抑郁症脑电信号特征提取及分类研究
|
摘要
精神抑郁症是一种常见的、慢性复发性疾病,表现为心境显著和持久的低落,伴有相应的思维和行为的改变。研究表明,抑郁症患者脑电信号(EEG)在节律、波形幅度和功率谱等参数中存在着不同于健康人的特征。自发脑电信号含有丰富的频率成分,不同的生理状态和病因下某些频段的能量在头皮不同区域的分布会发生变化,因此可以提取不同频段上的能量作为分类器的特征参数实现抑郁症自发脑电信号的分类。本文使用小波分析和特征向量法对抑郁症患者及健康人脑电信号进行特性分析和特征提取,结合支持向量机分类器实现两类信号的准确分类。具体内容如下:
1.通过小波变换和小波包变换对原始采样信号进行多尺度小波分解,得到的不同尺度的频带分量,提取EEG在不同频段上的能量特征。小波变换是一种多尺度信号分析方法,具有良好的时频局部化特性,非常适合于分析像EEG这样非平稳信号的瞬态特性和时变特性。小波包分解具有任意多尺度特点,避免了小波变换固定时频分解的缺陷(如高频段频率分辨率低),为时频分析提供了极大的选择余地,更能反映信号的本质和特征。
2.将特征向量功率谱估计法应用到抑郁症脑电信号的特征提取中,我们对试验对象的脑电信号功率谱幅度进行统计分析,选取功率谱幅度的最大值、最小值、平均值和标准偏差作为信号的分类特征参数。特征向量法功率谱估计是基于矩阵特征分解的一种非参数建模谱估计方法,它主要适用于混有白噪声的正弦信号的频率估计及功率谱估计,甚至对于信噪比很低的信号,也能取得很高的谱分辨率。
3.在完成抑郁症患者和健康人脑电信号特征提取的基础上,我们使用支持向量机对这两类信号进行分类研究。支持向量机是根据统计学理论提出的一种机器学习方法,它集成了最大间隔超平面、Mercer核、凸二次规划和松弛变量等多项技术。支持向量机的方法根据结构风险最小化原则,提高学习机的泛化能力,它将优化问题转化为求解一个凸二次规划的问题,二次规划所得的解是唯一的且为全局最优解,这样就不存在一般神经网络的局部极值问题。支持向量机由于较好地解决了小样本、非线性、高维数、局部极小点等实际问题,在若干具有挑战性的应用中,获得了目前为止最好的性能。支持向量机已经逐渐成为解决模式分类问题的首选工具。
实验结果表明,采用以上三种特征提取方法提取的特征参数作为分类器的输入向量均可以取得理想的效果,抑郁症脑电信号分类准确率达87%以上。该研究成果将为精神抑郁症的病理临床诊断提供一种新的途径,为下一步基于自发脑电的抑郁症疾病诊断实用系统开发奠定基础。
Melancholia is a kind of common dysfunction disease characterized by an obvious reduction in intellectual and physiological vigor. Some related studies found that electroencephalogram (EEG) signals of melancholic differ from that of healthy persons in rhythm, wave amplitude and power spectrum amplitude. A number of frequency components are included in spontaneous EEG and the energy corresponding to different frequency bands, which is detected in different physiological states and pathogeny, changes with the scalp area. Thus the energy corresponding to a certain frequency sub-band can be taken as a feature parameter of the classifier to realize the classification of melancholia EEG. In this paper, the use of wavelet analysis and eigenvector estimation was proposed for the extraction of discriminating features from melancholia and nomal people's EEG. Subsequently, we achieved the classification combining with SVM. The main work done in this dissertation is as follows:
1. The EEG recordings were decomposed into various frequency bands through multiscale decomposition by the method of wavelet transaction (WT) and wavelet package transaction (WPT) respectively. And then, we extracted the energy feature using wavelet coefficients. WT is a multiscale signal analysis method which key feature is the time -freqency localsation, and it is suitable for capturing transient nature of nonstationary EEG signals. With the trait of arbitrary multiscale decomposition, WPT cover the shortage of fixed time-frequency decomposition in WT (i.e. poor frequency resolution for high frequency component). Therefore, WPT has better time-frequency charactristic and provides more choice in time-frequency signal analysis.
