基于运动想象的脑—机接口系统模式识别算法研究
|
摘要
脑-机接口(brain-computer interface, BCI)是一种不依赖于正常的由外围神经和肌肉组成的输出通道的通讯系统。它在医学领域、人工智能的实现以及新型的娱乐研究等方面有重要应用,其实现涉及多个学科,触及许多前沿技术。因此BCI技术的研究具有科学与应用的双重价值,已经在国际上引起了广泛的兴趣并获得了快速的发展。其中,信号处理环节是实现BCI系统、提高系统可靠性与性能的关键,其实质是BCI信号的模式识别,主要包括三部分:信号预处理、特征提取和分类,本文着重研究后两部分,以期提高BCI系统的识别率。针对BCI发展过程中遇到的主要问题,如提高系统模式识别的精度和鲁棒性、缩短训练时间、发展异步工作模式下BCI系统的模式识别等,本文开展了如下工作:
1、针对脑电信号噪声强、数据分布复杂、维数高、训练样本相对不足等特点,本文提出了两种不同的运动相关电位(movement related potentials, MRPs)特征提取算法——邻域空间模式和自适应空间模式算法。前者基于流形学习思想,利用样本向量之间的邻域关系和标签信息构造目标函数确定映射矩阵,不依赖于样本的分布;后者采用特征向量的欧式距离估计样本之间的相似关系,并基于这种关系建立目标函数,通过自适应迭代确定样本之间的邻域关系和最佳的特征投影矩阵,该算法的实施同样不需要对样本数据的分布做任何假设,还给出了高维EEG信号数据相似性的一种有效度量方法。实验证明,这两种算法均能增强MRPs特征的鲁棒性,提高分类精度;
2、事件相关失同步/同步(event-related desynchronization/synchronization, ERD/ERS)和MRPs是BCI特征提取中的两大生理背景基础,它们都是在运动/运动想象前后或者过程当中产生,在某一特定的时间、某些电极位置、某一特定频段,特性表现比较明显,即对时空频信息敏感。针对这些性质,本文提出广义时空特征提取算法(general temporal- spatial extraction, GTSE),同时优化时空判别信息。ERD/ERS和MRPs的特性不同,针对它们的GTSE算法也不同。实验结果证明,GTSE算法能有效捕捉ERD/ERS和MRPs的时频特性,有效提高分类精度。
3、针对BCI发展过程中缩短训练时间的要求,本文提出了两种针对BCI系统的半监督学习算法,一是基于联合特征的半监督学习算法,选择置信度高的无标样本(连同预测标签)迭代扩充训练集,并基于现有的训练集更新特征提取器和分类器,从而达到利用大量未标样本和少量的有标训练集学习模式识别系统参数的目的;二是针对MRPs特征的半监督特征提取算法,直接利用标签和未标签样本信息优化特征提取模型的参数。实验结果证明,基于少量的有标签样本,这两种半监督学习算法都能取得较为满意的分类效果。
4、异步BCI系统的模式识别是近期的研究热点,其难点之一是识别实验过程中用户思维想象状态和空闲状态。由于空闲状态具有多样性,往往没有有效的空闲状态样本。本文提出了一种自适应的空闲状态检测方法。它以训练集(只有各类运动想象样本)的正确检测率和正确分类样本的类内散度为指标,根据接受者操作特性曲线的最佳临界点选择原则,构造目标函数,确定三分类器的上下阈值。为了进一步优化分类结果,该算法还采用了模糊化技术对预测标签进行处理。实验结果证明了算法的有效性。
总的说来,本论文着眼于EEG作为生物医学信号固有的处理难点和BCI技术的进一步发展和实际应用推广过程中出现的新研究课题,研究更加有效、实用的BCI系统特征提取和分类方法,并用实验证明相关算法的有效性。
A brain-computer interface (BCI) is a communication system. The messages or commands in the system sends from an individual to the external world not passing through the brain’s normal output pathways of nerves system and muscles. The BCI has very important application in medical, artificial intelligence, novel entertainment and so on. Its implement refers to many subjects and frontier technologies. So the study about BCI has both science and application value. It has attracted much interest and been well developed. Signal processing is the key issue for implementing a BCI system as well as improving its reliability and performance, whose essence is the signal pattern recognition. It mainly includes three parts: signal preprocess, feature extraction and classification. The study emphasis of this paper is concentrated on the last two parts and is proved of improving the recognition accuracy of BCI system. Focusing on the main problem of BCI signal processing methods during the development, such as how to enhance classification accuracies and robustness, reduce training time and develop new effective methods for the pattern recognition in asynchronous modes, and so on, our research results and main contribution include:
1. Focusing on the EEG characteristic, such as fully noisy, complicated data distribution, high dimensions, relative-un-abound training samples, and so on, two algorithms for the extraction of movement related potentials (MRPs) have been proposed: neighborhood spatial pattern algorithm and adapting spatial pattern algorithm. Based on the idea of manifold learning, the former one constructs the target function to estimate the optimal map matrix, only utilizing the neighborhood and label information, while not depending on the underlying data distribution. The latter estimates the similarity between samples by the corresponding features’distance, and then constructs the target function based on this similar relationship. It adaptively determines the neighbor relationship and the optimal direction via iterations. Its implement also doesn’t need any assumption about the underlying data distribution, but proposes an alternative for the similar measurement of EEG data with high dimension. Experimental results show that: the two algorithms all strengthen MRPs feature’s robustness, and improve classification accuracy.
2. Event-related desynchronization/synchronization (ERD/ERS) and MRPs are two of the most important neurophysiological backgrounds of motor imagine utilized in the feature extraction of BCI pattern recognition. They appear before/after or during the process of motor imagery. Their characteristics are distinct at special temporal area, electrodes and band of frequency, i.e., they are sensitive to time, space and frequency. Based on these, we proposed general temporal-spatial extraction (GTSE) algorithm which can optimize temporal and spatial discriminative information together. The characteristics of ERD/ERS and MRPs are different, so the corresponding GTSE algorithms are different, too. Experimental results show that: the algorithms can catch more essential discriminative information of ERD/ERS and MRPs, and efficiently improve classification accuracy.
3. Focusing on reducing training time to meet the requirement in the development of BCI, two semi-supervised learning algorithms for BCI are proposed. One is a learning algorithm based on combining-features. It chooses the most confident unlabeled samples (with their predicted labels) to enlarge the training set via iterations, and then based on the enlarged training set, retrains the parameters of the feature extractor and classifier. And consequently it gains its ends of using the information of large number of unlabeled samples with a few labeled samples to train feature extractor and classifier. The other is a semi-supervised feature extraction algorithm for MRPs. It straightly utilizes the information of labeled and unlabeled samples together to optimize the parameters of feature extraction model. Experimental results show that: based on a few labeled samples, the two semi-supervised learning algorithms can also obtain favorable classification accuracy.
4. The pattern recognition of asynchronization BCI system recently is a hot topic. One of its biggest challenges is to discriminate which state the user is during experiment processing: imagining or idle? Because of the diversity of idle state, there are no effective training samples for idle sate. A novel algorithm is proposed for the detection of the idle state. Using the classification accuracy and the within-class scatter of the samples classified correctly in the training set (only with motor imagine samples) as two indexes, the algorithm constructs the target function according to the chosen criterion for the optimal operating point of the receiver operating characteristic curve, and determines the minimal/maximal decision thresholds for classification. To further optimize the classification effect, the algorithm treats the prediction labels by a fuzzy way. Its efficiency was demonstrated by experiment.
To sum up, in this paper, we studied feature extraction and classification algorithms for BCI, focusing on the processing challenges including intrinsic nodus for EEG as biomedicine signal and the topics come forth from further development and practical application of BCI technique. The efficiency of the algorithms was all demonstrated by related experiments.
