基于平行因子模型的运动想象脑电分类
|
摘要
近年来,脑-机接口研究的兴趣持续强劲增长。脑-机接口系统使其用户可以通过大脑活动来控制外部设备,它把用户的意图翻译成设备的控制命令,为用户提供了一条新的控制或交流通道,该通道不依赖于外周神经系统和肌肉等大脑正常的输出通道。
时-频分析能够把信号的能量分布描述为时间和频率的函数,是非平稳信号处理的有力工具。短时傅里叶变换、小波变换和wigner-ville分布是脑-机接口系统中三种常用的时频分析方法,论文从时间分辨率和频率分辨率角度讨论了这些方法的优缺点,并通过一些测试来深入讨论它们的优缺点及参数的选择。
作为一种张量分解方法,平行因子分解保留数据的所有维,能够产生唯一的分解和具有物理意义的分量。论文把来自于不同通道脑电信号的时频分布组合成张量数据,其结构为通道×频率×时间,并通过拟合平行因子模型从这些张量数据中提取事件相关(去)同步化模式。为了评估这些特征的分类能力,采用了基于支持向量机、贝叶斯理论和隐马尔可夫模型的分类器并对它们进行对比。
从结果可知,对于不同的时-频分析方法,短时傅里叶变换与小波变换的性能接近,而wigner-ville分布由于受干扰项的影响,性能稍差；参数的选择对这三种方法都很重要,尤其是短时傅里叶变换对窗函数的长度很敏感,而小波变换则能产生鲁棒的结果；对于分类器,改进的贝叶斯分类器通过整合不同时间处的信息而获得了比其它分类器更好的分类精度。
Recently years, the interest in BCI research is strongly increasing. A Brain-Computer Interface is a system that allows its user to control external devices with brain activity, it translates user intents into device control commands, thus offering a new channel of control or communication that doesn't does not depend on the brain's normal output channels such as peripheral nerves and muscles.
Time-frequency analysis is used to describe the distribution of signal energy as a function of both time and frequency, and is a powerful tool for non-stationary signal processing. short time Fourier transformation, wavelet transformation and Wigner-Ville distribution are three major time-frequency analysis approaches used in BCI systems, this article explained the merits and defects of those methods from the time resolution, frequency resolution, the advantages and shortcomings of these methods, and choosing of parameters are explained deeply by test cases.
Parallel Factor Analysis(PARAFAC), a tensor decomposition approach, retains all dimensions and produces unique decomposition and physically meaningful components. Time-frequency distributions of EEG from different channels were grouped together to form data tensors of structure channel×frequency×time, and from which event-related (de)synchronization patterns were extracted by fitted to PARAFAC model. To evaluate the discriminative power of these features, classifiers designed by Support Vector Machine (SVM), Bayes theory and Hidden Markov Models (HMM) are introduced and compared with each other.
For different time-frequency analysis methods, short time Fourier transformation and wavelet transformation revealed similar performance, and wigner-ville distribution analysis performed slightly worse than them because of interference terms. As indicated by results, selecting of parameters is important for all three methods, but short time Fourier transformation is sensitive to window length, and wavelet provides the most robust results. As classifier, through combining the information across time, modified Bayes theory based classifier made the highest accuracy.
时-频分析能够把信号的能量分布描述为时间和频率的函数,是非平稳信号处理的有力工具。短时傅里叶变换、小波变换和wigner-ville分布是脑-机接口系统中三种常用的时频分析方法,论文从时间分辨率和频率分辨率角度讨论了这些方法的优缺点,并通过一些测试来深入讨论它们的优缺点及参数的选择。
作为一种张量分解方法,平行因子分解保留数据的所有维,能够产生唯一的分解和具有物理意义的分量。论文把来自于不同通道脑电信号的时频分布组合成张量数据,其结构为通道×频率×时间,并通过拟合平行因子模型从这些张量数据中提取事件相关(去)同步化模式。为了评估这些特征的分类能力,采用了基于支持向量机、贝叶斯理论和隐马尔可夫模型的分类器并对它们进行对比。
从结果可知,对于不同的时-频分析方法,短时傅里叶变换与小波变换的性能接近,而wigner-ville分布由于受干扰项的影响,性能稍差；参数的选择对这三种方法都很重要,尤其是短时傅里叶变换对窗函数的长度很敏感,而小波变换则能产生鲁棒的结果；对于分类器,改进的贝叶斯分类器通过整合不同时间处的信息而获得了比其它分类器更好的分类精度。
Recently years, the interest in BCI research is strongly increasing. A Brain-Computer Interface is a system that allows its user to control external devices with brain activity, it translates user intents into device control commands, thus offering a new channel of control or communication that doesn't does not depend on the brain's normal output channels such as peripheral nerves and muscles.