2. By applying the method of eigenvector estimation to the feature extraction of EEG signal, we carry a statistical analysis on the EEG power spectrum amplitude. And then, we take the maximum, minimum, mean and standard deviation of EEG power spectrum amplitude as characteristic parameters. Eigenvector estimation is a non-parametric method based on an eigen-decomposition of the correlation matrix of the noise-corrupted signals. It is best suited to the signals assumed to be composed of several specific sinusoids buried in noise. Even when the signal-to-noise ratio (SNR) is low, the eigenvector estimation can still obtain a high resolution of frequency spectra.
3. Having finished the feature extraction of the melancholic and healthy persons' EEG, we achieved the classification of these two kinds of EEG by Support Vector Machine (SVM). SVM is a machine learning method based on statistics theory, which includes a number of techniques such as the largest interval hyper plane, Mercer kernel, convex quadratic programming and relaxation variables etc. According to the principle of minimizing structural risk, SVM enhances the generalization capability of learning machine and converts the optimization problem into a convex quadratic programming problem. Since the solution of this convex quadratic programming problem is unique and global, local extremum problem existing in general neural networks doesn't occur. Since practical problems such as nonlinear problem, high dimension problem and local extremum problem have been resolved, SVM obtains the best performance in a variety of practical applications with much challenge. Consequently, SVM has gradually become a superior tool to solve the problem of pattern classification.
Experiments demonstrate that taking the feature parameter, which is extracted by the above three feature extraction methods, as the input eigenvector can achieve ideal clsssification accuracy which arrives 87%. This paper presented a new method for melancholia diagnose. The present research provides a basis for the ongoing study "research of melancholic diagnose based on spontaneous EEG".
1.通过小波变换和小波包变换对原始采样信号进行多尺度小波分解,得到的不同尺度的频带分量,提取EEG在不同频段上的能量特征。小波变换是一种多尺度信号分析方法,具有良好的时频局部化特性,非常适合于分析像EEG这样非平稳信号的瞬态特性和时变特性。小波包分解具有任意多尺度特点,避免了小波变换固定时频分解的缺陷(如高频段频率分辨率低),为时频分析提供了极大的选择余地,更能反映信号的本质和特征。
2.将特征向量功率谱估计法应用到抑郁症脑电信号的特征提取中,我们对试验对象的脑电信号功率谱幅度进行统计分析,选取功率谱幅度的最大值、最小值、平均值和标准偏差作为信号的分类特征参数。特征向量法功率谱估计是基于矩阵特征分解的一种非参数建模谱估计方法,它主要适用于混有白噪声的正弦信号的频率估计及功率谱估计,甚至对于信噪比很低的信号,也能取得很高的谱分辨率。
3.在完成抑郁症患者和健康人脑电信号特征提取的基础上,我们使用支持向量机对这两类信号进行分类研究。支持向量机是根据统计学理论提出的一种机器学习方法,它集成了最大间隔超平面、Mercer核、凸二次规划和松弛变量等多项技术。支持向量机的方法根据结构风险最小化原则,提高学习机的泛化能力,它将优化问题转化为求解一个凸二次规划的问题,二次规划所得的解是唯一的且为全局最优解,这样就不存在一般神经网络的局部极值问题。支持向量机由于较好地解决了小样本、非线性、高维数、局部极小点等实际问题,在若干具有挑战性的应用中,获得了目前为止最好的性能。支持向量机已经逐渐成为解决模式分类问题的首选工具。
实验结果表明,采用以上三种特征提取方法提取的特征参数作为分类器的输入向量均可以取得理想的效果,抑郁症脑电信号分类准确率达87%以上。该研究成果将为精神抑郁症的病理临床诊断提供一种新的途径,为下一步基于自发脑电的抑郁症疾病诊断实用系统开发奠定基础。
Melancholia is a kind of common dysfunction disease characterized by an obvious reduction in intellectual and physiological vigor. Some related studies found that electroencephalogram (EEG) signals of melancholic differ from that of healthy persons in rhythm, wave amplitude and power spectrum amplitude. A number of frequency components are included in spontaneous EEG and the energy corresponding to different frequency bands, which is detected in different physiological states and pathogeny, changes with the scalp area. Thus the energy corresponding to a certain frequency sub-band can be taken as a feature parameter of the classifier to realize the classification of melancholia EEG. In this paper, the use of wavelet analysis and eigenvector estimation was proposed for the extraction of discriminating features from melancholia and nomal people's EEG. Subsequently, we achieved the classification combining with SVM. The main work done in this dissertation is as follows:
1. The EEG recordings were decomposed into various frequency bands through multiscale decomposition by the method of wavelet transaction (WT) and wavelet package transaction (WPT) respectively. And then, we extracted the energy feature using wavelet coefficients. WT is a multiscale signal analysis method which key feature is the time -freqency localsation, and it is suitable for capturing transient nature of nonstationary EEG signals. With the trait of arbitrary multiscale decomposition, WPT cover the shortage of fixed time-frequency decomposition in WT (i.e. poor frequency resolution for high frequency component). Therefore, WPT has better time-frequency charactristic and provides more choice in time-frequency signal analysis.
