脉象信号人工智能辨识
|
摘要
脉诊在中医理论与临床诊断中都占有很重要的地位,运用数学分析法判别脉象是近代中医学研究的重要课题之一。本文以中医脉象人工智能辩识的研究与开发为背景,对脉象信号的分析和识别做了研究和探讨。传统的脉象图形数学分析法为时域分析法,对时域内脉象图的特征形参数进行分析研究,寻找出了部分中医脉象的参数定义,解释与疾病的关系。本文将小波分析理论应用于脉象信号的分析和处理,讨论了小波变换对脉象信号除噪的效果,利用小波分析所具有良好的时-频同时局部化的能力和对非平稳信号突变点的检测能力对脉象信号进行了分析和时域特征值的提取,并提取了脉象信号的小波变换在不同尺度上的能量这一新的表征脉象的特征参数。在此基础上提出了利用BP神经网络对健康人和脑血管病人脉象信号进行分类,比较了以脉象信号的频谱能量和以其小波变换高频部分d6尺度上的能量为神经网络输入时的训练结果的差异。尽管文中的训练样本有限,但仿真结果表明:对脉象信号的一些特定的特征值(如原始信号的小波变换在不同尺度上的能量),利用神经网络进行识别是一种可行而有效的方法。最后介绍了基于DSP的脉象信号采集系统的设计。
Diagnosis based on pulse tracings plays an important part both in theory and in clinical traditional Chinese medicine. Signal processing and pattern recognition of Human Pulse are studied and discussed in this thesis on the basis of the research and development of AI recognition system for Human Pulse. The traditional mathematical analysis of pulse tracing graph is a time domain analysis that found part parameters defining traditional Chinese medicine pulse tracings and interpreted the relation between pulse tracings and disease of entrails. As for the periodicity of pulse tracing signals, frequency domain analysis has been used. Based on the characteristics of Human Pulse, Wavelet Transform (WT) is originally used to process and analysis it. Wavelet analysis has a good qualities both in time domain and frequency domain and is an ideal tool in analyzing unsteady signal,so it is used to detect the singularity of Human Pulse and extract the features of Human Pulse in time-domain. Human Pulse is characterized by a new feature, which is the energy of its wavelet transform in different scales. BP Neural Network is used to classify the Human Pulse between health and Cerebrovascular Disease (CVD) according to its spectra features and new features extracted on d6 by Wavelet Transform. The results show that different inputs of features will lead to different outcomes of pattern recognition. In spite of limited training samples, the method in this thesis is superior to traditional Pattern Recognition methods if choose suitable features to be input-cell such as features extracted by Wavelet Transform. A data processing system base on DSP is designed according to the new characteristics.
Diagnosis based on pulse tracings plays an important part both in theory and in clinical traditional Chinese medicine. Signal processing and pattern recognition of Human Pulse are studied and discussed in this thesis on the basis of the research and development of AI recognition system for Human Pulse. The traditional mathematical analysis of pulse tracing graph is a time domain analysis that found part parameters defining traditional Chinese medicine pulse tracings and interpreted the relation between pulse tracings and disease of entrails. As for the periodicity of pulse tracing signals, frequency domain analysis has been used. Based on the characteristics of Human Pulse, Wavelet Transform (WT) is originally used to process and analysis it. Wavelet analysis has a good qualities both in time domain and frequency domain and is an ideal tool in analyzing unsteady signal,so it is used to detect the singularity of Human Pulse and extract the features of Human Pulse in time-domain. Human Pulse is characterized by a new feature, which is the energy of its wavelet transform in different scales. BP Neural Network is used to classify the Human Pulse between health and Cerebrovascular Disease (CVD) according to its spectra features and new features extracted on d6 by Wavelet Transform. The results show that different inputs of features will lead to different outcomes of pattern recognition. In spite of limited training samples, the method in this thesis is superior to traditional Pattern Recognition methods if choose suitable features to be input-cell such as features extracted by Wavelet Transform. A data processing system base on DSP is designed according to the new characteristics.