1、针对脑电信号噪声强、数据分布复杂、维数高、训练样本相对不足等特点,本文提出了两种不同的运动相关电位(movement related potentials, MRPs)特征提取算法——邻域空间模式和自适应空间模式算法。前者基于流形学习思想,利用样本向量之间的邻域关系和标签信息构造目标函数确定映射矩阵,不依赖于样本的分布;后者采用特征向量的欧式距离估计样本之间的相似关系,并基于这种关系建立目标函数,通过自适应迭代确定样本之间的邻域关系和最佳的特征投影矩阵,该算法的实施同样不需要对样本数据的分布做任何假设,还给出了高维EEG信号数据相似性的一种有效度量方法。实验证明,这两种算法均能增强MRPs特征的鲁棒性,提高分类精度;
2、事件相关失同步/同步(event-related desynchronization/synchronization, ERD/ERS)和MRPs是BCI特征提取中的两大生理背景基础,它们都是在运动/运动想象前后或者过程当中产生,在某一特定的时间、某些电极位置、某一特定频段,特性表现比较明显,即对时空频信息敏感。针对这些性质,本文提出广义时空特征提取算法(general temporal- spatial extraction, GTSE),同时优化时空判别信息。ERD/ERS和MRPs的特性不同,针对它们的GTSE算法也不同。实验结果证明,GTSE算法能有效捕捉ERD/ERS和MRPs的时频特性,有效提高分类精度。
3、针对BCI发展过程中缩短训练时间的要求,本文提出了两种针对BCI系统的半监督学习算法,一是基于联合特征的半监督学习算法,选择置信度高的无标样本(连同预测标签)迭代扩充训练集,并基于现有的训练集更新特征提取器和分类器,从而达到利用大量未标样本和少量的有标训练集学习模式识别系统参数的目的;二是针对MRPs特征的半监督特征提取算法,直接利用标签和未标签样本信息优化特征提取模型的参数。实验结果证明,基于少量的有标签样本,这两种半监督学习算法都能取得较为满意的分类效果。
4、异步BCI系统的模式识别是近期的研究热点,其难点之一是识别实验过程中用户思维想象状态和空闲状态。由于空闲状态具有多样性,往往没有有效的空闲状态样本。本文提出了一种自适应的空闲状态检测方法。它以训练集(只有各类运动想象样本)的正确检测率和正确分类样本的类内散度为指标,根据接受者操作特性曲线的最佳临界点选择原则,构造目标函数,确定三分类器的上下阈值。为了进一步优化分类结果,该算法还采用了模糊化技术对预测标签进行处理。实验结果证明了算法的有效性。
总的说来,本论文着眼于EEG作为生物医学信号固有的处理难点和BCI技术的进一步发展和实际应用推广过程中出现的新研究课题,研究更加有效、实用的BCI系统特征提取和分类方法,并用实验证明相关算法的有效性。
A brain-computer interface (BCI) is a communication system. The messages or commands in the system sends from an individual to the external world not passing through the brain’s normal output pathways of nerves system and muscles. The BCI has very important application in medical, artificial intelligence, novel entertainment and so on. Its implement refers to many subjects and frontier technologies. So the study about BCI has both science and application value. It has attracted much interest and been well developed. Signal processing is the key issue for implementing a BCI system as well as improving its reliability and performance, whose essence is the signal pattern recognition. It mainly includes three parts: signal preprocess, feature extraction and classification. The study emphasis of this paper is concentrated on the last two parts and is proved of improving the recognition accuracy of BCI system. Focusing on the main problem of BCI signal processing methods during the development, such as how to enhance classification accuracies and robustness, reduce training time and develop new effective methods for the pattern recognition in asynchronous modes, and so on, our research results and main contribution include:
1. Focusing on the EEG characteristic, such as fully noisy, complicated data distribution, high dimensions, relative-un-abound training samples, and so on, two algorithms for the extraction of movement related potentials (MRPs) have been proposed: neighborhood spatial pattern algorithm and adapting spatial pattern algorithm. Based on the idea of manifold learning, the former one constructs the target function to estimate the optimal map matrix, only utilizing the neighborhood and label information, while not depending on the underlying data distribution. The latter estimates the similarity between samples by the corresponding features’distance, and then constructs the target function based on this similar relationship. It adaptively determines the neighbor relationship and the optimal direction via iterations. Its implement also doesn’t need any assumption about the underlying data distribution, but proposes an alternative for the similar measurement of EEG data with high dimension. Experimental results show that: the two algorithms all strengthen MRPs feature’s robustness, and improve classification accuracy.
2. Event-related desynchronization/synchronization (ERD/ERS) and MRPs are two of the most important neurophysiological backgrounds of motor imagine utilized in the feature extraction of BCI pattern recognition. They appear before/after or during the process of motor imagery. Their characteristics are distinct at special temporal area, electrodes and band of frequency, i.e., they are sensitive to time, space and frequency. Based on these, we proposed general temporal-spatial extraction (GTSE) algorithm which can optimize temporal and spatial discriminative information together. The characteristics of ERD/ERS and MRPs are different, so the corresponding GTSE algorithms are different, too. Experimental results show that: the algorithms can catch more essential discriminative information of ERD/ERS and MRPs, and efficiently improve classification accuracy.
3. Focusing on reducing training time to meet the requirement in the development of BCI, two semi-supervised learning algorithms for BCI are proposed. One is a learning algorithm based on combining-features. It chooses the most confident unlabeled samples (with their predicted labels) to enlarge the training set via iterations, and then based on the enlarged training set, retrains the parameters of the feature extractor and classifier. And consequently it gains its ends of using the information of large number of unlabeled samples with a few labeled samples to train feature extractor and classifier. The other is a semi-supervised feature extraction algorithm for MRPs. It straightly utilizes the information of labeled and unlabeled samples together to optimize the parameters of feature extraction model. Experimental results show that: based on a few labeled samples, the two semi-supervised learning algorithms can also obtain favorable classification accuracy.
4. The pattern recognition of asynchronization BCI system recently is a hot topic. One of its biggest challenges is to discriminate which state the user is during experiment processing: imagining or idle? Because of the diversity of idle state, there are no effective training samples for idle sate. A novel algorithm is proposed for the detection of the idle state. Using the classification accuracy and the within-class scatter of the samples classified correctly in the training set (only with motor imagine samples) as two indexes, the algorithm constructs the target function according to the chosen criterion for the optimal operating point of the receiver operating characteristic curve, and determines the minimal/maximal decision thresholds for classification. To further optimize the classification effect, the algorithm treats the prediction labels by a fuzzy way. Its efficiency was demonstrated by experiment.
To sum up, in this paper, we studied feature extraction and classification algorithms for BCI, focusing on the processing challenges including intrinsic nodus for EEG as biomedicine signal and the topics come forth from further development and practical application of BCI technique. The efficiency of the algorithms was all demonstrated by related experiments.
引文
[1]罗焕敏.人类脑计划:神经科学领域划时代的里程碑[J].暨南大学学报(医学版),2002, 23(6): 31-34
[2] Berger H.. Uber das Electrenkephalogramm des Menchen[J]. Arch Psychiat Nervenkr, 1929,(87): 527-570
[3] Vidal J.J.. Real-time detection of brain events in EEG[C]. Proceedings of the IEEE, 1977,65(5): 633-664
[4] Wolpaw J.R., Birbaumer N., Mcfarland W.J., et al. Brain-computer interfaces for communication and control[J]. Clin. Neurophysiol., 2002, vol.113:767-791
[5]杨立才,李佰敏,李光林等.脑-机接口技术综述[J].电子学报, 2005, 33(7): 1234-1241
[6]胡剑锋,肖守柏.脑机接口研究概述[J].科技广场,2007,9:1- 4
[7]维基百科.脑机接口[EB/OL]. http://zh.wikipedia.org/wiki/%E8%84%91% E6%9C% BA%E6%8E%A5% E5%8F%A3
[8]杨帮华.自发脑电脑机接口技术及脑电信号识别方法研究[D].上海:上海交通大学, 2006
[9] Fitzpatrick T.. Teenager moves video icons just by imagination hands off [R]. St Louis: Washington University, 2006, 9
[10] Serruya M.D, Donoghue J.P.. Chapter III: Design Principles of a Neuromotor Prosthetic Device in Neuroprosthetics: Theory and Practice. London[M]. England: Imperial College Press, 2003
[11] Müller K.R., Curio G., Blankertz B.. Berlin Brain-computer Interface [DB/OL]. http://www.bbci.de/, 2009-9-8