2. By applying the method of eigenvector estimation to the feature extraction of EEG signal, we carry a statistical analysis on the EEG power spectrum amplitude. And then, we take the maximum, minimum, mean and standard deviation of EEG power spectrum amplitude as characteristic parameters. Eigenvector estimation is a non-parametric method based on an eigen-decomposition of the correlation matrix of the noise-corrupted signals. It is best suited to the signals assumed to be composed of several specific sinusoids buried in noise. Even when the signal-to-noise ratio (SNR) is low, the eigenvector estimation can still obtain a high resolution of frequency spectra.
3. Having finished the feature extraction of the melancholic and healthy persons' EEG, we achieved the classification of these two kinds of EEG by Support Vector Machine (SVM). SVM is a machine learning method based on statistics theory, which includes a number of techniques such as the largest interval hyper plane, Mercer kernel, convex quadratic programming and relaxation variables etc. According to the principle of minimizing structural risk, SVM enhances the generalization capability of learning machine and converts the optimization problem into a convex quadratic programming problem. Since the solution of this convex quadratic programming problem is unique and global, local extremum problem existing in general neural networks doesn't occur. Since practical problems such as nonlinear problem, high dimension problem and local extremum problem have been resolved, SVM obtains the best performance in a variety of practical applications with much challenge. Consequently, SVM has gradually become a superior tool to solve the problem of pattern classification.
Experiments demonstrate that taking the feature parameter, which is extracted by the above three feature extraction methods, as the input eigenvector can achieve ideal clsssification accuracy which arrives 87%. This paper presented a new method for melancholia diagnose. The present research provides a basis for the ongoing study "research of melancholic diagnose based on spontaneous EEG".
引文
[1]朱艺.抑郁症研究进展[J].实用中医药杂志,2005,24(2):131-132.
[2]李跃华,张兰风.抑郁症研究现状及未来研究目标探讨[J].中国中医药信息杂志,2006,13(10):1-3.
[3]李蕴,熊才涛,李幼晖.CIDI对抑郁症48例的心里评估--全国CIDI和SCAN测试协作报告之三[J].中国精神医学杂志,1995,1(3):78-80.
[4]宋建成,费立鹏,张培炎等.精明精神病评定量表中各分量表的评价[J].临床精神医学杂志,2001,11(2):86-88.
[5]Kikenny TM.Fundamentals of Polysomnography and Sleep Disorders.New Hope:Intellisleep Technology and Consulting,2002:197-215.
[6]Ogura C,Koga Y,Shimokochi M,et al.Recent Advances in Event-related Brain Potential Research.Ansterdam:Elservier,1996:1085-1088.
[7]Mikhailova E.S.EEG Mapping of Three Alpha Subbands in Healthy and Depressive Subjects under Music Test.Proceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.IEEE Piscataway NJ.USA,1991,13:12010-12018.
[8]Shagass C.Combinations of Evoked Potential Amplitude Measurements in Relations to Psychiatric Diagnosis.Biol-Psychiatry,1985,20:701-705.
