 简析常见脉象特点及临床意义, 陕西中医 2005 年第 26 卷第 6 期.
[51] Yue Wang, Quantification and Segmentation of Brain Tissues from MR Images: A Probabilistic Neural Network Approach IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL.7,NO.8, AUGUST 1998.
[52] P.P.Raghu, Supervised Texture Classification Using a Probabilistic Neural Network and Constraint Satisfaction Modes, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.9,NO.3, MAY 1998.
[53] K.Z.Mao, Probabilistic Neural-Network Structure Determination for Pattern Classification, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.11,NO.4, MAY 2000.
[54] Anthony Zaknich, Introduction to the Modified Probabilistic Neural Network for General Signal Processing Applications, IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL.46, NO.7, JULY 1998.
[55] Xin Jin, Classification of Freeway Traffic Patterns for Incident Detection Using Constructive Probabilistic Neural Networks, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.12,NO.5, MAY 2001.
[56] DONALD F.SPECHT, Probabilistic Neural Networks and the Polynomial Adaline as Complementary Techniques for Classification, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.1,NO.1, MAY 1990.
[57] 王炳和, 基于 AR 模型的人体脉象信号模糊聚类研究, 应用声学, 20 卷 5 期(2001).
[2] 飞思科技产品研发中心编著. 小波分析理论与实现. 电子工业出版社. 2005
[3] 费兆馥,张志枫.中医脉诊的图像化和定量化.自然杂志,1995,Vol.17, No.5:269-274.
[4] 王丽勤.中医诊寸口脉的历史和体会.北京医科大学学报,1994, Vol.26, No.1:55-57.
[5] 杨福生,高上凯.生物医学信号处理.高等教育出版社,1989.
[6] 唐晓初.小波分析及其应用.重庆大学光电工程学院,2003..
[7] 许东.基于 MATLAB6.X 的系统分析与设计—神经网络 西安电子科技大学出版社 2002
[8] Simmon Haykin Neural networks China Machine Press 2004.
[9] 张力.脉诊研究进展.山东中医学院学报,1995,Vol.19, No.4:281-284.
[10] 王崇骏.人工智能理论研究及测控技术在中医脉象辨识中的应用.河海大学硕士论文,2001.
[11] 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. 重庆大学硕士学位论文,2000.
[12] 冯月明.基于小波分析的海量图像管理与发布方法及其系统实现.西安电子科技大学硕士论文,2003.
[13] 王颖东. 基于小波分析的电路故障诊断技术研究,华中科技大学硕士论文,2003
[14] 徐凌.基于小波分析的网络业务的研究,天津大学硕士论文,2003
[15] 许刚.基于小波分析的视频图象编码研究,中国科学院软件研究所博士后论文,1999
[16] 曹茂森.基于动力指纹小波分析的结构损伤特征提取与辨识基本问题研究,河海大学博士论文,2005
[17] 赵温波.径向基概率神经网络研究,中国科技大学博士论文,2003
[18] 徐旺林.概率神经网络及其在地球物理勘探中的应用,兰州大学硕士论文,2003
[19] 杨晓楠.基于概率神经网络与小波变换的结构检测方法研究,沈阳建筑大学硕士论文,2004
[20] 张卫东.基于概率神经网络的鲁棒性云检测研究,青岛海洋大学博士论文,2001
[21] Donald B.Percival Wavelet Methods for Time Series Analysis China Machine Press 2004
[22] D Veitch, M S Taqqu, P Abry. Meaningful MRA initialization for discrete time series. Signal Processing 80,2000:1971-1983.
[23] D Labata, R Ababoua, A Manginb. Rainfall–runoff relations for karstic springs. Part II: continuous wavelet and discrete orthogonal multiresolution analyses, Journal of Hydrology 238,2000:149-178.
[24] J.Martinez-Alajarin, Wavelet and Wavelet Packet Compression of Phonocardiograms,ELECTRONICS LETTERS 19th August 2004 Vol.40 No.17.
[25] D K Hoffman, D J Kouri. Shannon–Gabor wavelet distributed approximating functional. Chemical Physics Letters 287,1998:119–124.
[26] W.P.Sweeney Jr. PROBABILISTIC NEURAL NETWORK AS CHROMOSOME CLASSIFIER, Proceeding of 1993 International Joint Conference on Neural Networks.
[27] Stephane G Mallat. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,1989,VOL.II,NO.7:674-693.
