基于TM_EMD的脉搏信号多模态特征情感识别方法
|
摘要
作为涉及多领域知识的跨学科的综合类课题,情感研究目前已成为心理学、计算机科学以及医学界广泛关注的热点,它具有高度的综合性以及实际应用价值。基于生理信号的情感研究是当前心理学及医学研究领域较为新颖的课题。脉搏作为人体一种常见的生理特征,其在心脏及动脉血管系统的相互影响下能够反映动脉血压的变化情况,并且与人体的健康状况密切相关。通过提取脉搏信号不同特征来分析和辨别不同情感状态的研究可以为临床医学、社会科学以及工程应用提供理论依据与实践基础。
本研究在现有生理特征情感识别研究的基础上,针对现有生理信号情感识别方法中存在的不足,提出了一种新的基于脉搏信号的情感识别方法。该方法通过提取脉搏信号的频谱特征、非线性特征和经验模态分解特征来辨别个体的不同情感状态。实验结果表明该方法对于所研究的四种基本情感状态具有较高的识别率。具体内容如下：
(1)根据脉搏信号产生的生理学机理,详细分析了脉搏信号情感识别研究的可行性。脉搏作为人体的一种生理特征,其变化不受人的主观意识控制,能够客观地反映个体的情感状态。另外,脉搏信号具有采集过程简单、信号易处理等优势。
(2)分析小波变换理论,结合脉搏信号在采集过程中存在的噪声类型,选用db5小波对脉搏信号进行去噪处理。对于脉搏信号的低频噪声,采用近似分量置零操作；对于脉搏信号高频噪声,采用改进的阈值处理方法,然后用处理后的小波分解系数重构脉搏信号。
(3)将经验模态分解算法引入到脉搏信号情感识别研究中,针对该算法在信号分解过程中存在的端点效应提出了种改善方法。该方法首先利用信号相干平均技术获取脉搏信号模板,然后将信号端点处的数据与模板匹配,将原始信号延拓至整周期,最后利用镜像延拓法对延拓后的信号进行经验模态分解。
(4)本研究将通过经验模态分解得到的模态能量商以及脉搏信号非线性特征和频谱特征融合应用于脉搏情感识别研究中,探讨了不同情感状态下脉搏信号对应的特征信息。给出了三种特征信息的提取方法,并实现脉搏信号有效特征的提取。
(5)为完成不同情感状态的自动判别,本研究构造了一种基于支持向量机多分类方法,对80个样本(快乐状态20例,愉悦状态20例,悲伤状态20例,愤怒状态20例)的脉搏信号进行情感状态自动判别分析,实验结果表明本文选取的脉搏信号多模态特征信息组合对于情感状态识别效果更佳
Emotion research as a comprehensive topic involving many different fields of knowledge has attracted widely attention in Psychology, Computer science and Medical field. It has the highly integration and practical value. Emotion research based on physiological signals is a novel topic in the field of Psychology and Medical. Pulse as a common physiological feature reflects the arterial pressure changes under the interaction of heart and arterial vascular system and also closed related to the health status. The difference character of pulse signals can be used to analyze and recognize vary emotion status, it is as a research can provide the basis of clinical medicine, social science and engineering application.
This research is based on previous study, it puts forward a new emotion recognition method due to the deficiencies existing current emotion recognition method. It can recognize the different emotion states of individual by the extracting the spectrum character, nonlinear character and empirical mode decomposition character. It proves to be that this method has the higher recognition rate. More details as below:
(1) It analyzes the feasibility of pulse signal-emotion recognition research in details according to the physiological mechanism generated by pulse signal. Pulse as a physiological feature can not be controlled subjectively and can reflect emotion objectively. In addition, pulse signals have the advantages of simple collecting and easy processing.
(2) Analyzing wavelet conversion theory:remove the noise exist in the pulse signals by db5wavelet combing with the noise type in the acquisition process of pulse signals. Low-frequency noise from pulse signal processes by approximate component zero setting and high-frequency noise from pulse signal by improved threshold value and then rebuilds pulse signals by wavelet coefficients.