[9]Allen R.Braun,Thomas J.Balk in,Nancy J.Wesensten,et al.Dissociated Pattern of Activity in Visual Cortices and Their Projections During Human Rapid Eye Movement Sleep.Science,1998:279-291.
[10]Emesto Pereda,Rodrigo Quian Quiroga,Joydeep Bhattacharya.Nonlinear Multivariate Analysis of Neurophysiological Signals.Progress in Neurobiology,2005,77:1-37.
[11]Spencer K.M.,Nestor P.G.,Niznikiewicz M.A.,etal.Abnormal Neural Synchrony Schizophrenia.J.Neurosci,2003,23:7407-7411.
[12]魏有东,谢鹏.神经性障碍与抑郁症患者脑电图比较分析[J].山西医科大学学报,2005,36(1):96-97.
[13]Blanco S.,DpAttellis C.,Isaacson S.,et al.Time-Frequency Analysis of Electroencephalograms Series:Gabor and Wavelet Transforms.Physical Review,1996,54(6):6661-6672.
[14]Hamid E.Y,Mardiana R,Kawasaki Z.I.Method for RMS and Power Measurements Based on the Wavelet Packet Transform.IEEE Proceedings-Science,Measurement and Technology,2002,149(2):60-66.
[15]Ernesto Pereda,Rodrigo Quian Quiroga,Joydeep Bhattacharya.Nonlinear Multivariate Analysis of Neurophysiological Signals.Progress in Neurobiology,2005,77:1-37.
[16]Spencer K.M.,Nestor P.G.,Niznikiewicz M.A.,et al.Abnormal neural synchrony in schizophrenia.J.Neurosci,2003,23:7407-7411.
[17]Spyers Ashby J.M.,Bain P.G.,Roberts S.J.A Comparison of Fast Fourier Transform (FFT) and Autoregressive(AR) Spectral Estimation Techniques for the Analysis of Tremor Data.J.Neurosci Methods,1998,83:35-43.
[18]Pereda E.,Gamundi A.,Rial R.,et al.Non-linearBehaviour of Human EEG:Fractal Exponent Versus Correlation Dimension in Awake and Sleep Stages.Neurosci.Lett,1998,250:91-94.
[19]Babloyantz A.,Salazar J.M.,Nicolis C.Evidence of Chaotic Dynamics of Brain Activity During the Sleep Cycle.Phys.Lett.A,1998,111:152-156.
[20]Breakspear M.,Terry J.R.,Friston K.J.,et al.A Disturbance of Nonlinear Interdependence in Scalp EEG of Subjects with First Episode Schizophrenia.Neuroimage,2003,20:466-478.
[21]Stam C.J.,Jelles B.,A ch tereek te HAM,et al.Investigation of EEG Non-linearity in Dementia and Park-Vinson's Disease.Electroenceph Clin Neurophysio,Neur,1995,95:309-313.
[22]Roschke J.,Aldenhoff J.The Dimensionality of Human's Electroencephalogram During Sleep.BiolCybern,1991,64:307-311.
[23]Cristianini N.,Taylor JS.An Introduction to Support Vector Machines.Cambridge,UK:Cambridge University Press,2000.
[24]Morik K.,Brockhausen P.,and Joachims T.Combining Statistical Learning with a Knowledge-based Approach-a Case Study in Intensive Care Monitoring.Proc.16th Int'l Conf.on Machine Learning(ICML-99),1999.
[25]Skeerthi,Chih-Jen Lin.Symptotic Behavior of Support Vector Machines with Gaussian Kernel.Nerual Computation.2003,15:1667-1689.
[26]谭郁玲.临床脑电图与脑电地形图学[M].北京:人民卫生出版社,1999.
[27]Saeid Sanei,J.A.Chambers.EEG SIGNAL PROCESSING.John Wiley & Sons,Ltd,2007:15-16.
[28]马颖颖,张泾周,吴疆.脑电信号处理方法.北京生物医学工程,2007,26(1):99-102.
[29]崔建国,王旭,訾学博等.脑电信号的最新研究方法[J].沈阳航空工业学院学报,2004,21(2):64-66.
[30]季忠,秦树人,彭丽领.脑电信号的现代分析方法[J].重庆大学学报,2002,25(9):108-112.