Time-frequency analysis is used to describe the distribution of signal energy as a function of both time and frequency, and is a powerful tool for non-stationary signal processing. short time Fourier transformation, wavelet transformation and Wigner-Ville distribution are three major time-frequency analysis approaches used in BCI systems, this article explained the merits and defects of those methods from the time resolution, frequency resolution, the advantages and shortcomings of these methods, and choosing of parameters are explained deeply by test cases.
Parallel Factor Analysis(PARAFAC), a tensor decomposition approach, retains all dimensions and produces unique decomposition and physically meaningful components. Time-frequency distributions of EEG from different channels were grouped together to form data tensors of structure channel×frequency×time, and from which event-related (de)synchronization patterns were extracted by fitted to PARAFAC model. To evaluate the discriminative power of these features, classifiers designed by Support Vector Machine (SVM), Bayes theory and Hidden Markov Models (HMM) are introduced and compared with each other.
For different time-frequency analysis methods, short time Fourier transformation and wavelet transformation revealed similar performance, and wigner-ville distribution analysis performed slightly worse than them because of interference terms. As indicated by results, selecting of parameters is important for all three methods, but short time Fourier transformation is sensitive to window length, and wavelet provides the most robust results. As classifier, through combining the information across time, modified Bayes theory based classifier made the highest accuracy.
引文
[1]K. Andrea, K. R. Muller, An introduction to brain computer interfacing. In Toward brain-computer interfacing, edited by G. Dornhege, J. D. R. Millan, T. Hinterberger, et al., Cambridge, MA:MIT Press,2007, ch.1, p. 1-25.
[2]J. R. Millan, P. W. Ferrez, A. Buttfield, The IDIAP Brain-Computer Interface:An Asynchronous Multiclass Approach. In Toward brain-computer interfacing, edited by G. Dornhege, J. D. R. Millan, T. Hinterberger, et al., Cambridge, MA:MIT Press,2007, ch.6, 103-110
[3]J. R. Wolpaw, D. J. McFarland, Multichannel EEG-based brain-computer communication. Electroencephalography and clinical Neurophysiology, 1994.90(6):p.444-449.
[4]J. R. Wolpaw, D. J. McFarland, Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. Proceedings of the National Academy of Sciences of the United States of America, 2004. 101(51):p. 17849-17854.
[5]D. J. McFarland, W. A. Sarnacki, J. R. Wolpaw, Brain-computer interface (BCI) operation:optimizing information transfer rates. Biological psychology, 2003.63(3):p. 237-251.
[6]E. W. Sellers, E. Donchin, A P300-based brain-computer interface: initial tests by ALS patients. Clinical neurophysiology,2006. 117(3): p. 538-548.
[7]D. J. Krusienski, E. W. Seller, F. Cabestaing, et al., A comparison of classification techniques for the P300 Speller. Journal of neural engineering, 2006. 3:p. 299-305.
[8]L. A. Farwell, E. Donchin, Talking off the top of your head:toward a mental prosthesis utilizing event-related brain potentials. Electroencephalography and clinical Neurophysiology,1988.70(6):p. 510-523.
[9]T. M. Vaughan, D. J. McFarland, G. Schalk, et al., The wadsworth BCI research and development program:at home with BCI. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 2006. 14(2):p. 229-233.
[10]G. Pfurtscheller, C. Neuper, Motor imagery and direct brain-computer communication. Proceedings of the IEEE, 2001.89(7):p.1123-1134.