(3) Empirical mode decomposition algorithm is introduced to the pulse signal emotion recognition study; it comes up with an improved method in the terms of endpoint effect in the process of signal decomposition. This method first takes use of signal coherent averaging technique to obtain the pulse signal template and then match the data located the endpoint with template extending original signal to the whole cycle; at last compose the extended signal in the empirical mode by Mirror extension method.
(4) This study integrates EMD generated by Empirical mode decomposition and nonlinear and spectrum character of pulse signal and then apply to the pulse-emotion recognition research discussing different pulse signal reflected by different emotions。 Gained the extraction methods of three types of certain character information and released the extraction of pulse signal effective character.
(5) This study also constructed Multi-classification based on supporting Vector Machine in order to fulfill auto-recognition of different emotion. Extract pulse signal from80samples(20samples of states of happiness,20samples of states of pleasure,20samples of states of sadness,20samples of states of anger) to do auto-recognition analysis and it proves that combination of pulse signal multi-mode character information is a more efficient way to emotion recognition.
本研究在现有生理特征情感识别研究的基础上,针对现有生理信号情感识别方法中存在的不足,提出了一种新的基于脉搏信号的情感识别方法。该方法通过提取脉搏信号的频谱特征、非线性特征和经验模态分解特征来辨别个体的不同情感状态。实验结果表明该方法对于所研究的四种基本情感状态具有较高的识别率。具体内容如下：
(1)根据脉搏信号产生的生理学机理,详细分析了脉搏信号情感识别研究的可行性。脉搏作为人体的一种生理特征,其变化不受人的主观意识控制,能够客观地反映个体的情感状态。另外,脉搏信号具有采集过程简单、信号易处理等优势。
(2)分析小波变换理论,结合脉搏信号在采集过程中存在的噪声类型,选用db5小波对脉搏信号进行去噪处理。对于脉搏信号的低频噪声,采用近似分量置零操作；对于脉搏信号高频噪声,采用改进的阈值处理方法,然后用处理后的小波分解系数重构脉搏信号。
(3)将经验模态分解算法引入到脉搏信号情感识别研究中,针对该算法在信号分解过程中存在的端点效应提出了种改善方法。该方法首先利用信号相干平均技术获取脉搏信号模板,然后将信号端点处的数据与模板匹配,将原始信号延拓至整周期,最后利用镜像延拓法对延拓后的信号进行经验模态分解。
(4)本研究将通过经验模态分解得到的模态能量商以及脉搏信号非线性特征和频谱特征融合应用于脉搏情感识别研究中,探讨了不同情感状态下脉搏信号对应的特征信息。给出了三种特征信息的提取方法,并实现脉搏信号有效特征的提取。
(5)为完成不同情感状态的自动判别,本研究构造了一种基于支持向量机多分类方法,对80个样本(快乐状态20例,愉悦状态20例,悲伤状态20例,愤怒状态20例)的脉搏信号进行情感状态自动判别分析,实验结果表明本文选取的脉搏信号多模态特征信息组合对于情感状态识别效果更佳
Emotion research as a comprehensive topic involving many different fields of knowledge has attracted widely attention in Psychology, Computer science and Medical field. It has the highly integration and practical value. Emotion research based on physiological signals is a novel topic in the field of Psychology and Medical. Pulse as a common physiological feature reflects the arterial pressure changes under the interaction of heart and arterial vascular system and also closed related to the health status. The difference character of pulse signals can be used to analyze and recognize vary emotion status, it is as a research can provide the basis of clinical medicine, social science and engineering application.
This research is based on previous study, it puts forward a new emotion recognition method due to the deficiencies existing current emotion recognition method. It can recognize the different emotion states of individual by the extracting the spectrum character, nonlinear character and empirical mode decomposition character. It proves to be that this method has the higher recognition rate. More details as below:
(1) It analyzes the feasibility of pulse signal-emotion recognition research in details according to the physiological mechanism generated by pulse signal. Pulse as a physiological feature can not be controlled subjectively and can reflect emotion objectively. In addition, pulse signals have the advantages of simple collecting and easy processing.