[31]张明友,吕明.近代信号处理理论与方法[M].国防工业出版社,2005.
[32]胡广书.数字信号处理-理论、算法与实现[M].清华大学出版社,2001.
[33]Chen F,Xu JH,Gu FJ,et al.Dynamic Process of Information Transmission Complexity in Human Brain.Biological Cybernetics,2000,83(4):355-366.
[34]黄华品,陈清棠,郑安.健康人不同生理状态下的脑电近似嫡的观测.中国应用生理学杂志,2000,16(4):321-323.
[35]孟欣,欧阳楷.脑电信号的几个非线性动力学分析方法[J].北京生物医学工程,1997,16(3):135-140.
[36]徐琳,许百华.非线性动力学脑电信号分析方法的研究与应用[J].心理科学,2005,28(3):761-763.
[37]程正兴.小波分析与应用实例.西安交通大学出版社,2006.
[38]葛哲学,沙威.小波分析理论与MATLABR2007实现.电子工业大学出版社,2007.
[39]张毅刚,郁惟镛,黄成军等.基于小波包及隐式马尔科夫模型的局放信号去噪.上海交通大学学报.2004,8(8):1269-1272.
[40]J.Z.Xue,H.Zhang,C.X.Zheng,"Wavelet Packet Transform for Feature Extraction of EEG During Mental Tasks" presented at Proceedings of the Second International Conference on Machine Learning and Cybernetics,Xi'an,2003.
[41]李弼程,罗建书.小波分析及其应用.北京:电子工业出版社,2003.
[42]刘毅,张彩明,赵玉华等.基于多尺度小波包分析的肺音特征提取与分类[J].计算机学报,2006,5:769-777.
[43]沃建中,曹河圻,潘昱等.6-12岁儿童脑电α波的发展特点[J].心理发展与教育,2000,4:1-7.
[44]Elif Derya(u|¨)beyli.Analysis of EEG Signals by Combining Eigenvector Methods and Multielass Support Vector Machines[J].Computers in Biology and Medicine,2008,38:14-22.
[45]Elif Derya(u|¨)beyli.Features Extracted by Eigenvector Methods for Detecting Variability of EEG Signals.Pattern Recognition Letters,2008,28:592-603.
[46]Vapnik V N.The Nature of Statistical Learning Theory.NY:Springer-Verlag,1995.
[47]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,(1):32-42.
[48]Vapnik V N.An overview of statistical Learning Theory.IEEETrans.Neural Network,1999,10(5):988-999.
[49]杨帮华,颜国正,丁国清等.脑机接口关键技术研究.北京生物医学工程.2005,24,(4):309-312.
[50]McFarland D.J.,Miner L.A.,Vaughan T.M.,et al.Mu and Beta Rhythm Topographies During Motor Imagery and Actual Movements.Brain Topography,2000,12(3):177-186.
[51]A.Delorme,S.Makeig.EEG Changes Accompanying Learned Regulation of 12-Hz EEG Activity.IEEE Transactions on Neural System and Rehabilitation Engineering,2003,11(2):133-136.
[52]J.R.Mill(?)n,M.Franz(?),J.Mourino.Relevant EEG Features for the Classification of Spontaneous Motor-related Tasks.Biological Cybernetics,2002,86:89-97.
[53]Z.A.Keirn,J.I.Aunon.A new Mode of Communication between Man and his Surroundings.IEEE Transactions on Biomedical Engineering,1990,37(12):1209-1214.
[54]C.W.Anderson,E.A.Stolz,S.Shamsunder.Multivariate Autoregressive Models for Classification of Spontaneous Electroencephalographic Signals.IEEE Transactions on Biomedical Engineering,1998,45(3):277-286.
[55]X.M.Pei,C.X.Zheng.“Feature Extraction and Classification of Brain Motor Imagery Task Based on MVAR Model” presented at Proceedings of the Third International Conference on Machine Learning and Cybernetics,shanghai,2004.
[56]G.Bernhard,E.H.Jane,P.L.Simon,et al.Toward a Direct Brain Interface Based on Human Subdural Recordings and Wavelet-packet Analysis.IEEE Trans on Biomedical Engineering,2004,51(6):954-962.