[12] Farwell L.A., Donchin E.. Talking off the top of your head: Toward a mental prosthesis utilizing event-related brain potentials [J]. Electroencephalograph Clin Neurophysiol. 1998, 70: 510–523
[13] Birbaumer N., Ghanayim N., Hinterberger T et al.. A spelling device for the paralyzed [J]. Nature, 1999, 398: 297–298
[14] Wolpaw J.R., Mcfarkand D.J.. EEG-based brain–computer communication[J]. Electroencephalograph Clin Neurophysiol, 1994, 90: 444–449
[15] George T., Bernhard G., Pfurtscheller G.. Continuous EEG classification during motor imagery-simulation of an asynchronous BCI [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2004, 12(2):258-265
[16] Tsui C.S. L., GAN J. Q.. A synchronous BCI control of a robot simulator with supervised online training [J]. Lecture Notes in Computer Science, 2007, 4881: 125-134
[17]百度百科.事件相关电位[EB/OL]. http://baike.baidu.com/view/1198359.html, 2009-9-10
[18] Wolpaw J.R., McFarland D.J, Neat G.W., et al.. An EEG-based brain-computer interface for cursor control[J]. Electroencephalograph Clin Neurophysiol, 1991, 78: 252-259
[19] Birbaumer N., Hinterberger T., Kübler A., et al.. The thought-translation device (TTD): neurobehavioral mechanisms and clinical outcome[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003,11:120-123
[20] Hinterberger T., Kübler A., Kaiser J., et al.. A brain-computer interface (BCI) for the locked-in: comparison of different EEG classifications for the thought translation device[J]. Clin Neurophysiol, 2003,114:416-425
[21] Sutter E E.. The brain response interface: communication through visually- induced electrical brain response[J]. Journal of Microcomputer Applications, 1992,15:31-45
[22] Neuper C., Schl?gl A., Pfurtscheller G.. Enhancement of left-right sensorimotor EEG differences during feedback-regulated motor imagery[J]. Journal of Clinical Neurophysiology, 1999,16:373-382
[23] Pfurtscheller G., Neuper C., Guger C., et al.. Current trends in Graz brain– computer interface(BCI) research[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2000,8:216-219
[24] Cincotti F., Mattia D., Babiloni C., et al.. The use of EEG modifications due to motor imagery for brain-computer interface[J]. IEEE transactions on neural systems and rehabilitation engineering, 2003, 11:131-133
[25] Kostov A., Polak M.. Parallel man-machine training in development of EEG-based cursor control[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2000,8:203-205
[26] Wolpaw J.R., Birbaumer N., Heetderks W.J.. Brain-computer interface technology: a review of the first international meeting[J]. IEEE Transactions on Rehabilitation Engineering, 2000,8(2): 164-173
[27] Mussa-Ivaldi S.. Real brain for real robots[J].Nature,2000,48(6810):305-306
[28] Vaughan T.M.. Brain-computer interface technology: A review of the second interational meeting[J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11(2): 94-109
[29] Virts J.. The third international meeting on brain-computer interface technology: makinga difference [J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2006,14(2): 126-127
[30] BCI Competitions [DB/OL]. http://www.bbci.de/competition, 2009-9-1
[31] Mason S.G.. A general framework for brain-computer interface design[J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11, (1): 70-85
[32] Pfurtscheller G., Neuper C.. Motor imagery and direct brain-computer communication[C]. presented at Proceedings of the IEEE, 2001,89(7): 1123-1134
[33] Müller G.R., Neuper C., Pfurtscheller G., et al.. Implementation of a telemonitoring system for the control of an EEG-based brain-computer interface[J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11(1): 54-59
[34] Wolpaw J.R., McFarland D.J., Vaughan T.M.. The wadsworth center brain- computer interface (BCI) research and development program [J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003,11(2): 204-207
[35] Vaughan T.M, McFarland D.J., Schalk G., et al.. The wadsworth BCI research and development program: At home with BCI[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006,14(2):229-233
[35] Wolpaw J.R., Birbaumer N., Heetderks W.J.. Brain computer interface technology: a review of the first international meeting[J]. IEEE Transactions on Rehabilitation Engineering 2000, 8(2):164-173
[36] Dornhege G., Benjamin B., Gabriel C.. Speeding up classification of multi-channel brain-computer spatial patterns for slow cortical potentials[C]. Proceedings of the 1st international IEEE EMBS Conference on Neural Engineering, 2003,674: 595-598
[37] Birch G.E., Mason S.G., Borisoff J.F.. Current trends in brain-computer interface research at the Neil Squire foundation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003, 11(2):123-126
[38] Birch G. E., Bozorgzadeh Z., Mason S. G.. Initial oh-line evaluations of the LF-ASD brain-computer interface with able-bodied and spinal-cord subjects using imagined voluntary motor potentials[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2002,10(4):219-224
[39] Mason S.G., Birch G.E.. A brain-controlled switch for asynchronous control applications [J]. IEEE Transactions on Biomedical Engineering, 2000, 47(10): 1297-1306
[40] Birch G.E., Mason S.G.. Brain-computer interface research at the Neil Squire foundation[J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(2):193-195
[41] Borisoff J.F., Mason S.G., Bashashati A.. Brain-computer interface design forasynchronous control applications: improvements to the LF-ASD asynchronous brain switch[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 985-992
[42] Mason, S. G., Bohringer, R., Borisoff, J. F., et al.. Real-time control of a video game with a direct brain-computer interface[J]. Journal of Clinical Neurophysiology, 2004, 21(6): 404-408
[43] Bashashati A., Ward R.K., Birch.G.E.. A new design of the asynchronous brain computer interface using the knowledge of the path of features[C]. Proceedings of the 2nd international IEEE EMBS conference on neural engineering, Arington,2005, 693:101-104
[44]徐丁峰,程明,高小榕.数字信号处理器在脑-机接口系统中的应用[J].北京生物医学工程, 2002,21(4):257-260
[45]赵香花,汪晓光.基于脑-机接口的残疾人环境控制装置的设计[J].中国康复医学杂志, 2004,19(5):324-326
[46]任宇鹏,王广志,程明.基于脑-机接口的康复辅助机械手控制[J].中国康复医学杂志, 2004, 19(5):330-333
[47]程明,高上凯,张琳.基于脑电信号的脑—计算机接口[J].北京生物医学工程, 2000, 19(2):113-118
[48] Ebrahimi T., Vesin J.M., Garcia G.. Brain-computer inyerface in multimedia communication[J]. IEEE Signal Processing Magazine, 2003, 20(1): 14-24
[49] Krepki R., Blankertz B., Curio G., et al.. The Berlin Brain-Computer Interface (BBCI) - towards a new communication channel for online control in gaming applications[J]. Multimedia Tools and Applications, 2007, 33(1): 73-90
[50] Krepki, R., Curio G., Blankertz B., et al. Berlin brain-computer interface-The HCI communication channel for discovery [J]. International Journal of Human-Computer Studies, 2007, 65(5): 460-477
[51]中华网科技.清华研制出脑机接口系统可用思维踢足球[EB/OL]. http://tech.163.com/ 07/0821 /14/ 3ME7AEFD00092CEI.html, 2009-9-2
[52]尧德中.脑功能探测的电学理论与方法[M].北京:科技出版社, 2003
[53] Wolpaw J.R., Birbaumer N., McFarlanda D.J., et al.. Brain–computer interfaces for communication and control[J].Clinical Neurophysiolopgy, 2002, 113:767–791
[54]黄远桂,吴声伶编著.临床脑电图学[M].北京:人民卫生出版社, 1998, 1-9
[55] User Tutorial. EEG Measurement Setup[EB/OL]. http://www.bci2000.org/wiki/ index.php/User_Tutorial:EEG_Measurement_Setup. 2009-9-2
[56]大熊辉雄.临床脑电图学[M].第5版.周锦华译.北京:清华大学出版社,2005:64-66
[57]谭玉玲编著.临床脑电图与脑电地形图学.北京:人民卫生出版社, 1999:16
[58]聂能,尧德中,谢正祥编著.生物医学信号数字处理技术及应用[M].北京:科学出版社, 2005,8
[59] Kübler A., Ghanayim N., Hinterberger T.. The thought translation device (TTD) for completely paralyzed patients[J]. IEEE Transactions on rehabilitation engineering, 2000, 8(2): 190-193
[60] Ho, C. K., Sasaki, M.. Brain-wave bio potentials based mobile robot control: wavelet-neural network pattern recognition approach[C]. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 2001, 3494:322-328