[11]G. Pfurtscheller, G. R. Muller-Putz, A. Schlogl, et al.,15 years of BCI research at Graz university of technology:current projects. Neural Systems and Rehabilitation Engineering, IEEE Transactions on,2006.14(2): p. 205-210.
[12]G. Pfurtscheller, F. L. Silva, Event-related EEG/MEG synchronization and desynchronization:basic principles. Clinical neurophysiology,1999. 110(11):p. 1842-1857.
[13]A. Schlogl, The electroencephalogram and the adaptive autoregressive model:theory and applications. Aachen, Germany:Shaker Verlag,2000.
[14]G. Pfurtscheller, C. Neuper, A. Schlogl, et al., Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. Rehabilitation Engineering, IEEE Transactions on, 1998. 6(3):p. 316-325.
[15]G. Townsend, B. Graimann, G. Pfurtscheller, A comparison of common spatial patterns with complex band power features in a four-class BCI experiment. Biomedical Engineering, IEEE Transactions on, 2006.53(4): p. 642-651.
[16]J. P. Lachaux, E. Rodriguez, J. Martinerie, et al., Measuring phase synchrony in brain signals. Human brain mapping, 1999.8(4):p. 194-208.
[17]B. Blankertz, M. Tangermann, C. Vidaurre, et al., Detecting Mental States by Machine Learning Techniques:The Berlin Brain - Computer Interface. Brain-Computer Interfaces:p. 113-135.
[18]B. Blankertz, G. Dornhege, S. Lemm, et al., The Berlin Brain-Computer Interface:Machine learning based detection of user specific brain states. Journal of Universal Computer Science, 2006. 12(6):p. 581-607.
[19]B. Blankertz, G. Dornhege, M. Krauledat, et al., The non-invasive Berlin Brain-Computer Interface:Fast acquisition of effective performance in untrained subjects. Neurolmage,2007.37(2):p.539-550.
[20]B. Blankertz, G. Dornhege, M. Krauledat, et al., The Berlin Brain-Computer Interface:EEG-based communication without subject training. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 2006. 14(2):p. 147-152.
[21]B. Blankertz, F. Losch, M. Krauledat, et al., The Berlin Brain--Computer Interface:accurate performance from first-session in BCI-naive subjects. Biomedical Engineering, IEEE Transactions on, 2008. 55(10):p.2452-2462.
[22]A. Schlogl, C. Brunner, Biosig:A free and open source software library for BCI research. Computer, 2008.41(10):p.44-50.
[23]G. Schalk, D. J. McFarland, T. Hinterberger, et al., BCI2000:a general-purpose brain-computer interface (BCI) system. Biomedical Engineering, IEEE Transactions on,2004.51(6):p.1034-1043.
[24]B. Blankertz, K. R. Muller, G. Curio, et al., The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. Biomedical Engineering, IEEE Transactions on,2004.51 (6):p. 1044-1051.
[25]E.J. Speckmann, C. E. Elger, Introduction of the neurophysiological basis of the EEG and DC potentials. in Electroencephalography:Basic principles, clinical applications, and related fields, edited by E. Niedermeyer, F.H. Lopes da Silva. Philadelphia: Lippincott Williams & Wilkins,4th edition 1999.
[26]G. M. Shepherd, The synaptic organization of the brain. Oxford University Press. USA,2004.
[27]赵伦,ERP实验教程.天津社会科学院出版社.天津,2004：p.1-2.
[28]B. Graimann, B. Allison, G. Pfurtscheller, Brain-Computer Interfaces:A Gentle Introduction. Brain-Computer Interfaces:p.1-27.
[29]R.W. Homan, J. Herman, P. Purdy, Cerebral location of international 10-20 system electrode placement. Electroencephalography and clinical Neurophysiology, 1987.66(4):p.376-382.
[30]A. Kiibler, B. Kotchoubey, J. Kaiser, et al., Brain-computer communication: Unlocking the locked in. Psychological Bulletin,2001.127(3):p.358-375.