[57]J.Z.Xue,W.X.He,X.G.Yan.Feature Extraction and Classification of EEG for Mental Tasks Based on Wavelet Packet Analysis.Journal of Biomedical Engineering,2004,21(3):396-400.
[58]F.Babiloni,F.Cincotti,L.Lazzarini,et al.Linear Classification of Low-resolution EEG Patterns Produced by Imagined Hand Movements.IEEE Transactions on Neural System and Rehabilitation Engineering,2000,8(2):186-188.
[59]C.W.Anderson,S.V.Devulapalli,E.A.Stolz.Determining Mental State from EEG Signals Using Neural Networks.Sci.Program,1995,4(3):171-183.
[60] K.Matthias, M.Peter, GUlf. BCI competition 2003-Data Set IIb: Support Vector Machines for the P300 Speller Paradigm. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1073-1076.
[61] N.L.Thomas, S.Michael, H.Thilo. Support Vector Channel Selection in BCI. IEEE Transactions on Biomedical Engineering, 2004, 5(16):1003-1010.
[62] GE.Birch, S.GMason. Brain-computer Interface Research at the Neil Squire Foundation. IEEE Transactions on Rehabilitation Engineering, 2000, 8(2): 193-195.
[63] P.Sykacek, S.Roberts, M.Stokes.Probabilistic Methods in BCI Research. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11 (2):192-195.
[2]李跃华,张兰风.抑郁症研究现状及未来研究目标探讨[J].中国中医药信息杂志,2006,13(10):1-3.
[3]李蕴,熊才涛,李幼晖.CIDI对抑郁症48例的心里评估--全国CIDI和SCAN测试协作报告之三[J].中国精神医学杂志,1995,1(3):78-80.
[4]宋建成,费立鹏,张培炎等.精明精神病评定量表中各分量表的评价[J].临床精神医学杂志,2001,11(2):86-88.
[5]Kikenny TM.Fundamentals of Polysomnography and Sleep Disorders.New Hope:Intellisleep Technology and Consulting,2002:197-215.
[6]Ogura C,Koga Y,Shimokochi M,et al.Recent Advances in Event-related Brain Potential Research.Ansterdam:Elservier,1996:1085-1088.
[7]Mikhailova E.S.EEG Mapping of Three Alpha Subbands in Healthy and Depressive Subjects under Music Test.Proceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.IEEE Piscataway NJ.USA,1991,13:12010-12018.
[8]Shagass C.Combinations of Evoked Potential Amplitude Measurements in Relations to Psychiatric Diagnosis.Biol-Psychiatry,1985,20:701-705.
[9]Allen R.Braun,Thomas J.Balk in,Nancy J.Wesensten,et al.Dissociated Pattern of Activity in Visual Cortices and Their Projections During Human Rapid Eye Movement Sleep.Science,1998:279-291.
[10]Emesto Pereda,Rodrigo Quian Quiroga,Joydeep Bhattacharya.Nonlinear Multivariate Analysis of Neurophysiological Signals.Progress in Neurobiology,2005,77:1-37.
[11]Spencer K.M.,Nestor P.G.,Niznikiewicz M.A.,etal.Abnormal Neural Synchrony Schizophrenia.J.Neurosci,2003,23:7407-7411.
[12]魏有东,谢鹏.神经性障碍与抑郁症患者脑电图比较分析[J].山西医科大学学报,2005,36(1):96-97.
[13]Blanco S.,DpAttellis C.,Isaacson S.,et al.Time-Frequency Analysis of Electroencephalograms Series:Gabor and Wavelet Transforms.Physical Review,1996,54(6):6661-6672.
[14]Hamid E.Y,Mardiana R,Kawasaki Z.I.Method for RMS and Power Measurements Based on the Wavelet Packet Transform.IEEE Proceedings-Science,Measurement and Technology,2002,149(2):60-66.
[15]Ernesto Pereda,Rodrigo Quian Quiroga,Joydeep Bhattacharya.Nonlinear Multivariate Analysis of Neurophysiological Signals.Progress in Neurobiology,2005,77:1-37.