引文
1 王新华.中医基础理论.北京:人民卫生出版社,2001:1-27
2 田合禄,田蔚.中医运气学解秘.太原:山西科学技术出版社,2002:1-33
3 李任先.中医内科五脏病学.广州:广东科技出版社,2001:21-27
4 天津中医学院.脏腑经络学说.天津:天津科学技术出版社,1988:1-73
5 祝世讷,陈少宗.中医系统论与系统工程学.北京:中国医药科技出版社,2002:20-22
6 董连荣,谢路山.中医基础理论.北京:中国工人出版社,1998:18-25
7 欧阳兵.中医诊法学.北京:中国医药科技出版社,2002:5-24
8 乔模.四诊歌诀.太原:山西科学技术出版社,2003:1-22
9 刘晋平,李慧吉.试论中西医理论结合研究.天津中医药,2005,2:5-37
10 张文康.中西医结合医学.北京:中国中医药出版社,2000:1-14
11 祝世讷 .中西医结合临床研究思路与方法学 . 北京 : 中国医药科技出版社 , 2002:13-37
12 杨在纲,王承炎.中医诊断学.北京:中医古籍出版社,2002:25-32
13 李冰星,宋文锋.中医脉诊研究思考.中国中医基础医学杂志,1998,4(6):21-35
14 M. Voelg. Measurement of the Blood-pressure Constant Cover a Pressure Range in the Canine Radial Artery.Med.&Biol.Eng.&Comput,1981(19):535-537
15 刘梅,郝小梅.中医脉诊客观化研究新探.中医函授通讯,2000, 19(2):9-11
16 费兆馥.现代中医脉诊学.北京:人民卫生出版社,2003:18-112
17 黄世林,孙明异.中医脉象研究.北京:人民卫生出版社,1986: 25-32
18 何素荣,刘世斌.临床脉图诊断学.北京:人民军医出版社,2003:32-81
19 张松,杨文鸣,杨子彬.脉搏波波形特征信息的研究.北京工大学报,1996,22(1):71-74
20 张力,脉诊研究进展.山东中医学院学报,1995,19(4):281-284.
21 Akimitsu Harada, Takashi Okada. New Methods of One-point Measurement of Pulse Wave Velocity. IEEE,2002:5-37
22 张镜人.脉搏线性化理论对正常人挠动脉买图和脉象的分析.中国生物医学工程学报,1987,6(1):58
23 费兆馥,张志枫.中医脉诊的图象化和定量化.自然杂志科技展,2003,7(5):235-237
24 姜涛.基于小波分析的中医脉象的识别研究.[河海大学硕士毕业论文].2003:6-7
25 王 滨 , 牛 欣 . 现 代 脉 诊 研 究 的 问 题 及 解 决 之 道 . 中 国 中 医 基 础 医 学 杂志,2005,l1(4):246-248
26 费兆馥.中国脉诊研究.上海:上海中医学院出版社,1991:78-132
27 蔡临宁.中华脉诊.北京:中国中医药出版社,2002:80-192
28 杨天权.中医脉学应用新进展.上海:上海交通大学出版社,1994:2-102
29 徐洪文.脉象图与脉诊客观化.山东中医学院学报,1993,17(2):12-13
30 郝敬尧.脉搏波的频谱分析.力学与实践,1980,2:54-56
31 柴新禹,吴朝霞.时频分析方法及其在医学信号处理中的应用.生物医学工程学杂志,2001,18(1):138-144
32 朱安娜.脉象信息和模糊识别.上海市脉象研究资料汇编,1983:83
33 冉启文.小波变换与分数傅里叶变换理论及应用.哈尔滨:哈尔滨工业大学出版社,2001:5-180
34 N Ronald. Bracewell. The Fourier Transform and Applications. McGraw-Hill Capanise,2000:55-71
35 L.科恩著,白居宪译.时-频分析理论与应用.西安:西安交通大学出版社,1998:81-87
36 D. E. Bedford. The Ancient Art of Feeling the Pulse. British Heart,1951,13(4):423
37 文成林,周东华.多尺度估计理论及其应用.北京:清华大学出版社,2002:1-77
38 柳兆荣.脉图与脉象的生物力学描述.力学进展,1986,11(2):11
39 孙铭.脉诊客观化研究方法探讨.北京生物医学工程,1996,15(3):170-173
40 E. Z. ahediet. Graphical Simulation of Artificial Hand Motion with Fuzzy EMG pattern recognition [J]. Proceedings RC IEEE-EMBS&14th BMESI,1995,3:43-44
41 罗志昌,张松,杨易民.脉搏波的工程分析与临床应用.北京:科学出版社,2006:35-70
42 A. A. Bharath, J. A. Ng. Steerable.Complex Wavelet Construction and Its Application to Image Denoising. IEEE Transactions on Image Processing,2005,14(7):48-59
43 S. Mallat, S. Zhong. Characterization of Signal from Multiscale Edges. IEEE Trans, 1992,14(7):710-732
44 S. Mallat.信号处理的小波导引.杨力华.北京:机械工业出社,2002:1-345
45 S. Mallat, W. L. Hwang. Singularity Detection and Processing with Wavelets. IEEE Transactions on Information Theory,1992,38(2):617-643