[28] M.T.Musavi, IMPROVING THE PERFORMANCE OF PROBABILISTIC NEURAL NETWORKS,0-7803-0559-0/92 $3.00@1992 IEEE.
[29] M Maslen, P Abbott. Automation of the lifting factorisation of wavelet transforms. Computer Physics Communications 127,2000:309–326
[30] 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.重庆大学硕士学位论文,2000.
[31] R G Lueck,F R Driscoll,M Nahon. A wavelet for predicting the time-domain response of vertically tethered systems. Ocean Engineering 27,2000: 1441–1453.
[32] Umberto Amato, Claudia Angelini, Carmine Serio. Compression of AVHRR images by wavelet packets. Environmental Modelling & Software 15,2000:127–138.
[33] L-K.Shark and D.Qi, Approach to Wavelet Transform Implementation: Wavelet-like filter banks, ELECTRONICS LETTERS 20th November 1997 Vol.33 No.24
[34] Leszek Rutkowski,Adaptive Probabilistic Neural Networks for Pattern Classification in Time-Varying Environment, 1045-9227/04$20.00@2004 IEEE.
[35] Fabio Ancona, Anna Marai Colla, Implementing Probabilistic Neural Networks, Neural Computing&Applic(1997)5:152~159.
[36] Donald F.specht Probabilistic Neural Network for Classification, Mapping, or Associative Memory, Digital Object Identifier 10.1109ACNN.1988.23887.
[37] Anthony Zaknich, A Modified Probabilistic Neural Network for Nonlinear Time Series Analysis, CH 3065-0/91/0000-1530$1.00@IEEE.
[38] L. Anagnostopoulos, Classifying Web pages employing a probabilistic neural network, IEEE, 2004.
[39] 余丙星, 小波分析在海洛因吸毒者脉象信号中的应用, 重庆大学硕士学位论文, 2006.
[40] 胡光强, 浅析脉象产生机制及其解剖生理学基础, 现代中西医结合杂志, 2004 年 7 月.
[41] 王明三, 论脉象的绝对性与相对性, 山东中医药大学学报, 2004 年 7 月.
[42] 李景唐, 中医脉象的客观检测和描述, 医疗设备 2005 第 5 期.
[43] 张丽琼, 基于小波变换的脉象信号特征提取方法, 数据采集与处理, 2004 年 9 月.
[44] 杨丽娟, 脉象信号的特征提取, 黑龙江医药, VOL.18 NO.6, 2005.
[45] 岳沛平, 基于小波变换的中医脉象信号的特征提取与分析, 医疗卫生装备, 2006 年第 27卷第一期.
[46] 杨丽娟等, 基于小波包分析和 BP 神经网络的中医脉象识别方法, 计算机应用研究, 2006年
[47] 王燕等, 基于小波模极大原理的脉象特征提取研究, 航天医学与医学工程, 第 19 卷第 1期, 2006 年 2 月.
[48] 柯学尧等, 用驻波观点研究脉和脉象的产生机制, 中国中医药信息杂志, 2006年6月第13卷第 6 期.
[49] 岳沛平等, 小波变换在中医脉象信号特征分析中的应用, 南京中医药大学学报 2005 年 11月第 21 卷第 6 期.
[50] 程荣朵, 简析常见脉象特点及临床意义, 陕西中医 2005 年第 26 卷第 6 期.
[51] Yue Wang, Quantification and Segmentation of Brain Tissues from MR Images: A Probabilistic Neural Network Approach IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL.7,NO.8, AUGUST 1998.
[52] P.P.Raghu, Supervised Texture Classification Using a Probabilistic Neural Network and Constraint Satisfaction Modes, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.9,NO.3, MAY 1998.
[53] K.Z.Mao, Probabilistic Neural-Network Structure Determination for Pattern Classification, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.11,NO.4, MAY 2000.
[54] Anthony Zaknich, Introduction to the Modified Probabilistic Neural Network for General Signal Processing Applications, IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL.46, NO.7, JULY 1998.
[55] Xin Jin, Classification of Freeway Traffic Patterns for Incident Detection Using Constructive Probabilistic Neural Networks, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.12,NO.5, MAY 2001.
[56] DONALD F.SPECHT, Probabilistic Neural Networks and the Polynomial Adaline as Complementary Techniques for Classification, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL.1,NO.1, MAY 1990.
[57] 王炳和, 基于 AR 模型的人体脉象信号模糊聚类研究, 应用声学, 20 卷 5 期(2001).