[16]Spencer K.M.,Nestor P.G.,Niznikiewicz M.A.,et al.Abnormal neural synchrony in schizophrenia.J.Neurosci,2003,23:7407-7411.
[17]Spyers Ashby J.M.,Bain P.G.,Roberts S.J.A Comparison of Fast Fourier Transform (FFT) and Autoregressive(AR) Spectral Estimation Techniques for the Analysis of Tremor Data.J.Neurosci Methods,1998,83:35-43.
[18]Pereda E.,Gamundi A.,Rial R.,et al.Non-linearBehaviour of Human EEG:Fractal Exponent Versus Correlation Dimension in Awake and Sleep Stages.Neurosci.Lett,1998,250:91-94.
[19]Babloyantz A.,Salazar J.M.,Nicolis C.Evidence of Chaotic Dynamics of Brain Activity During the Sleep Cycle.Phys.Lett.A,1998,111:152-156.
[20]Breakspear M.,Terry J.R.,Friston K.J.,et al.A Disturbance of Nonlinear Interdependence in Scalp EEG of Subjects with First Episode Schizophrenia.Neuroimage,2003,20:466-478.
[21]Stam C.J.,Jelles B.,A ch tereek te HAM,et al.Investigation of EEG Non-linearity in Dementia and Park-Vinson's Disease.Electroenceph Clin Neurophysio,Neur,1995,95:309-313.
[22]Roschke J.,Aldenhoff J.The Dimensionality of Human's Electroencephalogram During Sleep.BiolCybern,1991,64:307-311.
[23]Cristianini N.,Taylor JS.An Introduction to Support Vector Machines.Cambridge,UK:Cambridge University Press,2000.
[24]Morik K.,Brockhausen P.,and Joachims T.Combining Statistical Learning with a Knowledge-based Approach-a Case Study in Intensive Care Monitoring.Proc.16th Int'l Conf.on Machine Learning(ICML-99),1999.
[25]Skeerthi,Chih-Jen Lin.Symptotic Behavior of Support Vector Machines with Gaussian Kernel.Nerual Computation.2003,15:1667-1689.
[26]谭郁玲.临床脑电图与脑电地形图学[M].北京:人民卫生出版社,1999.
[27]Saeid Sanei,J.A.Chambers.EEG SIGNAL PROCESSING.John Wiley & Sons,Ltd,2007:15-16.
[28]马颖颖,张泾周,吴疆.脑电信号处理方法.北京生物医学工程,2007,26(1):99-102.
[29]崔建国,王旭,訾学博等.脑电信号的最新研究方法[J].沈阳航空工业学院学报,2004,21(2):64-66.
[30]季忠,秦树人,彭丽领.脑电信号的现代分析方法[J].重庆大学学报,2002,25(9):108-112.
[31]张明友,吕明.近代信号处理理论与方法[M].国防工业出版社,2005.
[32]胡广书.数字信号处理-理论、算法与实现[M].清华大学出版社,2001.
[33]Chen F,Xu JH,Gu FJ,et al.Dynamic Process of Information Transmission Complexity in Human Brain.Biological Cybernetics,2000,83(4):355-366.
[34]黄华品,陈清棠,郑安.健康人不同生理状态下的脑电近似嫡的观测.中国应用生理学杂志,2000,16(4):321-323.
[35]孟欣,欧阳楷.脑电信号的几个非线性动力学分析方法[J].北京生物医学工程,1997,16(3):135-140.
[36]徐琳,许百华.非线性动力学脑电信号分析方法的研究与应用[J].心理科学,2005,28(3):761-763.
[37]程正兴.小波分析与应用实例.西安交通大学出版社,2006.
[38]葛哲学,沙威.小波分析理论与MATLABR2007实现.电子工业大学出版社,2007.
[39]张毅刚,郁惟镛,黄成军等.基于小波包及隐式马尔科夫模型的局放信号去噪.上海交通大学学报.2004,8(8):1269-1272.
[40]J.Z.Xue,H.Zhang,C.X.Zheng,"Wavelet Packet Transform for Feature Extraction of EEG During Mental Tasks" presented at Proceedings of the Second International Conference on Machine Learning and Cybernetics,Xi'an,2003.