46 N. Aydin, F. Marvasti, H. S. Markus. Embolic Doppler Ultrasound Signal Detection Using Discrete Wavelet Transform. IEEE Transactions on Information Technology in Biomedicine,2004,8(2):182-190
47 M. Akey, Y. M. Akay. Investigating the Effects of Vasodilator Dungs on the Turblents Sound Caused by Efmoral Artery Stenosis Using Short-term Fourier and Wavelet Transform Methods.IEEE Biomedical Egineering,1994,10:921-928
48 Tai-ChicH Sung, Lun. Denoising by Singularity Detection. IEEE Transactions on Signal Processing,1999,47(11):3139-3144
49 I. Daubechies S. The wavelet Transform Time-Frequency Localization and Signal Analysis. IEEE Transacting on Information Theory,1990,l(36):961-1005
50 C Kok-Wui, J. M. Ciofi. Discrete Wavelet Transforms in Multi-carrier Modulation. IEEE Global Telecommunications Conference,1998,(5):2794-2799
51 G. W. Womell, A. V. Oppenheim. Wavelet-based Representations for a Class of Self-similar Signals with Application to Fractal Modulation. IEEE Transactions on Information Theory,1992,38(2):785-800
52 K. C. Ho, W. Prokopiw, Y. T. Chan. Modulation Identification by the Wavelet Transform. IEEE Military Communications Conference,1995,2:886-890
53 Y. T. Chan, J. W. Plews, K. C. Ho. Symbol Rate Estimation by the Wavelet Transform. IEEE International Symposium on Circuits and Systems,1997,l:177-180
54 S. G. Chang, Yu Bin, M. Vetterli. Adaptive Wavelet Thresholding for Image Denoising and Compression. IEEE Transactions on Image Processing,2000,9(9): 1532-1546
55 D. L. Donoho. De-noising by Soft Thresholding, IEEE Trans on Information Theory, 1995,41(3):613-627
56 Q. Pan, L. Zhang, G. Dai. Two Denoising Methods by Wavelet Transform. IEEE Trans,1999,47(12):3401-3406
57 K. Chen, L. Wang. Methods of Combining Multiple classifiers with Different Featuresand Their Applications to Text-independent Speaker Identification Pattern Recongition and Artificial Intellingence,1997,11(3):417-445
58 M. Ahmadi, M. Shridhar. Recognition of Handwritten Numerals with Multiple Feature and Multistage Classifier. Pattern Recognition,1995,28(2):153-160
59 R. Bajaj, S. Chaudhury. Signature Verification Using Multiple Neural Classifiers [J]. Pattern Recongnition,1997,30(1):1-7
60 白玉峰,罗志昌.逐步Bayes判别分析在心血管功能评定中的应用.北京工业大学学报,1994,20(1):54-60
61 L. Ohno-Machado, M. Musen. Sequential Versus Standard Neural Networks for Pattern Recognition an Example Using the Domain of Coronary Heart Disease. Comput Biol Med,1997:267-281
62 彭承琳.生物医学传感器原理及应用.北京:高等教育出版社,2000:55-78
63 王保华.生物医学测量与仪器.上海:复旦大学出版社,2003:40-56
64 马明建.数据采集与处理技术.西安:西安交通大学出版社,2002:8-10
65 刘和平,王维俊,江渝.TMS320LF240 DSP C 语言开发应用.北京:北京航空航天大学出版社,2003:30-35
66 江思敏.TMS320LF240xDSP硬件开发教程.北京:机械工业出版社,2003: 23-30
67 童诗白.模拟电子技术基础[M]. 北京:高等教育出版社,1988:445-487
68 陆坤.电子设计技术.北京:电子科技大学出版社,1997:1-56
69 姚成,吴小培.小波变换与生物医学信号处理.生物学杂志,2000,17(1):24-26