(2) Analyzing wavelet conversion theory:remove the noise exist in the pulse signals by db5wavelet combing with the noise type in the acquisition process of pulse signals. Low-frequency noise from pulse signal processes by approximate component zero setting and high-frequency noise from pulse signal by improved threshold value and then rebuilds pulse signals by wavelet coefficients.
(3) Empirical mode decomposition algorithm is introduced to the pulse signal emotion recognition study; it comes up with an improved method in the terms of endpoint effect in the process of signal decomposition. This method first takes use of signal coherent averaging technique to obtain the pulse signal template and then match the data located the endpoint with template extending original signal to the whole cycle; at last compose the extended signal in the empirical mode by Mirror extension method.
(4) This study integrates EMD generated by Empirical mode decomposition and nonlinear and spectrum character of pulse signal and then apply to the pulse-emotion recognition research discussing different pulse signal reflected by different emotions。 Gained the extraction methods of three types of certain character information and released the extraction of pulse signal effective character.
(5) This study also constructed Multi-classification based on supporting Vector Machine in order to fulfill auto-recognition of different emotion. Extract pulse signal from80samples(20samples of states of happiness,20samples of states of pleasure,20samples of states of sadness,20samples of states of anger) to do auto-recognition analysis and it proves that combination of pulse signal multi-mode character information is a more efficient way to emotion recognition.
引文
[1]A. R. Damasio. Descartes'Error:Emotion, Reason and the Human Brain. Gosset/Putnam Press, New York, NY,1994.
[2]Minsky, Marvin. The Society of Mind [M]. New York, USA: Simon & Schuster.1986.
[3]Rosalind W. Picard情感计算[M].罗森林译.北京：北京理工大学出版社.2005.
[4]陶建华,谭铁牛.数字化人类情感和谐人机交互环境中的情感计算[R].微电脑世界,2004(1)：29-32.
[5]R. W. Picard, Toward computers that recognize and respond to user emotion [J]. IBM Systems Journal,2000,39(3&4): 705-719.
[6]罗森林,潘丽敏.情感计算理论与技术[J].系统工程与电子技术,2003,25(7)：905-909.
[7]毛峡.情感信息处理[J].遥测遥控,2000,21(6)：58-62.
[8]张颖,罗森林.情感建模与情感识别[J].计算机工程与应用,2003,33：98-102.
[9]Maja Pantic, Leon J. M. Rothkrantz. Toward an Affect-Sensitive Multimodal Human-Computer Interaction [C]//Proceedings of the IEEE,2003,91(9):1370-1390.
[10]宋亦旭,贾培发.基于人工情感的拟人机器人控制体系结构[J].机器人,2004,26(6)：11.
[11]I. A. Essa, A. P. Pentland. Coding, Analysis, Interpretation, and Recognition of Facial Expressions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):757-763.
[12]蒋丹宁,蔡莲红.基于语音声学特征的情感信息识别[J].清华大学学报,2006,46(1)：86-89.
[13]Hongwu Yang, Helen Meng, Zhiyong Wu, etal. Modeling the Global Acoustic Correlates of Expressivity for Chinese Text-to-Speech Synthesis[C]//IEEE/ACL 2006 Workshop on Spoken Language Technology, Aruba,2006:10-13.
[14]R. W. Picard, E. Vyzas, J. Healey. Toward Machine Emotional Intelligence:Analysis of Affecfive Physiological State [J]. IEEE Transactions Pattern Analysis and Machine Intelligence,2001,23(10): 1175-1191.
[15]K. H. Kim, S. W. Bang, S. R. Kim. Emotion recognition system using short-term monitoring of physiological signals [J]. Medical and Biological Engineering and computing,2004,42(3):419-427.