[31]N. Birbaumer, T. Hinterberger, A. Kubler, et al., The thought-translation device (TTD):neurobehavioral mechanisms and clinical outcome. Neural Systems and Rehabilitation Engineering, IEEE Transactions on,2003.11(2):p.120-123.
[32]T. Hinterberger, R. Veit, U. Strehl, et al., Brain areas activated in fMRI during self-regulation of slow cortical potentials (SCPs). Experimental brain research,2003. 152(1):p.113-122.
[33]U. Strehl, T. Trevorrow, R. Veit, et al., Deactivation of brain areas during self-regulation of slow cortical potentials in seizure patients. Applied psychophysiology and biofeedback,2006.31(1):p.85-94.
[34]E. Niedermeyer, The Normal EEG of the Waking Adult. In Electroencephalography:Basic principles, clinical applications, and related fields, edited by E. Niedermeyer, F.H. Lopes da Silva. Philadelphia:Lippincott Williams & Wilkins,5th edition.2005.
[35]J. W. Kozelka, T. A. Pedley, Beta and mu rhythms. Journal of Clinical Neurophysiology,1990.7(2):p.191-207.
[36]Jeon, Y., et al., Event-related (De) synchronization (ERD/ERS) during motor imagery tasks:Implications for brain-computer interfaces. International Journal of Industrial Ergonomics,2011.
[37]D. J. McFarland, G. W. Neat, R. F. Read, et al., An EEG-based method for graded cursor control. Psychobiology,1993.21:p.77-81.
[38]J. Polich, Updating P300:an integrative theory of P3a and P3b. Clinical neurophysiology,2007.118(10):p.2128-2148.
[39]J. Polich, J. R. Criado, Neuropsychology and neuropharmacology of P3a and P3b. International Journal of Psychophysiology,2006.60(2):p.172-185.
[40]R der, B., et al., Event-related potentials during auditory and somatosensory discrimination in sighted and blind human subjects. Cognitive Brain Research,1996. 4(2):p.77-93.
[41]Y. Wang, R. Wang, X. G.ao, et al., A practical VEP-based brain-computer interface. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 2006.14(2):p.234-240.
[42]X. Gao, D. Xu, M. Cheng, et al., A BCI-based environmental controller for the motion-disabled. Neural Systems and Rehabilitation Engineering, IEEE Transactions on,2003.11(2):p.137-140.
[43]O. David, J. M. Kilner, K. J. Friston, Mechanisms of evoked and induced responses in MEG/EEG. NeuroImage,2006.31(4):p.1580-1591.
[44]G. Pfurtscheller, The cortical activation model (CAM). Progress in brain research, 2006.159:p.19-27.
[45]C. Neuper, G.R. Miiller-Putz, R. Scherer, et al., Motor imagery and EEG-based control of spelling devices and neuroprostheses. Progress in brain research,2006.159: p.393-409.
[46]B. Graimann, G. Pfurtscheller, Quantification and visualization of event-related changes in oscillatory brain activity in the time-frequency domain. Progress in brain research,2006.159:p.79-97.
[47]C. S. Herrmann, A. Mecklinger, E. Pfeifer. Gamma responses and ERPs in a visual classification task. Clin Neurophysiol,1999.110(4):p.636-642.
[48]C. Torrence, G.P. Compo. A practical guide to wavelet analysis. Bulletin of the American Meteorological Society,1998.79(1):p.61-78.
[49]蒋永华,汤宝平,刘文艺,et al.基于参数优化Morlet小波变换的故障特征提取方法.仪器仪表学报,2010.31(1)：p.56-61.
[50]张贤达,现代信号处理,第二版.清华大学出版社,2002.
[51]M. Morup, L. K. Hansen, C. S. Herrmann, et al.. Parallel factor analysis as an exploratory tool for wavelet transformed event-related EEG. Neurolmage,2006.29(3): p.938-947.
[52]N. D. Sidiropoulos, R. Bro. On the uniqueness of multilinear decomposition of N-way arrays. Journal of chemometrics,2000.14(3):p.229-239.
[53]R. A. Harshman, M. E. Lundy. Data preprocessing and the extended PARAFAC model. Research Methods for Multimode Data Analysis, Praeger,1984.