2 田合禄,田蔚.中医运气学解秘.太原:山西科学技术出版社,2002:1-33
3 李任先.中医内科五脏病学.广州:广东科技出版社,2001:21-27
4 天津中医学院.脏腑经络学说.天津:天津科学技术出版社,1988:1-73
5 祝世讷,陈少宗.中医系统论与系统工程学.北京:中国医药科技出版社,2002:20-22
6 董连荣,谢路山.中医基础理论.北京:中国工人出版社,1998:18-25
7 欧阳兵.中医诊法学.北京:中国医药科技出版社,2002:5-24
8 乔模.四诊歌诀.太原:山西科学技术出版社,2003:1-22
9 刘晋平,李慧吉.试论中西医理论结合研究.天津中医药,2005,2:5-37
10 张文康.中西医结合医学.北京:中国中医药出版社,2000:1-14
11 祝世讷 .中西医结合临床研究思路与方法学 . 北京 : 中国医药科技出版社 , 2002:13-37
12 杨在纲,王承炎.中医诊断学.北京:中医古籍出版社,2002:25-32
13 李冰星,宋文锋.中医脉诊研究思考.中国中医基础医学杂志,1998,4(6):21-35
14 M. Voelg. Measurement of the Blood-pressure Constant Cover a Pressure Range in the Canine Radial Artery.Med.&Biol.Eng.&Comput,1981(19):535-537
15 刘梅,郝小梅.中医脉诊客观化研究新探.中医函授通讯,2000, 19(2):9-11
16 费兆馥.现代中医脉诊学.北京:人民卫生出版社,2003:18-112
17 黄世林,孙明异.中医脉象研究.北京:人民卫生出版社,1986: 25-32
18 何素荣,刘世斌.临床脉图诊断学.北京:人民军医出版社,2003:32-81
19 张松,杨文鸣,杨子彬.脉搏波波形特征信息的研究.北京工大学报,1996,22(1):71-74
20 张力,脉诊研究进展.山东中医学院学报,1995,19(4):281-284.
21 Akimitsu Harada, Takashi Okada. New Methods of One-point Measurement of Pulse Wave Velocity. IEEE,2002:5-37
22 张镜人.脉搏线性化理论对正常人挠动脉买图和脉象的分析.中国生物医学工程学报,1987,6(1):58
23 费兆馥,张志枫.中医脉诊的图象化和定量化.自然杂志科技展,2003,7(5):235-237
24 姜涛.基于小波分析的中医脉象的识别研究.[河海大学硕士毕业论文].2003:6-7
25 王 滨 , 牛 欣 . 现 代 脉 诊 研 究 的 问 题 及 解 决 之 道 . 中 国 中 医 基 础 医 学 杂志,2005,l1(4):246-248
26 费兆馥.中国脉诊研究.上海:上海中医学院出版社,1991:78-132
27 蔡临宁.中华脉诊.北京:中国中医药出版社,2002:80-192
28 杨天权.中医脉学应用新进展.上海:上海交通大学出版社,1994:2-102
29 徐洪文.脉象图与脉诊客观化.山东中医学院学报,1993,17(2):12-13
30 郝敬尧.脉搏波的频谱分析.力学与实践,1980,2:54-56
31 柴新禹,吴朝霞.时频分析方法及其在医学信号处理中的应用.生物医学工程学杂志,2001,18(1):138-144
32 朱安娜.脉象信息和模糊识别.上海市脉象研究资料汇编,1983:83
33 冉启文.小波变换与分数傅里叶变换理论及应用.哈尔滨:哈尔滨工业大学出版社,2001:5-180
34 N Ronald. Bracewell. The Fourier Transform and Applications. McGraw-Hill Capanise,2000:55-71
35 L.科恩著,白居宪译.时-频分析理论与应用.西安:西安交通大学出版社,1998:81-87
36 D. E. Bedford. The Ancient Art of Feeling the Pulse. British Heart,1951,13(4):423
37 文成林,周东华.多尺度估计理论及其应用.北京:清华大学出版社,2002:1-77
38 柳兆荣.脉图与脉象的生物力学描述.力学进展,1986,11(2):11
39 孙铭.脉诊客观化研究方法探讨.北京生物医学工程,1996,15(3):170-173
40 E. Z. ahediet. Graphical Simulation of Artificial Hand Motion with Fuzzy EMG pattern recognition [J]. Proceedings RC IEEE-EMBS&14th BMESI,1995,3:43-44
41 罗志昌,张松,杨易民.脉搏波的工程分析与临床应用.北京:科学出版社,2006:35-70
42 A. A. Bharath, J. A. Ng. Steerable.Complex Wavelet Construction and Its Application to Image Denoising. IEEE Transactions on Image Processing,2005,14(7):48-59
43 S. Mallat, S. Zhong. Characterization of Signal from Multiscale Edges. IEEE Trans, 1992,14(7):710-732
44 S. Mallat.信号处理的小波导引.杨力华.北京:机械工业出社,2002:1-345
45 S. Mallat, W. L. Hwang. Singularity Detection and Processing with Wavelets. IEEE Transactions on Information Theory,1992,38(2):617-643
46 N. Aydin, F. Marvasti, H. S. Markus. Embolic Doppler Ultrasound Signal Detection Using Discrete Wavelet Transform. IEEE Transactions on Information Technology in Biomedicine,2004,8(2):182-190