[61] McFarland D.J., Lefkowicz A.T., WolPaw J.R.. Design and operation of an EEG based brain-computer interface (BCI) with digital signal processing technology [J]. Behavior research methods, instruments & computers, 1997, 29(3): 337-345
[62]魏庆国.基于运动想象的脑机接口分类算法的研究[D].北京:清华大学, 2006
[63]张旭东,陆明泉,离散随机信号处理[M].北京:清华大学出版社, 2005,1-400
[64]吴正国.现代信号处理技术:高阶谱、时频分析与小波变换[M].武汉:武汉大学出版社,2003
[65]余英林,谢胜利,蔡汉添等.信号处理新方法导论[M].北京:清华大学出版社, 2004: 255~262
[66] Freeman W.J., Burke B.C., Holmes M.D.. Aperiodic Phase Re-Setting in Scalp EEG of Beta–Gamma Oscillations by State Transitions at Alpha–Theta Rates[J].Human Brain Mapping,2003,19(4):248-272
[67] Mensh, B. D., Werfel, J., Seung, H. S.. BCI competition 2003-Data Set Ia: combining gamma-band power with slow cortical potentials to improve single-trial classification of electroencephalographic signals [J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1052-1056
[68]张贤达,保铮.非平稳信号分析与处理[M].上海:国防工业出版社,1999
[69] Xue J.Z., Zhang H., Zheng C.X., Wavelet packet transform for feature extraction of EEG during mental tasks[C]. presented at Proceedings of the Second International Conference on Machine Learning and Cybernetics, Xi'an,2003, 3268: 360-363
[70] Graimann B., Huggins J.E., Levine S.P.. Toward a direct brain interface based on human subdural recordings and wavelet-packet analysis[J]. IEEE Trans on Biomedical Engineering, 2004, 51(6):954-962
[71]毛大伟.分尺度复杂性及希尔伯特-黄变换在脑电分析中的应用[D].杭州:浙江大学, 2005
[72]沈恩华,脑电的复杂度分析[D].上海:复旦大学, 2004
[73] Lemm S., Blankertz B., Curio G., et al.. Spatio-spectral filters for improving the classification of single trial EEG[J]. IEEE Transactions on Biomedical Engineering, 2005, 52(9):1541-1548
[74] Wang Y., Berg P., Scherg M.. Common spatial subspace decomposition applied to analysis of brain responses under multiple task conditions: a simulation study [J]. Clinical neurophysiology , 1999,112(4): 604-614
[75] Liao X., Yao D. Z., Wu D.. Combining spatial filters for the classification of single-trial EEG in a finger movement task[J]. IEEE Transactions on Biomedical Engineering, 2007, 54(5): 821-831
[76] Burke D.P., Kelly S.P., Chazal P.D., et al.. A parametric feature extraction and classification strategy for brain-computer interfacing[J]. IEEE Transaction on Neural System and Rehabilitation Engineering, 2005, 13(1): 12-17
[77] Webb A., Statistical Pattern Recognition[D]. second edition. England: John Wiley & Sons Ltd, 2002
[78] Barreto A.B., Taberner A.M., Vicente L.M.. Neural network classification of spatio-temporal EEG readiness potentials [A]. Proceedings of the 15th Southern Biomedical Engineering Conference, Dayton ,USA: IEEE,1996: 73– 76
[79]刘红梅.数据挖掘中分类方法探究[J].硅谷,2009,3:56+76
[80]刘红岩,陈剑,陈国青.数据挖掘中的数据分类算法综述[J].清华大学学报(自然科学版), 2002,42(6):727-730
[81]台北荣民总医院教学研究部整合性脑功能实验室.脑电波研究室简介[EB/OL]. http://ibru.vghtpe.gov.tw/chinese/eeg.htm, 2008-10-3
[82] Graimann B., Huggins J.E., Levine S.P.. Visualization of significant ERD/ERS patterns in multichannel EEG and ECoG data [J].Cliniacl Neurophysiology, 2002 113: 43-47
[83] Pfurtscheller G., Lopes da Silva F.H.. Event-related EEG/MEG synchronization and desychronization: Basic principles[J]. Clin Neurophysiol, 1999, 110:1842-1857
[84] Suffczynski P., Kalitzin S., Pfurtscheller G., et al.. Computational model of thalamo-cortical networks: dynamical control of alpha rhythms in relation to focal attention[J]. International Journal of Psychophysiology, 2001, 43(1): 25-40
[85] do Nascimento O. F., Nielsen K. D., Voigt M.. Relationship between plantar-flexortorque generation and the magnitude of the movement-related potentials[J]. Experimental Brain Research, 2005, 160: 154–165
[86] Slobounov S.M., Ray W.J.. Movement-related potentials with reference to isometric force output in discrete and repetitive tasks[J]. Experimental Brain Research, 1998, 123:461–473
[87] do Nascimento O.F., Farina D.. Movement-Related Cortical Potentials Allow Discrimination of Rate of Torque Development in Imaginary Isometric Plantar Flexion[J]. IEEE Transactions on Biomedical Engineering, 2008, 55(11): 2675-2678
[88] Terada K., Lansek R., Johnson K.A., et al., Movement-related cortical potentials associated with voluntary relaxation of foot muscles[J]. Clinical Neurophysiology, 1999, 110(3): 397-403
[89] Cunnington, R., Ikeda A., Yazawa S., et al.. Movement-related potentials in Parkinson's disease-motor imagery and movement preparation[J]. Brain, 1997, 120: 1339-1353
[90] Shibasaki H., Barrett G., Halliday E., Halliday AM.. Cortical potentials associated with voluntary foot movement in man[J]. Electroencephalograph Clin Neurophysiol, 1981, 52:507–516
[91] Cunnington R., Iansek R., Bradshaw J. L., Phillips J. G.. Movement-related potentials associated with movement preparation and motor imagery[J]. Experimental Brain Research, 1996, 111:429–436
[92] Wang Y., Zhang Z., Li T., et al. BCI competition 2003-data set IV:An algorithm based on CSSD and FDA for classifying single-trial EEG[J]. IEEE Transactions on Biomedical Engineering, 2004,51(6): 1081-1086
[93] Dornhege G., Blankertz B., Curio G., et al.. Combining features for BCI[A]. Proceedings of Advances in Neural Information Processing Systems (NIPS02)[C]. Cambridge: MIT Press, 2003,15: 1115–1122
[94] Fu Y., Yan S. C., Huang T. S.. Classification and feature extraction by simplexization [J]. IEEE Transactions on Information Forensics and Security, 2008, 3(1): 91-100
[95] Roweis S. T., Saul L. K.. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 290: 323—2326
[96] Wang F., Zhang C.S.. Label Propagation through linear neighborhoods [J]. IEEE Transactions on Knowledge and Data Engineering, 2008, 20: 55-67
[97] He X.F., Niyogi P.. Locality preserving projection [C]. in: Proceedings of the Conference on Advances in Neural Information Processing Systems, 2003. 16: 153-160
[98] Fraunhofer-FIRST, Intelligent Data Analysis Group, Freie Universitat Berlin, Departmentof Neuropology, et al. Data set [EB/OL]. http://ida.first.fraunhofer.de/ projects/bci/competition_ii/berlin_desc.html, 2009-9-8
[99] Fraunhofer-FIRST, Intelligent Data Analysis Group. EEG Classification for self-paced key typing [EB/OL]. http://home.ustc.edu.cn/~cplee/, 2009-9-8
[100] Masashi S.. Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis[J]. Journal of Machine Learning Research, 2007, 8: 1027-1061
[101] Yan S. C., Xu D.B., Zhang Y., et al.. Graph Embedding and Extensions: A General Framework for Dimensionality Reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence., 2007, 29(1):40-51
[102]边肇祺,张学工等,模式识别[M].第二版.北京:清华大学出版社,2004
[103] Beyer K.S, Goldstein J., Ramakrishnan R., et al.. When Is Nearest Neighbor Meaningful [C]. Proceeding of the 7th International Conference on Database Theory, Icdt'99, 1999:217-235
[104] Sun Y. J.. Iterative RELIEF for feature weighting: algorithms, theories, and applications [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1035-1051
[105] Atkeson C.G., Moore A.W., Schaal S.. Locally weighted learning [J].. Artificial Intelligence Review, 1997, 11(15): 11-73, 1997
[106] Kress R. Numerical analysis[M]. New York: Springer-Verlag, 1998
[107] Van Winsum W., Sergeant J., Gueze R.. The functional significance of event-related desynchronization of alpha rhythms in attentional and activating tasks[J]. Electroenceph clin Neurophysiol,1984,58:519～524
[108] Pfurtscheller G, Flotzinger D., Kalcher J. Brain-computer interface: a new communication device for handicapped persons[J]. Journal of Microcomputer Applications, 1993, 16(3): 293-299
[109] Pfurtscheller G., Flotzinger D., Pregenzer M., et al. EEG-based brain computer interface (BCI): search for optimal electrode positions and frequency components [J]. Medical Progress through Technology, 1996,21(3): 111-121
[110] Pregenzer M., Pfurtscheller G.. Frequency component selection for an EEG-based brain-computer interface [J]. IEEE Transactions on Rehabilitation Engineering, 1999, 7(4): 413-419