[16]Rosalind Picard and Jennifer Healey. Digital Processing of Affective Signals [C]//In IEEE International Conference on Acoustics, Speech and Signal Processing, USA,1998, 6(6):3749-3752.
[17]Andreas Haag, Silke Goronzy, Peter Schaich, etal. Emotion Recognition Using Bio-Sensors:First Steps Towards an Automatic system [J], Affective Dialogue Systems,2004, 3068:36-48.
[18]Johannes Wagner, Jonghwa Kim, Elisabeth Andre. From Physiological Signals to Emotions:Implementing and Comparing Selected Methods for Feature Extraction and Classification [C]//In IEEE International Conference on Muhimedia & Expo (ICME 2005),2005,940-943.
[19]IBM Research Website. The doctors are in Physicians at IBM Research help create a new vision for healthcare technology [EB/OL].http://www.almaden.ibm.com/cs/blueeyes/, 2009-08-20.
[20]Exmovere Website. Emotions & Physiological Monitoring[EB/OL].http://www.exmovere.com/healthcare. html.2009-09-10.
[21]Philips Website.Philips Healthcare/Products and Solutions[EB/OL].http://www.design.philips.com/probes/i ndex.page,2010-06-23.
[23]王宏,颉斌,解仑等.基于人工心理理论的情感模型建立及其数值仿真[J].计算机应用,2004,6(24)：368-370.
[24]王志良,锋军,薛为民.人脸表情识别方法综述[J].计算机应用与软件,2003(12)：63-66.
[25]王颖.自适应语音情感识别方法研究[D].江苏：江苏大学硕士学位论文,2009.
[26]陆聪慧.面部表情识别系统中表情特征提取与识别算法的研究[D].南京：东南大学硕士学位论文,2006.
[27]温万惠,基于生理信号的情感识别方法研究[D].重庆：西南大学博士学位论文,2010.
[28]苏日娜.情绪与脉搏信号之间关系的研究[D].哈尔滨：东北林业大学硕士学位论文.2009.
[29]韩清鹏,脉搏信号的非线性分析及其不同情绪和环境的影响研究[D].浙江：浙江大学博士学位论文,2007.
[30]葛臣.脉搏信号在情感状态识别中的研究[D].重庆：西南大学硕士学位论文.2010.
[31]Tomokazu Kato,Haruki Kawanaka,Md.Shoaib Bhuiyan,et al. Classification of Positive and Negative Emotion Evoked by Traffic Jam based on electrocardiogram and Pulse Wave [C]//International IEEE Conference on Intelligent Transportation Systems,Washington,DC,USA, 2011.
[32]葛臣,刘光远,龙正吉.情感识别中脉搏信号的特征提取 与分析[J].西南师范大学学报(自然科学版),2010,35(3)：243-246.
[33]王东生,雷磊,李新芳等.从泊肃叶定律看中医脉象形成的机理[J].中国中医基础医学志,2001,7(6)：5.
[34]David L. Donoho, Iain M. Johnstone. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika,1994, 81(3):425-455.
[35]胡广书.现代信号处理教程[M].北京：清华大学出版社2004.
[36]M. A. Chappell, S. J. Payne. A method for the automated detection of venous gas bubbles in humans using empirical mode decomposition [J]. Annals of Biomedical Engineering,2005,33(10):1411-1421.
[37]E. P. Souza Neto, M. A. Custaud, J. C. Cejka, etal. Assessment of cardiovascular autonomic control by the empirical mode decomposition [J]. Methods of Information in Medicine,2004,43(1):60-65.
[38]C. Jeffery Chan, W. T. Peter. A Novel, Fast, Reliable data transmission algorithm for wireless machine health monitoring [C]//IEEE Transportation on Reliability, 2009,58(2):295-304.
[39]Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings The Royal of Society,1998,454:903-995.
[40]Huang N E, Shen Z, Long S R. A new view of nonlinear water waves:the Hilbert spectrum [J]. Annual Review of Fluid Mechanics,1999,31:417-457.