47 M. Akey, Y. M. Akay. Investigating the Effects of Vasodilator Dungs on the Turblents Sound Caused by Efmoral Artery Stenosis Using Short-term Fourier and Wavelet Transform Methods.IEEE Biomedical Egineering,1994,10:921-928
48 Tai-ChicH Sung, Lun. Denoising by Singularity Detection. IEEE Transactions on Signal Processing,1999,47(11):3139-3144
49 I. Daubechies S. The wavelet Transform Time-Frequency Localization and Signal Analysis. IEEE Transacting on Information Theory,1990,l(36):961-1005
50 C Kok-Wui, J. M. Ciofi. Discrete Wavelet Transforms in Multi-carrier Modulation. IEEE Global Telecommunications Conference,1998,(5):2794-2799
51 G. W. Womell, A. V. Oppenheim. Wavelet-based Representations for a Class of Self-similar Signals with Application to Fractal Modulation. IEEE Transactions on Information Theory,1992,38(2):785-800
52 K. C. Ho, W. Prokopiw, Y. T. Chan. Modulation Identification by the Wavelet Transform. IEEE Military Communications Conference,1995,2:886-890
53 Y. T. Chan, J. W. Plews, K. C. Ho. Symbol Rate Estimation by the Wavelet Transform. IEEE International Symposium on Circuits and Systems,1997,l:177-180
54 S. G. Chang, Yu Bin, M. Vetterli. Adaptive Wavelet Thresholding for Image Denoising and Compression. IEEE Transactions on Image Processing,2000,9(9): 1532-1546
55 D. L. Donoho. De-noising by Soft Thresholding, IEEE Trans on Information Theory, 1995,41(3):613-627
56 Q. Pan, L. Zhang, G. Dai. Two Denoising Methods by Wavelet Transform. IEEE Trans,1999,47(12):3401-3406
57 K. Chen, L. Wang. Methods of Combining Multiple classifiers with Different Featuresand Their Applications to Text-independent Speaker Identification Pattern Recongition and Artificial Intellingence,1997,11(3):417-445
58 M. Ahmadi, M. Shridhar. Recognition of Handwritten Numerals with Multiple Feature and Multistage Classifier. Pattern Recognition,1995,28(2):153-160
59 R. Bajaj, S. Chaudhury. Signature Verification Using Multiple Neural Classifiers [J]. Pattern Recongnition,1997,30(1):1-7
60 白玉峰,罗志昌.逐步Bayes判别分析在心血管功能评定中的应用.北京工业大学学报,1994,20(1):54-60
61 L. Ohno-Machado, M. Musen. Sequential Versus Standard Neural Networks for Pattern Recognition an Example Using the Domain of Coronary Heart Disease. Comput Biol Med,1997:267-281
62 彭承琳.生物医学传感器原理及应用.北京:高等教育出版社,2000:55-78
63 王保华.生物医学测量与仪器.上海:复旦大学出版社,2003:40-56
64 马明建.数据采集与处理技术.西安:西安交通大学出版社,2002:8-10
65 刘和平,王维俊,江渝.TMS320LF240 DSP C 语言开发应用.北京:北京航空航天大学出版社,2003:30-35
66 江思敏.TMS320LF240xDSP硬件开发教程.北京:机械工业出版社,2003: 23-30
67 童诗白.模拟电子技术基础[M]. 北京:高等教育出版社,1988:445-487
68 陆坤.电子设计技术.北京:电子科技大学出版社,1997:1-56
69 姚成,吴小培.小波变换与生物医学信号处理.生物学杂志,2000,17(1):24-26