[111] Guger C., Edlinger G., Harkam W, et al.. How many people are able to operate an EEG- based brain-computer interface (BCI)?[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003,11(2): 145-147
[112] Schl?gl A., Lee F., Bischof H., et al.. Characterization of four-class motor imagery EEG data for the BCI competition 2005[J]. Journal of Neural Engineering, 2005,2(4): 14-22
[113] Bostanov V.. BCI Competition 2003-Data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram[J]. IEEE Transactions on Biomedical Engnieering, 2004, 51(6):1057-1061
[114] Fatourechi M., Birch G.E., Ward R.K.. Application of a hybrid wavelet feature selection method in the design of a self-paced brain interface system[J]. Journal of Neuro Engineering and Rehabilitation, 2007, doi:10.1186/1743-0003-4-11
[115] Gysels E., Renevey P., Celka P.. SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in brain-computer interfaces[J]. Signal Processing, 2005,85(11): 2178-2189
[116] Wang S.G., James C.J.. Extracting rhythmic brain activity for brain-computer interfacing through constrained independent component analysis[J]. Comput-ational Intelligence and Neuroscience, 2007, doi:10.1155/2007/41468
[117] Ramoser H., Gerking J. M., Pfurtscherller G.. Optimal spatiall filtering of single trial EEG during imagined hand movement [J]. IEEE Transactions on Rehabilitation Engineering, 2000,8(4):441-446
[118] Koles Z.J., Lazar M.S., Zhou S.Z.. Spatial patterns underlying population differences in the background EEG[J]. Brain Topography, 1990,2(4): 275-284
[119] Dornhege G., Blankertz B., Krauledat M., et al.. Combined optimization of spatial and temporal filters for improving brain-computer interfacing[J]. IEEE Transactions on Biomedical Engineering, 2006,53(11): 2274-2281
[120] Wang H., Zheng W.. Local temporal common spatial patterns for robust single-trial EEG classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2008,16(2): 131-139
[121] Blankertz B., Kawanabe M., Tomioka R., et al.. Invariant common spatial patterns: Alleviating nonstationarities in brain-computer interfacing [A]. Advances in Neural Information Processing Systems 20[C]. Cambridge, MA: MIT Press, 2008: 983-911
[122] Boudet S., Peyrodie L., Gallois P., et al.. Filtering by optimal projection and application to automatic artifact removal from EEG[J]. Signal Processing, 2007,87: 1978–1992
[123] Xie S.L, Lv J., Liu M.C., et al. Temporal-spatial filter algorithm for MRP feature extraction [C]. International Conference on Information Computing and Automation 2007, 2008, 2 : 707-710
[124] Ye J.P., Janardan R., Li Q.. GPCA: An Efficient Dimension Reduction Scheme forImage Compression and Retrieval[C]. ACM SIGKDD Int’l Conf. Knowledge Discovery and Data Mining, 2004: 354–363
[125] Chen H.T, Chang H., Liu T.. Local discriminant embedding and its variants[C/OL]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005:846-853
[126] Ye J P.. Generalized Low Rank Approximations of Matrices [J]. Machine learning, 2005, 61:167-191
[127] Golub G.H., Van Loan C. F.. Matrix Computations[M]. third edition. Baltimore, MD, USA: The Johns Hopkins University Press, 1996
[128] Zhu X.J.. Semi-Supervised Learning Literature Survey[R]. America: University of Wisconsin-Madison, 2005
[129]易星.半监督学习若干问题的研究[D].北京:清华大学,2004
[130] Le A.C., Shimazu A., Huynh V.N., et al.. Semi-supervised learning integrated with classifier combination for word sense disambiguation[J]. Computer Speech and Language, 2008, 22(4): 330-345
[131] Yarowsky D.. Unsupervised word sense disambiguation rivaling supervised methods[C]. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics 1995: 189–196
[132] Rosenberg C., Hebert, M., Schneiderman, H.. Semi-supervised selftraining of object detection models[C]. Proceedings of the Seventh IEEE Workshop on Applications of Computer Vision, 2005, 1:29-36
[133] Blum A., Mitchell T.. Combining labeled and unlabeled data with co-training[C]. Proceeding of the 11th Conference on Computational Learning Theory, 1998: 92–100.
[134] Nigam K., Ghani R.. Analyzing the effectiveness and applicability of co-training[C]. Ninth International Conference on Information and Knowledge Management, 2000: 86–93
[135] Nigam K., McCallum A.K., Thrun S., et al.. Text classification from labeled and unlabeled documents using EM[J]. Machine Learning, 2000, 39, 103–134
[136] Fujino A., Ueda N., Saito K.. A hybrid generative/discriminative approach to semi-supervised classifier design[C]. The Twentieth National Conference on Artificial Intelligence, 2005, AAAI-05:764-769
[137] Bennett K., Demiriz A.. Semi-supervised support vector machines[C]. Advances in Neural Information Processing Systems, 1999, 11:368-374
[138] Blum A., Chawla S.. Learning from labeled and unlabeled data using graph mincuts[C].Proceeding of 18th International Conference on Machine Learning, 2001:19-21
[139]王宏禹.信号处理相关理论综合与统一法[D].北京:国防工业出版社,2005
[140] Li Y.Q., Guan C.T.. An Extended EM Algorithm for Joint Feature Extraction and Classification in Brain-Computer Interfaces[J]. Neural Computation, 2006, 18(11): 2730-2761
[141] Zhang R., Rudnicky A.I.. A new data selection principle for semi-supervised incremental learning[C]. ICPR 2006 (2): 780-783
[142] Qin J.Z., Li Y.Q., Sun W.. A Semisupervised Suppport Vector Machines Algorithm for BCI Systems[J]. Hindawi Publishing Corporation Computational Intelligence and Neuroscience, 2007:1-9
[143] Huang N.E., Shen Z., Long S.R., et al.. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-station time series analysis [C]. Proceedings of the Royal Society, 1998(454): 903~995
[144] Fraunhofer FIRST,Wadsworth Center, Graz University of Technology,et al.. BCI competition III [EB/OL]. http://ida.first.fhg.de/projects/bci/competition_iii/. 2009-9-5
[145] Miller D. J., Uyar H. S.. A mixture of experts classifier with learning based on both labelled and unlabelled data[M]. Cambridge, MA: MIT Press, 1997: 571–577
[146] Joachims T.. Transductive Inference for Text Classification Using Support Vector Machines[C]. Proceedings of ICML, 1999:200–209
[147] Wolpaw J.R., Mcfarland D.J.. Multichannel EEG-based brain–computer communication [J]. Electroencephalograph Clin Neurophysiol, 1994, 90: 444–449
[148] Müller K.R., Blankertz B., Curio G.. Data set IVc[EB/OL]. http://ida.first.fraunhofer.de/projects/BCI/competition_iii/ desc_IVc.html,2009-9-8
[149] Zhang D., Wang Y.J., Gao X.R., et al.. An algorithm for idle-state detection in motor- imagery-based brain-computer interface[J]. Hindawi Publishing Corporation Computational Intelligence and Neuroscience, 2007:1-9. doi:10.1155/2007/39714
[150] Sadeghlan E.B, Moradi M.H.. Continuous detection of motor imagery in a four-class asynchronous BCI [A]. Procdings of the 29th Annual International Conference of the IEEE EMBS[C].Cite Internationale, Lyon, France, 2007: 3241-3244
[151] Wikipedia. Receiver operating characteristic [EB/OL]. http://wwww.unionbig.com/ P.Html?a=;WindowsNT5.1;SV1;CIBA)&p=2666&t=1&z=386&key=v3FlsSQOnoq& ap= http://club.xilu.com/cadwer/msgview-1006621-56.html, 2009-9-1
[152] Bewick V., Cheek L., Ball J.. Statistics review 13: Receiver operating characteristiccurves[J]. Critical Care, 2004; 8(6): 508–512.doi: 10.1186/cc3000
[153]陈卫中,倪宗瓒,潘晓平等.用ROC曲线确定最佳临界点和可疑值范围[J].现代预防医学, 2005, 32(7): 729-731
[154]吕俊.基于运动想象的脑-机接口信号处理算法的研究[D].广州:华南理工大学, 2008
[2] Berger H.. Uber das Electrenkephalogramm des Menchen[J]. Arch Psychiat Nervenkr, 1929,(87): 527-570
[3] Vidal J.J.. Real-time detection of brain events in EEG[C]. Proceedings of the IEEE, 1977,65(5): 633-664
[4] Wolpaw J.R., Birbaumer N., Mcfarland W.J., et al. Brain-computer interfaces for communication and control[J]. Clin. Neurophysiol., 2002, vol.113:767-791
[5]杨立才,李佰敏,李光林等.脑-机接口技术综述[J].电子学报, 2005, 33(7): 1234-1241
[6]胡剑锋,肖守柏.脑机接口研究概述[J].科技广场,2007,9:1- 4