[41]N.E.Huang. A new method for nonlinear and nonstationary time series analysis:empirical mode decomposition and Hilbert spectral analysis[C]//Proc. of SPIE, Orlando, 2000, (4056):197-209.
[42]孙晖,经验模态分解理论与应用研究[D],浙江：浙江大学博士学位论文,2005.
[43]张海勇.一种新的非平稳信号分析方法_局域波分析[J].电子与信息学报,2003,10(2：5)1327-1333.
[44]陈忠,郑时雄.EMD信号分析方法边缘效应的分析[J],数据采集与处理,2003,18(1)：114-118.
[45]张子良,李世平.应用加权法处理EMD方法中的边界问题[J].计量与测试技术,2008,35(8)：34-36.
[46]邵晨曦,王剑,范金锋,等.一种自适应的EMD端点延拓方法[J].电子学报,2007,10(10)：1945-1948.
[47]邓拥军,王伟,钱成春,等.EMD方法及Hilbert变换中边界问题的处理[J].科学通报,2001,46(3)：257-263.
[48]刘慧婷,张旻,程家兴.基于多项式拟合算法的EMD端点问题的处理[J].计算机工程与应用,2004,40(16)：84-86,100.
[49]Rilling G, Flandrin P. On the influence of sampling on the empirical mode decomposition[C]//Proc 2006 IEEE International Conference on Acoustics, Speech and Signal Processing (CASSP 2006),Toulouse,France,2006, 3:444-447.
[50]Wei L Y, Chow P. Frequency distribution of human pulse spectra[C]//IEEE Transactions on Biomedical Engineering.1985,BME-32(3):245-246.
[51]Chuang-Chien Chiu, Shoou-Jeng Yeh, Ching-Hsiu Chen. Self-organizing arterial pressure pulse classification using neural networks:theoretical considerations and clinical applicability [J]. Computers in Biology and Medicine,2000.30:71-88.
[52]陶波.利用脉搏波波形特征参数变化诊断动脉硬化的研究[D].西安：西安交通大学硕士学位论文.2002.
[53]韩晟,段玉斌,管忠.用近似熵测量神经放电峰峰间期的复杂性[J].生物物理学报,2002,18(4)：448-451.
[54]洪波,唐庆玉,杨福生.近似熵、互近似熵的性质、快速算法及其在脑电与认知研究中的初步应用[J].信号处理,1999,15(2)：100-107.
[55]王小宇,贾嵘.基于Hilbert-Huang变换和支持向量机的水轮发电机组状态监测与故障诊断方法研究[D].西安：西安理工大学,2007：4041.
[56]行鸿彦,许瑞庆,王长松.基于经验模态分解的脉搏信号特征研究[J].仪器仪表学报,2009：30(3)：596-602.
[57]苟博,黄贤武.支持向量机多类分类方法[J].数据采集与处理,2006：21(3)：334-339.
[2]Minsky, Marvin. The Society of Mind [M]. New York, USA: Simon & Schuster.1986.
[3]Rosalind W. Picard情感计算[M].罗森林译.北京：北京理工大学出版社.2005.
[4]陶建华,谭铁牛.数字化人类情感和谐人机交互环境中的情感计算[R].微电脑世界,2004(1)：29-32.
[5]R. W. Picard, Toward computers that recognize and respond to user emotion [J]. IBM Systems Journal,2000,39(3&4): 705-719.
[6]罗森林,潘丽敏.情感计算理论与技术[J].系统工程与电子技术,2003,25(7)：905-909.
[7]毛峡.情感信息处理[J].遥测遥控,2000,21(6)：58-62.
[8]张颖,罗森林.情感建模与情感识别[J].计算机工程与应用,2003,33：98-102.
[9]Maja Pantic, Leon J. M. Rothkrantz. Toward an Affect-Sensitive Multimodal Human-Computer Interaction [C]//Proceedings of the IEEE,2003,91(9):1370-1390.
[10]宋亦旭,贾培发.基于人工情感的拟人机器人控制体系结构[J].机器人,2004,26(6)：11.