[54]R. Bro. Multi-way analysis in the food industry:models, algorithms, and applications. PhD Thesis. University of Amsterdam and Royal veterinary and Agricultural University,1998.
[55]S. Sanei, J. Chambers, EEG signal processing. John Wiley & Sons, New York, 2007.
[56]G. D. Forney. The viterbi algorithm. Proceedings of the IEEE,1973.61(3):p. 268-278.
[57]R. Duda, P. Hart, D. Stork. Pattern Classication,2nd ed. John Wiley & Sons, New York,2001.
[58]S. Lemm, C. Schafer, G. Curio. Probabilistic modeling of sensorimotor μ-rhythms for classification of imaginary hand movements. Biomedical Engineering, IEEE Transactions on,2004.51(6):p.1077-1080.
[59]H. Lee, Y. -D. Kim, A. Cichocki, et al.. Nonnegative tensor factorization for continuous EEG classification. International journal of neural systems,2007.17(4):p. 305-318.
[60]R. A. Harshman. PARAFAC2:Mathematical and technical notes. UCLA Working Papers in Phonetics,1972.22:p.30-44.
[2]J. R. Millan, P. W. Ferrez, A. Buttfield, The IDIAP Brain-Computer Interface:An Asynchronous Multiclass Approach. In Toward brain-computer interfacing, edited by G. Dornhege, J. D. R. Millan, T. Hinterberger, et al., Cambridge, MA:MIT Press,2007, ch.6, 103-110
[3]J. R. Wolpaw, D. J. McFarland, Multichannel EEG-based brain-computer communication. Electroencephalography and clinical Neurophysiology, 1994.90(6):p.444-449.
[4]J. R. Wolpaw, D. J. McFarland, Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. Proceedings of the National Academy of Sciences of the United States of America, 2004. 101(51):p. 17849-17854.
[5]D. J. McFarland, W. A. Sarnacki, J. R. Wolpaw, Brain-computer interface (BCI) operation:optimizing information transfer rates. Biological psychology, 2003.63(3):p. 237-251.
[6]E. W. Sellers, E. Donchin, A P300-based brain-computer interface: initial tests by ALS patients. Clinical neurophysiology,2006. 117(3): p. 538-548.
[7]D. J. Krusienski, E. W. Seller, F. Cabestaing, et al., A comparison of classification techniques for the P300 Speller. Journal of neural engineering, 2006. 3:p. 299-305.
[8]L. A. Farwell, E. Donchin, Talking off the top of your head:toward a mental prosthesis utilizing event-related brain potentials. Electroencephalography and clinical Neurophysiology,1988.70(6):p. 510-523.
[9]T. M. Vaughan, D. J. McFarland, G. Schalk, et al., The wadsworth BCI research and development program:at home with BCI. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 2006. 14(2):p. 229-233.
[10]G. Pfurtscheller, C. Neuper, Motor imagery and direct brain-computer communication. Proceedings of the IEEE, 2001.89(7):p.1123-1134.
[11]G. Pfurtscheller, G. R. Muller-Putz, A. Schlogl, et al.,15 years of BCI research at Graz university of technology:current projects. Neural Systems and Rehabilitation Engineering, IEEE Transactions on,2006.14(2): p. 205-210.
[12]G. Pfurtscheller, F. L. Silva, Event-related EEG/MEG synchronization and desynchronization:basic principles. Clinical neurophysiology,1999. 110(11):p. 1842-1857.
[13]A. Schlogl, The electroencephalogram and the adaptive autoregressive model:theory and applications. Aachen, Germany:Shaker Verlag,2000.
[14]G. Pfurtscheller, C. Neuper, A. Schlogl, et al., Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. Rehabilitation Engineering, IEEE Transactions on, 1998. 6(3):p. 316-325.
[15]G. Townsend, B. Graimann, G. Pfurtscheller, A comparison of common spatial patterns with complex band power features in a four-class BCI experiment. Biomedical Engineering, IEEE Transactions on, 2006.53(4): p. 642-651.