[7]维基百科.脑机接口[EB/OL]. http://zh.wikipedia.org/wiki/%E8%84%91% E6%9C% BA%E6%8E%A5% E5%8F%A3
[8]杨帮华.自发脑电脑机接口技术及脑电信号识别方法研究[D].上海:上海交通大学, 2006
[9] Fitzpatrick T.. Teenager moves video icons just by imagination hands off [R]. St Louis: Washington University, 2006, 9
[10] Serruya M.D, Donoghue J.P.. Chapter III: Design Principles of a Neuromotor Prosthetic Device in Neuroprosthetics: Theory and Practice. London[M]. England: Imperial College Press, 2003
[11] Müller K.R., Curio G., Blankertz B.. Berlin Brain-computer Interface [DB/OL]. http://www.bbci.de/, 2009-9-8
[12] Farwell L.A., Donchin E.. Talking off the top of your head: Toward a mental prosthesis utilizing event-related brain potentials [J]. Electroencephalograph Clin Neurophysiol. 1998, 70: 510–523
[13] Birbaumer N., Ghanayim N., Hinterberger T et al.. A spelling device for the paralyzed [J]. Nature, 1999, 398: 297–298
[14] Wolpaw J.R., Mcfarkand D.J.. EEG-based brain–computer communication[J]. Electroencephalograph Clin Neurophysiol, 1994, 90: 444–449
[15] George T., Bernhard G., Pfurtscheller G.. Continuous EEG classification during motor imagery-simulation of an asynchronous BCI [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2004, 12(2):258-265
[16] Tsui C.S. L., GAN J. Q.. A synchronous BCI control of a robot simulator with supervised online training [J]. Lecture Notes in Computer Science, 2007, 4881: 125-134
[17]百度百科.事件相关电位[EB/OL]. http://baike.baidu.com/view/1198359.html, 2009-9-10
[18] Wolpaw J.R., McFarland D.J, Neat G.W., et al.. An EEG-based brain-computer interface for cursor control[J]. Electroencephalograph Clin Neurophysiol, 1991, 78: 252-259
[19] Birbaumer N., Hinterberger T., Kübler A., et al.. The thought-translation device (TTD): neurobehavioral mechanisms and clinical outcome[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003,11:120-123
[20] Hinterberger T., Kübler A., Kaiser J., et al.. A brain-computer interface (BCI) for the locked-in: comparison of different EEG classifications for the thought translation device[J]. Clin Neurophysiol, 2003,114:416-425
[21] Sutter E E.. The brain response interface: communication through visually- induced electrical brain response[J]. Journal of Microcomputer Applications, 1992,15:31-45
[22] Neuper C., Schl?gl A., Pfurtscheller G.. Enhancement of left-right sensorimotor EEG differences during feedback-regulated motor imagery[J]. Journal of Clinical Neurophysiology, 1999,16:373-382
[23] Pfurtscheller G., Neuper C., Guger C., et al.. Current trends in Graz brain– computer interface(BCI) research[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2000,8:216-219
[24] Cincotti F., Mattia D., Babiloni C., et al.. The use of EEG modifications due to motor imagery for brain-computer interface[J]. IEEE transactions on neural systems and rehabilitation engineering, 2003, 11:131-133
[25] Kostov A., Polak M.. Parallel man-machine training in development of EEG-based cursor control[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2000,8:203-205
[26] Wolpaw J.R., Birbaumer N., Heetderks W.J.. Brain-computer interface technology: a review of the first international meeting[J]. IEEE Transactions on Rehabilitation Engineering, 2000,8(2): 164-173
[27] Mussa-Ivaldi S.. Real brain for real robots[J].Nature,2000,48(6810):305-306
[28] Vaughan T.M.. Brain-computer interface technology: A review of the second interational meeting[J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11(2): 94-109
[29] Virts J.. The third international meeting on brain-computer interface technology: makinga difference [J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2006,14(2): 126-127
[30] BCI Competitions [DB/OL]. http://www.bbci.de/competition, 2009-9-1
[31] Mason S.G.. A general framework for brain-computer interface design[J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11, (1): 70-85
[32] Pfurtscheller G., Neuper C.. Motor imagery and direct brain-computer communication[C]. presented at Proceedings of the IEEE, 2001,89(7): 1123-1134
[33] Müller G.R., Neuper C., Pfurtscheller G., et al.. Implementation of a telemonitoring system for the control of an EEG-based brain-computer interface[J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003, 11(1): 54-59
[34] Wolpaw J.R., McFarland D.J., Vaughan T.M.. The wadsworth center brain- computer interface (BCI) research and development program [J]. IEEE Transactions on Neural System and Rehabilitation Engineering, 2003,11(2): 204-207
[35] Vaughan T.M, McFarland D.J., Schalk G., et al.. The wadsworth BCI research and development program: At home with BCI[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006,14(2):229-233
[35] Wolpaw J.R., Birbaumer N., Heetderks W.J.. Brain computer interface technology: a review of the first international meeting[J]. IEEE Transactions on Rehabilitation Engineering 2000, 8(2):164-173
[36] Dornhege G., Benjamin B., Gabriel C.. Speeding up classification of multi-channel brain-computer spatial patterns for slow cortical potentials[C]. Proceedings of the 1st international IEEE EMBS Conference on Neural Engineering, 2003,674: 595-598
[37] Birch G.E., Mason S.G., Borisoff J.F.. Current trends in brain-computer interface research at the Neil Squire foundation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003, 11(2):123-126
[38] Birch G. E., Bozorgzadeh Z., Mason S. G.. Initial oh-line evaluations of the LF-ASD brain-computer interface with able-bodied and spinal-cord subjects using imagined voluntary motor potentials[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2002,10(4):219-224
[39] Mason S.G., Birch G.E.. A brain-controlled switch for asynchronous control applications [J]. IEEE Transactions on Biomedical Engineering, 2000, 47(10): 1297-1306
[40] Birch G.E., Mason S.G.. Brain-computer interface research at the Neil Squire foundation[J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(2):193-195
[41] Borisoff J.F., Mason S.G., Bashashati A.. Brain-computer interface design forasynchronous control applications: improvements to the LF-ASD asynchronous brain switch[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 985-992
[42] Mason, S. G., Bohringer, R., Borisoff, J. F., et al.. Real-time control of a video game with a direct brain-computer interface[J]. Journal of Clinical Neurophysiology, 2004, 21(6): 404-408
[43] Bashashati A., Ward R.K., Birch.G.E.. A new design of the asynchronous brain computer interface using the knowledge of the path of features[C]. Proceedings of the 2nd international IEEE EMBS conference on neural engineering, Arington,2005, 693:101-104
[44]徐丁峰,程明,高小榕.数字信号处理器在脑-机接口系统中的应用[J].北京生物医学工程, 2002,21(4):257-260
[45]赵香花,汪晓光.基于脑-机接口的残疾人环境控制装置的设计[J].中国康复医学杂志, 2004,19(5):324-326
[46]任宇鹏,王广志,程明.基于脑-机接口的康复辅助机械手控制[J].中国康复医学杂志, 2004, 19(5):330-333
[47]程明,高上凯,张琳.基于脑电信号的脑—计算机接口[J].北京生物医学工程, 2000, 19(2):113-118
[48] Ebrahimi T., Vesin J.M., Garcia G.. Brain-computer inyerface in multimedia communication[J]. IEEE Signal Processing Magazine, 2003, 20(1): 14-24
[49] Krepki R., Blankertz B., Curio G., et al.. The Berlin Brain-Computer Interface (BBCI) - towards a new communication channel for online control in gaming applications[J]. Multimedia Tools and Applications, 2007, 33(1): 73-90
[50] Krepki, R., Curio G., Blankertz B., et al. Berlin brain-computer interface-The HCI communication channel for discovery [J]. International Journal of Human-Computer Studies, 2007, 65(5): 460-477
[51]中华网科技.清华研制出脑机接口系统可用思维踢足球[EB/OL]. http://tech.163.com/ 07/0821 /14/ 3ME7AEFD00092CEI.html, 2009-9-2
[52]尧德中.脑功能探测的电学理论与方法[M].北京:科技出版社, 2003
[53] Wolpaw J.R., Birbaumer N., McFarlanda D.J., et al.. Brain–computer interfaces for communication and control[J].Clinical Neurophysiolopgy, 2002, 113:767–791
[54]黄远桂,吴声伶编著.临床脑电图学[M].北京:人民卫生出版社, 1998, 1-9