[11]I. A. Essa, A. P. Pentland. Coding, Analysis, Interpretation, and Recognition of Facial Expressions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):757-763.
[12]蒋丹宁,蔡莲红.基于语音声学特征的情感信息识别[J].清华大学学报,2006,46(1)：86-89.
[13]Hongwu Yang, Helen Meng, Zhiyong Wu, etal. Modeling the Global Acoustic Correlates of Expressivity for Chinese Text-to-Speech Synthesis[C]//IEEE/ACL 2006 Workshop on Spoken Language Technology, Aruba,2006:10-13.
[14]R. W. Picard, E. Vyzas, J. Healey. Toward Machine Emotional Intelligence:Analysis of Affecfive Physiological State [J]. IEEE Transactions Pattern Analysis and Machine Intelligence,2001,23(10): 1175-1191.
[15]K. H. Kim, S. W. Bang, S. R. Kim. Emotion recognition system using short-term monitoring of physiological signals [J]. Medical and Biological Engineering and computing,2004,42(3):419-427.
[16]Rosalind Picard and Jennifer Healey. Digital Processing of Affective Signals [C]//In IEEE International Conference on Acoustics, Speech and Signal Processing, USA,1998, 6(6):3749-3752.
[17]Andreas Haag, Silke Goronzy, Peter Schaich, etal. Emotion Recognition Using Bio-Sensors:First Steps Towards an Automatic system [J], Affective Dialogue Systems,2004, 3068:36-48.
[18]Johannes Wagner, Jonghwa Kim, Elisabeth Andre. From Physiological Signals to Emotions:Implementing and Comparing Selected Methods for Feature Extraction and Classification [C]//In IEEE International Conference on Muhimedia & Expo (ICME 2005),2005,940-943.
[19]IBM Research Website. The doctors are in Physicians at IBM Research help create a new vision for healthcare technology [EB/OL].http://www.almaden.ibm.com/cs/blueeyes/, 2009-08-20.
[20]Exmovere Website. Emotions & Physiological Monitoring[EB/OL].http://www.exmovere.com/healthcare. html.2009-09-10.
[21]Philips Website.Philips Healthcare/Products and Solutions[EB/OL].http://www.design.philips.com/probes/i ndex.page,2010-06-23.
[23]王宏,颉斌,解仑等.基于人工心理理论的情感模型建立及其数值仿真[J].计算机应用,2004,6(24)：368-370.
[24]王志良,锋军,薛为民.人脸表情识别方法综述[J].计算机应用与软件,2003(12)：63-66.
[25]王颖.自适应语音情感识别方法研究[D].江苏：江苏大学硕士学位论文,2009.
[26]陆聪慧.面部表情识别系统中表情特征提取与识别算法的研究[D].南京：东南大学硕士学位论文,2006.
[27]温万惠,基于生理信号的情感识别方法研究[D].重庆：西南大学博士学位论文,2010.
[28]苏日娜.情绪与脉搏信号之间关系的研究[D].哈尔滨：东北林业大学硕士学位论文.2009.
[29]韩清鹏,脉搏信号的非线性分析及其不同情绪和环境的影响研究[D].浙江：浙江大学博士学位论文,2007.
[30]葛臣.脉搏信号在情感状态识别中的研究[D].重庆：西南大学硕士学位论文.2010.
[31]Tomokazu Kato,Haruki Kawanaka,Md.Shoaib Bhuiyan,et al. Classification of Positive and Negative Emotion Evoked by Traffic Jam based on electrocardiogram and Pulse Wave [C]//International IEEE Conference on Intelligent Transportation Systems,Washington,DC,USA, 2011.
[32]葛臣,刘光远,龙正吉.情感识别中脉搏信号的特征提取 与分析[J].西南师范大学学报(自然科学版),2010,35(3)：243-246.
[33]王东生,雷磊,李新芳等.从泊肃叶定律看中医脉象形成的机理[J].中国中医基础医学志,2001,7(6)：5.