[16]J. P. Lachaux, E. Rodriguez, J. Martinerie, et al., Measuring phase synchrony in brain signals. Human brain mapping, 1999.8(4):p. 194-208.
[17]B. Blankertz, M. Tangermann, C. Vidaurre, et al., Detecting Mental States by Machine Learning Techniques:The Berlin Brain - Computer Interface. Brain-Computer Interfaces:p. 113-135.
[18]B. Blankertz, G. Dornhege, S. Lemm, et al., The Berlin Brain-Computer Interface:Machine learning based detection of user specific brain states. Journal of Universal Computer Science, 2006. 12(6):p. 581-607.
[19]B. Blankertz, G. Dornhege, M. Krauledat, et al., The non-invasive Berlin Brain-Computer Interface:Fast acquisition of effective performance in untrained subjects. Neurolmage,2007.37(2):p.539-550.
[20]B. Blankertz, G. Dornhege, M. Krauledat, et al., The Berlin Brain-Computer Interface:EEG-based communication without subject training. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 2006. 14(2):p. 147-152.
[21]B. Blankertz, F. Losch, M. Krauledat, et al., The Berlin Brain--Computer Interface:accurate performance from first-session in BCI-naive subjects. Biomedical Engineering, IEEE Transactions on, 2008. 55(10):p.2452-2462.
[22]A. Schlogl, C. Brunner, Biosig:A free and open source software library for BCI research. Computer, 2008.41(10):p.44-50.
[23]G. Schalk, D. J. McFarland, T. Hinterberger, et al., BCI2000:a general-purpose brain-computer interface (BCI) system. Biomedical Engineering, IEEE Transactions on,2004.51(6):p.1034-1043.
[24]B. Blankertz, K. R. Muller, G. Curio, et al., The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. Biomedical Engineering, IEEE Transactions on,2004.51 (6):p. 1044-1051.
[25]E.J. Speckmann, C. E. Elger, Introduction of the neurophysiological basis of the EEG and DC potentials. in Electroencephalography:Basic principles, clinical applications, and related fields, edited by E. Niedermeyer, F.H. Lopes da Silva. Philadelphia: Lippincott Williams & Wilkins,4th edition 1999.
[26]G. M. Shepherd, The synaptic organization of the brain. Oxford University Press. USA,2004.
[27]赵伦,ERP实验教程.天津社会科学院出版社.天津,2004：p.1-2.
[28]B. Graimann, B. Allison, G. Pfurtscheller, Brain-Computer Interfaces:A Gentle Introduction. Brain-Computer Interfaces:p.1-27.
[29]R.W. Homan, J. Herman, P. Purdy, Cerebral location of international 10-20 system electrode placement. Electroencephalography and clinical Neurophysiology, 1987.66(4):p.376-382.
[30]A. Kiibler, B. Kotchoubey, J. Kaiser, et al., Brain-computer communication: Unlocking the locked in. Psychological Bulletin,2001.127(3):p.358-375.
[31]N. Birbaumer, T. Hinterberger, A. Kubler, et al., The thought-translation device (TTD):neurobehavioral mechanisms and clinical outcome. Neural Systems and Rehabilitation Engineering, IEEE Transactions on,2003.11(2):p.120-123.
[32]T. Hinterberger, R. Veit, U. Strehl, et al., Brain areas activated in fMRI during self-regulation of slow cortical potentials (SCPs). Experimental brain research,2003. 152(1):p.113-122.
[33]U. Strehl, T. Trevorrow, R. Veit, et al., Deactivation of brain areas during self-regulation of slow cortical potentials in seizure patients. Applied psychophysiology and biofeedback,2006.31(1):p.85-94.
[34]E. Niedermeyer, The Normal EEG of the Waking Adult. In Electroencephalography:Basic principles, clinical applications, and related fields, edited by E. Niedermeyer, F.H. Lopes da Silva. Philadelphia:Lippincott Williams & Wilkins,5th edition.2005.
[35]J. W. Kozelka, T. A. Pedley, Beta and mu rhythms. Journal of Clinical Neurophysiology,1990.7(2):p.191-207.