[41]李弼程,罗建书.小波分析及其应用.北京:电子工业出版社,2003.
[42]刘毅,张彩明,赵玉华等.基于多尺度小波包分析的肺音特征提取与分类[J].计算机学报,2006,5:769-777.
[43]沃建中,曹河圻,潘昱等.6-12岁儿童脑电α波的发展特点[J].心理发展与教育,2000,4:1-7.
[44]Elif Derya(u|¨)beyli.Analysis of EEG Signals by Combining Eigenvector Methods and Multielass Support Vector Machines[J].Computers in Biology and Medicine,2008,38:14-22.
[45]Elif Derya(u|¨)beyli.Features Extracted by Eigenvector Methods for Detecting Variability of EEG Signals.Pattern Recognition Letters,2008,28:592-603.
[46]Vapnik V N.The Nature of Statistical Learning Theory.NY:Springer-Verlag,1995.
[47]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,(1):32-42.
[48]Vapnik V N.An overview of statistical Learning Theory.IEEETrans.Neural Network,1999,10(5):988-999.
[49]杨帮华,颜国正,丁国清等.脑机接口关键技术研究.北京生物医学工程.2005,24,(4):309-312.
[50]McFarland D.J.,Miner L.A.,Vaughan T.M.,et al.Mu and Beta Rhythm Topographies During Motor Imagery and Actual Movements.Brain Topography,2000,12(3):177-186.
[51]A.Delorme,S.Makeig.EEG Changes Accompanying Learned Regulation of 12-Hz EEG Activity.IEEE Transactions on Neural System and Rehabilitation Engineering,2003,11(2):133-136.
[52]J.R.Mill(?)n,M.Franz(?),J.Mourino.Relevant EEG Features for the Classification of Spontaneous Motor-related Tasks.Biological Cybernetics,2002,86:89-97.
[53]Z.A.Keirn,J.I.Aunon.A new Mode of Communication between Man and his Surroundings.IEEE Transactions on Biomedical Engineering,1990,37(12):1209-1214.
[54]C.W.Anderson,E.A.Stolz,S.Shamsunder.Multivariate Autoregressive Models for Classification of Spontaneous Electroencephalographic Signals.IEEE Transactions on Biomedical Engineering,1998,45(3):277-286.
[55]X.M.Pei,C.X.Zheng.“Feature Extraction and Classification of Brain Motor Imagery Task Based on MVAR Model” presented at Proceedings of the Third International Conference on Machine Learning and Cybernetics,shanghai,2004.
[56]G.Bernhard,E.H.Jane,P.L.Simon,et al.Toward a Direct Brain Interface Based on Human Subdural Recordings and Wavelet-packet Analysis.IEEE Trans on Biomedical Engineering,2004,51(6):954-962.
[57]J.Z.Xue,W.X.He,X.G.Yan.Feature Extraction and Classification of EEG for Mental Tasks Based on Wavelet Packet Analysis.Journal of Biomedical Engineering,2004,21(3):396-400.
[58]F.Babiloni,F.Cincotti,L.Lazzarini,et al.Linear Classification of Low-resolution EEG Patterns Produced by Imagined Hand Movements.IEEE Transactions on Neural System and Rehabilitation Engineering,2000,8(2):186-188.
[59]C.W.Anderson,S.V.Devulapalli,E.A.Stolz.Determining Mental State from EEG Signals Using Neural Networks.Sci.Program,1995,4(3):171-183.
[60] K.Matthias, M.Peter, GUlf. BCI competition 2003-Data Set IIb: Support Vector Machines for the P300 Speller Paradigm. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1073-1076.
[61] N.L.Thomas, S.Michael, H.Thilo. Support Vector Channel Selection in BCI. IEEE Transactions on Biomedical Engineering, 2004, 5(16):1003-1010.
[62] GE.Birch, S.GMason. Brain-computer Interface Research at the Neil Squire Foundation. IEEE Transactions on Rehabilitation Engineering, 2000, 8(2): 193-195.
[63] P.Sykacek, S.Roberts, M.Stokes.Probabilistic Methods in BCI Research. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11 (2):192-195.