[34]David L. Donoho, Iain M. Johnstone. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika,1994, 81(3):425-455.
[35]胡广书.现代信号处理教程[M].北京：清华大学出版社2004.
[36]M. A. Chappell, S. J. Payne. A method for the automated detection of venous gas bubbles in humans using empirical mode decomposition [J]. Annals of Biomedical Engineering,2005,33(10):1411-1421.
[37]E. P. Souza Neto, M. A. Custaud, J. C. Cejka, etal. Assessment of cardiovascular autonomic control by the empirical mode decomposition [J]. Methods of Information in Medicine,2004,43(1):60-65.
[38]C. Jeffery Chan, W. T. Peter. A Novel, Fast, Reliable data transmission algorithm for wireless machine health monitoring [C]//IEEE Transportation on Reliability, 2009,58(2):295-304.
[39]Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings The Royal of Society,1998,454:903-995.
[40]Huang N E, Shen Z, Long S R. A new view of nonlinear water waves:the Hilbert spectrum [J]. Annual Review of Fluid Mechanics,1999,31:417-457.
[41]N.E.Huang. A new method for nonlinear and nonstationary time series analysis:empirical mode decomposition and Hilbert spectral analysis[C]//Proc. of SPIE, Orlando, 2000, (4056):197-209.
[42]孙晖,经验模态分解理论与应用研究[D],浙江：浙江大学博士学位论文,2005.
[43]张海勇.一种新的非平稳信号分析方法_局域波分析[J].电子与信息学报,2003,10(2：5)1327-1333.
[44]陈忠,郑时雄.EMD信号分析方法边缘效应的分析[J],数据采集与处理,2003,18(1)：114-118.
[45]张子良,李世平.应用加权法处理EMD方法中的边界问题[J].计量与测试技术,2008,35(8)：34-36.
[46]邵晨曦,王剑,范金锋,等.一种自适应的EMD端点延拓方法[J].电子学报,2007,10(10)：1945-1948.
[47]邓拥军,王伟,钱成春,等.EMD方法及Hilbert变换中边界问题的处理[J].科学通报,2001,46(3)：257-263.
[48]刘慧婷,张旻,程家兴.基于多项式拟合算法的EMD端点问题的处理[J].计算机工程与应用,2004,40(16)：84-86,100.
[49]Rilling G, Flandrin P. On the influence of sampling on the empirical mode decomposition[C]//Proc 2006 IEEE International Conference on Acoustics, Speech and Signal Processing (CASSP 2006),Toulouse,France,2006, 3:444-447.
[50]Wei L Y, Chow P. Frequency distribution of human pulse spectra[C]//IEEE Transactions on Biomedical Engineering.1985,BME-32(3):245-246.
[51]Chuang-Chien Chiu, Shoou-Jeng Yeh, Ching-Hsiu Chen. Self-organizing arterial pressure pulse classification using neural networks:theoretical considerations and clinical applicability [J]. Computers in Biology and Medicine,2000.30:71-88.
[52]陶波.利用脉搏波波形特征参数变化诊断动脉硬化的研究[D].西安：西安交通大学硕士学位论文.2002.
[53]韩晟,段玉斌,管忠.用近似熵测量神经放电峰峰间期的复杂性[J].生物物理学报,2002,18(4)：448-451.
[54]洪波,唐庆玉,杨福生.近似熵、互近似熵的性质、快速算法及其在脑电与认知研究中的初步应用[J].信号处理,1999,15(2)：100-107.
[55]王小宇,贾嵘.基于Hilbert-Huang变换和支持向量机的水轮发电机组状态监测与故障诊断方法研究[D].西安：西安理工大学,2007：4041.
[56]行鸿彦,许瑞庆,王长松.基于经验模态分解的脉搏信号特征研究[J].仪器仪表学报,2009：30(3)：596-602.
[57]苟博,黄贤武.支持向量机多类分类方法[J].数据采集与处理,2006：21(3)：334-339.