[36]Jeon, Y., et al., Event-related (De) synchronization (ERD/ERS) during motor imagery tasks:Implications for brain-computer interfaces. International Journal of Industrial Ergonomics,2011.
[37]D. J. McFarland, G. W. Neat, R. F. Read, et al., An EEG-based method for graded cursor control. Psychobiology,1993.21:p.77-81.
[38]J. Polich, Updating P300:an integrative theory of P3a and P3b. Clinical neurophysiology,2007.118(10):p.2128-2148.
[39]J. Polich, J. R. Criado, Neuropsychology and neuropharmacology of P3a and P3b. International Journal of Psychophysiology,2006.60(2):p.172-185.
[40]R der, B., et al., Event-related potentials during auditory and somatosensory discrimination in sighted and blind human subjects. Cognitive Brain Research,1996. 4(2):p.77-93.
[41]Y. Wang, R. Wang, X. G.ao, et al., A practical VEP-based brain-computer interface. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 2006.14(2):p.234-240.
[42]X. Gao, D. Xu, M. Cheng, et al., A BCI-based environmental controller for the motion-disabled. Neural Systems and Rehabilitation Engineering, IEEE Transactions on,2003.11(2):p.137-140.
[43]O. David, J. M. Kilner, K. J. Friston, Mechanisms of evoked and induced responses in MEG/EEG. NeuroImage,2006.31(4):p.1580-1591.
[44]G. Pfurtscheller, The cortical activation model (CAM). Progress in brain research, 2006.159:p.19-27.
[45]C. Neuper, G.R. Miiller-Putz, R. Scherer, et al., Motor imagery and EEG-based control of spelling devices and neuroprostheses. Progress in brain research,2006.159: p.393-409.
[46]B. Graimann, G. Pfurtscheller, Quantification and visualization of event-related changes in oscillatory brain activity in the time-frequency domain. Progress in brain research,2006.159:p.79-97.
[47]C. S. Herrmann, A. Mecklinger, E. Pfeifer. Gamma responses and ERPs in a visual classification task. Clin Neurophysiol,1999.110(4):p.636-642.
[48]C. Torrence, G.P. Compo. A practical guide to wavelet analysis. Bulletin of the American Meteorological Society,1998.79(1):p.61-78.
[49]蒋永华,汤宝平,刘文艺,et al.基于参数优化Morlet小波变换的故障特征提取方法.仪器仪表学报,2010.31(1)：p.56-61.
[50]张贤达,现代信号处理,第二版.清华大学出版社,2002.
[51]M. Morup, L. K. Hansen, C. S. Herrmann, et al.. Parallel factor analysis as an exploratory tool for wavelet transformed event-related EEG. Neurolmage,2006.29(3): p.938-947.
[52]N. D. Sidiropoulos, R. Bro. On the uniqueness of multilinear decomposition of N-way arrays. Journal of chemometrics,2000.14(3):p.229-239.
[53]R. A. Harshman, M. E. Lundy. Data preprocessing and the extended PARAFAC model. Research Methods for Multimode Data Analysis, Praeger,1984.
[54]R. Bro. Multi-way analysis in the food industry:models, algorithms, and applications. PhD Thesis. University of Amsterdam and Royal veterinary and Agricultural University,1998.
[55]S. Sanei, J. Chambers, EEG signal processing. John Wiley & Sons, New York, 2007.
[56]G. D. Forney. The viterbi algorithm. Proceedings of the IEEE,1973.61(3):p. 268-278.
[57]R. Duda, P. Hart, D. Stork. Pattern Classication,2nd ed. John Wiley & Sons, New York,2001.
[58]S. Lemm, C. Schafer, G. Curio. Probabilistic modeling of sensorimotor μ-rhythms for classification of imaginary hand movements. Biomedical Engineering, IEEE Transactions on,2004.51(6):p.1077-1080.
[59]H. Lee, Y. -D. Kim, A. Cichocki, et al.. Nonnegative tensor factorization for continuous EEG classification. International journal of neural systems,2007.17(4):p. 305-318.
[60]R. A. Harshman. PARAFAC2:Mathematical and technical notes. UCLA Working Papers in Phonetics,1972.22:p.30-44.