[55] User Tutorial. EEG Measurement Setup[EB/OL]. http://www.bci2000.org/wiki/ index.php/User_Tutorial:EEG_Measurement_Setup. 2009-9-2
[56]大熊辉雄.临床脑电图学[M].第5版.周锦华译.北京:清华大学出版社,2005:64-66
[57]谭玉玲编著.临床脑电图与脑电地形图学.北京:人民卫生出版社, 1999:16
[58]聂能,尧德中,谢正祥编著.生物医学信号数字处理技术及应用[M].北京:科学出版社, 2005,8
[59] Kübler A., Ghanayim N., Hinterberger T.. The thought translation device (TTD) for completely paralyzed patients[J]. IEEE Transactions on rehabilitation engineering, 2000, 8(2): 190-193
[60] Ho, C. K., Sasaki, M.. Brain-wave bio potentials based mobile robot control: wavelet-neural network pattern recognition approach[C]. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 2001, 3494:322-328
[61] McFarland D.J., Lefkowicz A.T., WolPaw J.R.. Design and operation of an EEG based brain-computer interface (BCI) with digital signal processing technology [J]. Behavior research methods, instruments & computers, 1997, 29(3): 337-345
[62]魏庆国.基于运动想象的脑机接口分类算法的研究[D].北京:清华大学, 2006
[63]张旭东,陆明泉,离散随机信号处理[M].北京:清华大学出版社, 2005,1-400
[64]吴正国.现代信号处理技术:高阶谱、时频分析与小波变换[M].武汉:武汉大学出版社,2003
[65]余英林,谢胜利,蔡汉添等.信号处理新方法导论[M].北京:清华大学出版社, 2004: 255~262
[66] Freeman W.J., Burke B.C., Holmes M.D.. Aperiodic Phase Re-Setting in Scalp EEG of Beta–Gamma Oscillations by State Transitions at Alpha–Theta Rates[J].Human Brain Mapping,2003,19(4):248-272
[67] Mensh, B. D., Werfel, J., Seung, H. S.. BCI competition 2003-Data Set Ia: combining gamma-band power with slow cortical potentials to improve single-trial classification of electroencephalographic signals [J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1052-1056
[68]张贤达,保铮.非平稳信号分析与处理[M].上海:国防工业出版社,1999
[69] Xue J.Z., Zhang H., Zheng C.X., Wavelet packet transform for feature extraction of EEG during mental tasks[C]. presented at Proceedings of the Second International Conference on Machine Learning and Cybernetics, Xi'an,2003, 3268: 360-363
[70] Graimann B., Huggins J.E., Levine S.P.. Toward a direct brain interface based on human subdural recordings and wavelet-packet analysis[J]. IEEE Trans on Biomedical Engineering, 2004, 51(6):954-962
[71]毛大伟.分尺度复杂性及希尔伯特-黄变换在脑电分析中的应用[D].杭州:浙江大学, 2005
[72]沈恩华,脑电的复杂度分析[D].上海:复旦大学, 2004
[73] Lemm S., Blankertz B., Curio G., et al.. Spatio-spectral filters for improving the classification of single trial EEG[J]. IEEE Transactions on Biomedical Engineering, 2005, 52(9):1541-1548
[74] Wang Y., Berg P., Scherg M.. Common spatial subspace decomposition applied to analysis of brain responses under multiple task conditions: a simulation study [J]. Clinical neurophysiology , 1999,112(4): 604-614
[75] Liao X., Yao D. Z., Wu D.. Combining spatial filters for the classification of single-trial EEG in a finger movement task[J]. IEEE Transactions on Biomedical Engineering, 2007, 54(5): 821-831
[76] Burke D.P., Kelly S.P., Chazal P.D., et al.. A parametric feature extraction and classification strategy for brain-computer interfacing[J]. IEEE Transaction on Neural System and Rehabilitation Engineering, 2005, 13(1): 12-17
[77] Webb A., Statistical Pattern Recognition[D]. second edition. England: John Wiley & Sons Ltd, 2002
[78] Barreto A.B., Taberner A.M., Vicente L.M.. Neural network classification of spatio-temporal EEG readiness potentials [A]. Proceedings of the 15th Southern Biomedical Engineering Conference, Dayton ,USA: IEEE,1996: 73– 76
[79]刘红梅.数据挖掘中分类方法探究[J].硅谷,2009,3:56+76
[80]刘红岩,陈剑,陈国青.数据挖掘中的数据分类算法综述[J].清华大学学报(自然科学版), 2002,42(6):727-730
[81]台北荣民总医院教学研究部整合性脑功能实验室.脑电波研究室简介[EB/OL]. http://ibru.vghtpe.gov.tw/chinese/eeg.htm, 2008-10-3
[82] Graimann B., Huggins J.E., Levine S.P.. Visualization of significant ERD/ERS patterns in multichannel EEG and ECoG data [J].Cliniacl Neurophysiology, 2002 113: 43-47
[83] Pfurtscheller G., Lopes da Silva F.H.. Event-related EEG/MEG synchronization and desychronization: Basic principles[J]. Clin Neurophysiol, 1999, 110:1842-1857
[84] Suffczynski P., Kalitzin S., Pfurtscheller G., et al.. Computational model of thalamo-cortical networks: dynamical control of alpha rhythms in relation to focal attention[J]. International Journal of Psychophysiology, 2001, 43(1): 25-40
[85] do Nascimento O. F., Nielsen K. D., Voigt M.. Relationship between plantar-flexortorque generation and the magnitude of the movement-related potentials[J]. Experimental Brain Research, 2005, 160: 154–165
[86] Slobounov S.M., Ray W.J.. Movement-related potentials with reference to isometric force output in discrete and repetitive tasks[J]. Experimental Brain Research, 1998, 123:461–473
[87] do Nascimento O.F., Farina D.. Movement-Related Cortical Potentials Allow Discrimination of Rate of Torque Development in Imaginary Isometric Plantar Flexion[J]. IEEE Transactions on Biomedical Engineering, 2008, 55(11): 2675-2678
[88] Terada K., Lansek R., Johnson K.A., et al., Movement-related cortical potentials associated with voluntary relaxation of foot muscles[J]. Clinical Neurophysiology, 1999, 110(3): 397-403
[89] Cunnington, R., Ikeda A., Yazawa S., et al.. Movement-related potentials in Parkinson's disease-motor imagery and movement preparation[J]. Brain, 1997, 120: 1339-1353
[90] Shibasaki H., Barrett G., Halliday E., Halliday AM.. Cortical potentials associated with voluntary foot movement in man[J]. Electroencephalograph Clin Neurophysiol, 1981, 52:507–516
[91] Cunnington R., Iansek R., Bradshaw J. L., Phillips J. G.. Movement-related potentials associated with movement preparation and motor imagery[J]. Experimental Brain Research, 1996, 111:429–436
[92] Wang Y., Zhang Z., Li T., et al. BCI competition 2003-data set IV:An algorithm based on CSSD and FDA for classifying single-trial EEG[J]. IEEE Transactions on Biomedical Engineering, 2004,51(6): 1081-1086
[93] Dornhege G., Blankertz B., Curio G., et al.. Combining features for BCI[A]. Proceedings of Advances in Neural Information Processing Systems (NIPS02)[C]. Cambridge: MIT Press, 2003,15: 1115–1122
[94] Fu Y., Yan S. C., Huang T. S.. Classification and feature extraction by simplexization [J]. IEEE Transactions on Information Forensics and Security, 2008, 3(1): 91-100
[95] Roweis S. T., Saul L. K.. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 290: 323—2326
[96] Wang F., Zhang C.S.. Label Propagation through linear neighborhoods [J]. IEEE Transactions on Knowledge and Data Engineering, 2008, 20: 55-67
[97] He X.F., Niyogi P.. Locality preserving projection [C]. in: Proceedings of the Conference on Advances in Neural Information Processing Systems, 2003. 16: 153-160
[98] Fraunhofer-FIRST, Intelligent Data Analysis Group, Freie Universitat Berlin, Departmentof Neuropology, et al. Data set
[99] Fraunhofer-FIRST, Intelligent Data Analysis Group. EEG Classification for self-paced key typing [EB/OL]. http://home.ustc.edu.cn/~cplee/, 2009-9-8
[100] Masashi S.. Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis[J]. Journal of Machine Learning Research, 2007, 8: 1027-1061
[101] Yan S. C., Xu D.B., Zhang Y., et al.. Graph Embedding and Extensions: A General Framework for Dimensionality Reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence., 2007, 29(1):40-51
[102]边肇祺,张学工等,模式识别[M].第二版.北京:清华大学出版社,2004
[103] Beyer K.S, Goldstein J., Ramakrishnan R., et al.. When Is Nearest Neighbor Meaningful [C]. Proceeding of the 7th International Conference on Database Theory, Icdt'99, 1999:217-235
[104] Sun Y. J.. Iterative RELIEF for feature weighting: algorithms, theories, and applications [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1035-1051
[105] Atkeson C.G., Moore A.W., Schaal S.. Locally weighted learning [J].. Artificial Intelligence Review, 1997, 11(15): 11-73, 1997
[106] Kress R. Numerical analysis[M]. New York: Springer-Verlag, 1998
[107] Van Winsum W., Sergeant J., Gueze R.. The functional significance of event-related desynchronization of alpha rhythms in attentional and activating tasks[J]. Electroenceph clin Neurophysiol,1984,58:519～524
[108] Pfurtscheller G, Flotzinger D., Kalcher J. Brain-computer interface: a new communication device for handicapped persons[J]. Journal of Microcomputer Applications, 1993, 16(3): 293-299
[109] Pfurtscheller G., Flotzinger D., Pregenzer M., et al. EEG-based brain computer interface (BCI): search for optimal electrode positions and frequency components [J]. Medical Progress through Technology, 1996,21(3): 111-121
[110] Pregenzer M., Pfurtscheller G.. Frequency component selection for an EEG-based brain-computer interface [J]. IEEE Transactions on Rehabilitation Engineering, 1999, 7(4): 413-419
[111] Guger C., Edlinger G., Harkam W, et al.. How many people are able to operate an EEG- based brain-computer interface (BCI)?[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003,11(2): 145-147
[112] Schl?gl A., Lee F., Bischof H., et al.. Characterization of four-class motor imagery EEG data for the BCI competition 2005[J]. Journal of Neural Engineering, 2005,2(4): 14-22
[113] Bostanov V.. BCI Competition 2003-Data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram[J]. IEEE Transactions on Biomedical Engnieering, 2004, 51(6):1057-1061
[114] Fatourechi M., Birch G.E., Ward R.K.. Application of a hybrid wavelet feature selection method in the design of a self-paced brain interface system[J]. Journal of Neuro Engineering and Rehabilitation, 2007, doi:10.1186/1743-0003-4-11
[115] Gysels E., Renevey P., Celka P.. SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in brain-computer interfaces[J]. Signal Processing, 2005,85(11): 2178-2189
[116] Wang S.G., James C.J.. Extracting rhythmic brain activity for brain-computer interfacing through constrained independent component analysis[J]. Comput-ational Intelligence and Neuroscience, 2007, doi:10.1155/2007/41468
[117] Ramoser H., Gerking J. M., Pfurtscherller G.. Optimal spatiall filtering of single trial EEG during imagined hand movement [J]. IEEE Transactions on Rehabilitation Engineering, 2000,8(4):441-446
[118] Koles Z.J., Lazar M.S., Zhou S.Z.. Spatial patterns underlying population differences in the background EEG[J]. Brain Topography, 1990,2(4): 275-284
[119] Dornhege G., Blankertz B., Krauledat M., et al.. Combined optimization of spatial and temporal filters for improving brain-computer interfacing[J]. IEEE Transactions on Biomedical Engineering, 2006,53(11): 2274-2281
[120] Wang H., Zheng W.. Local temporal common spatial patterns for robust single-trial EEG classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2008,16(2): 131-139
[121] Blankertz B., Kawanabe M., Tomioka R., et al.. Invariant common spatial patterns: Alleviating nonstationarities in brain-computer interfacing [A]. Advances in Neural Information Processing Systems 20[C]. Cambridge, MA: MIT Press, 2008: 983-911
[122] Boudet S., Peyrodie L., Gallois P., et al.. Filtering by optimal projection and application to automatic artifact removal from EEG[J]. Signal Processing, 2007,87: 1978–1992
[123] Xie S.L, Lv J., Liu M.C., et al. Temporal-spatial filter algorithm for MRP feature extraction [C]. International Conference on Information Computing and Automation 2007, 2008, 2 : 707-710
[124] Ye J.P., Janardan R., Li Q.. GPCA: An Efficient Dimension Reduction Scheme forImage Compression and Retrieval[C]. ACM SIGKDD Int’l Conf. Knowledge Discovery and Data Mining, 2004: 354–363
[125] Chen H.T, Chang H., Liu T.. Local discriminant embedding and its variants[C/OL]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005:846-853
[126] Ye J P.. Generalized Low Rank Approximations of Matrices [J]. Machine learning, 2005, 61:167-191
[127] Golub G.H., Van Loan C. F.. Matrix Computations[M]. third edition. Baltimore, MD, USA: The Johns Hopkins University Press, 1996
[128] Zhu X.J.. Semi-Supervised Learning Literature Survey[R]. America: University of Wisconsin-Madison, 2005
[129]易星.半监督学习若干问题的研究[D].北京:清华大学,2004
[130] Le A.C., Shimazu A., Huynh V.N., et al.. Semi-supervised learning integrated with classifier combination for word sense disambiguation[J]. Computer Speech and Language, 2008, 22(4): 330-345
[131] Yarowsky D.. Unsupervised word sense disambiguation rivaling supervised methods[C]. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics 1995: 189–196
[132] Rosenberg C., Hebert, M., Schneiderman, H.. Semi-supervised selftraining of object detection models[C]. Proceedings of the Seventh IEEE Workshop on Applications of Computer Vision, 2005, 1:29-36
[133] Blum A., Mitchell T.. Combining labeled and unlabeled data with co-training[C]. Proceeding of the 11th Conference on Computational Learning Theory, 1998: 92–100.
[134] Nigam K., Ghani R.. Analyzing the effectiveness and applicability of co-training[C]. Ninth International Conference on Information and Knowledge Management, 2000: 86–93
[135] Nigam K., McCallum A.K., Thrun S., et al.. Text classification from labeled and unlabeled documents using EM[J]. Machine Learning, 2000, 39, 103–134
[136] Fujino A., Ueda N., Saito K.. A hybrid generative/discriminative approach to semi-supervised classifier design[C]. The Twentieth National Conference on Artificial Intelligence, 2005, AAAI-05:764-769
[137] Bennett K., Demiriz A.. Semi-supervised support vector machines[C]. Advances in Neural Information Processing Systems, 1999, 11:368-374
[138] Blum A., Chawla S.. Learning from labeled and unlabeled data using graph mincuts[C].Proceeding of 18th International Conference on Machine Learning, 2001:19-21
[139]王宏禹.信号处理相关理论综合与统一法[D].北京:国防工业出版社,2005
[140] Li Y.Q., Guan C.T.. An Extended EM Algorithm for Joint Feature Extraction and Classification in Brain-Computer Interfaces[J]. Neural Computation, 2006, 18(11): 2730-2761
[141] Zhang R., Rudnicky A.I.. A new data selection principle for semi-supervised incremental learning[C]. ICPR 2006 (2): 780-783
[142] Qin J.Z., Li Y.Q., Sun W.. A Semisupervised Suppport Vector Machines Algorithm for BCI Systems[J]. Hindawi Publishing Corporation Computational Intelligence and Neuroscience, 2007:1-9
[143] Huang N.E., Shen Z., Long S.R., et al.. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-station time series analysis [C]. Proceedings of the Royal Society, 1998(454): 903~995
[144] Fraunhofer FIRST,Wadsworth Center, Graz University of Technology,et al.. BCI competition III [EB/OL]. http://ida.first.fhg.de/projects/bci/competition_iii/. 2009-9-5
[145] Miller D. J., Uyar H. S.. A mixture of experts classifier with learning based on both labelled and unlabelled data[M]. Cambridge, MA: MIT Press, 1997: 571–577
[146] Joachims T.. Transductive Inference for Text Classification Using Support Vector Machines[C]. Proceedings of ICML, 1999:200–209
[147] Wolpaw J.R., Mcfarland D.J.. Multichannel EEG-based brain–computer communication [J]. Electroencephalograph Clin Neurophysiol, 1994, 90: 444–449
[148] Müller K.R., Blankertz B., Curio G.. Data set IVc
[149] Zhang D., Wang Y.J., Gao X.R., et al.. An algorithm for idle-state detection in motor- imagery-based brain-computer interface[J]. Hindawi Publishing Corporation Computational Intelligence and Neuroscience, 2007:1-9. doi:10.1155/2007/39714
[150] Sadeghlan E.B, Moradi M.H.. Continuous detection of motor imagery in a four-class asynchronous BCI [A]. Procdings of the 29th Annual International Conference of the IEEE EMBS[C].Cite Internationale, Lyon, France, 2007: 3241-3244
[151] Wikipedia. Receiver operating characteristic [EB/OL]. http://wwww.unionbig.com/ P.Html?a=;WindowsNT5.1;SV1;CIBA)&p=2666&t=1&z=386&key=v3FlsSQOnoq& ap= http://club.xilu.com/cadwer/msgview-1006621-56.html, 2009-9-1
[152] Bewick V., Cheek L., Ball J.. Statistics review 13: Receiver operating characteristiccurves[J]. Critical Care, 2004; 8(6): 508–512.doi: 10.1186/cc3000
[153]陈卫中,倪宗瓒,潘晓平等.用ROC曲线确定最佳临界点和可疑值范围[J].现代预防医学, 2005, 32(7): 729-731
[154]吕俊.基于运动想象的脑-机接口信号处理算法的研究[D].广州:华南理工大学, 2008