基于运动想象脑电信号非线性特性分析的脑—机接口研究
|
摘要
脑-机接口（Brain-Computer Interface，BCI）是一种帮助人们利用他们的大脑控制和使用外部设备的一种通信系统，在此过程中不需要外周神经和肌肉的参与。BCI是一门涉及神经科学、信号处理、计算机科学等多个领域的交叉学科。近20年来，已成为国际智能科学领域的一个研究热点。BCI研究的核心就是如何将用户的脑电信号转换成外部设备的控制信号。所以BCI研究最重要的工作就是要寻找合适的信号处理和转换方法，使得人脑的意识特征信号能够快速、准确地被计算机识别。一般来说，BCI系统可以看成是一个模式识别系统。一个BCI系统是否成功主要取决于两个方面的因素：①获取的特征能够区分不同的意识任务；②分类算法准确有效。所以如何建立准确可靠的特征提取模型和设计高效的分类算法是目前研究的主要难点。
目前，在基于运动想象的脑-机接口研究中，对EEG进行特征提取和分类往往都建立在EEG信号是线性的这一假设的基础之上。然而，大量研究表明，EEG信号是非线性的，采用线性方法来对EEG信号进行处理，会导致其非线性特征丢失，从而减弱这些特征在区分不同意识任务时的性能。所以，本论文在针对EEG信号的非线性特性研究的基础上，根据目前特征提取和分类算法中存在的问题，提出了新的基于EEG非线性特性的特征提取算法，并通过仿真实验证明了其可行性。论文的主要研究内容包括以下几个方面：
①对EEG动力学模型的非线性特性进行分析。通过相空间重构技术，对求解得到的EEG信号进行了重构。得出了he的吸引子随着参数p ee和pe i变化的规律。从而证实了大脑中存在混沌这一观点。对实际测得的EEG信号进行了非线性特性的研究。计算了脑-机接口竞赛提供的两个基于运动想象的数据集中EEG样本的最大Lyapunov指数，计算结果表明，几乎所有的标准数据集当中的EEG样本的最大Lyapunov指数均大于零。进一步证实了大脑中存在混沌的论点，因而可以使用非线性分析方法来对EEG信号进行分析。
②分别计算了两个标准数据集样本的几种常见的混沌特征量，即最大Lyapunov指数、关联维数和近似熵，并分别使用最大Lyapunov指数、关联维数和近似熵作为运动想象的特征进行分类。结果表明，直接使用最大Lyapunov指数和关联维数作为运动想象任务的特征，不能很好的区分各种运动想象任务。而近似熵是衡量时间序列中产生新模式概率大小的一种度量，它更适合表示不同的意识任务。在对近似熵特征进行分析的基础上，提出了一种基于时间窗的近似熵特征提取和分类算法。该算法模拟在线脑-机接口的情况，在每个时间窗内对意识任务进行分类，实验结果表明，分类器能较好的区分左右手运动想象任务。
③提出了一套基于相空间重构的特征提取方法。从理论上证明了相空间重构函数具有滤波功能，并能够对EEG信号进行相位和幅度调节，从而使相空间的特征更能区别不同的脑电任务。基于相空间的特征提取方法保留了传统的线性特征提取方法的优势，又使获取的特征具有相空间的信息，因而提高了分类器的分类性能。本文使用了2003和2005两届脑机接口竞赛提供的数据进行了仿真，并采用了和竞赛相同的评价标准：互信息和最大互信息峭度。实验结果表明，该方法是一种极具竞争力的特征提取方法。采用相空间特征的Fisher分类器在Graz2003数据集取得了最大互信息值0.67，这是目前报道的最好结果。在对Graz2005数据集进行仿真的结果表明，相空间特征同样具有很好的效能，在平均最大互信息峭度和分类正确率的评价标准下均取得了很好的成绩。
④针对共空间模式（Common spatial pattern，CSP）在解决多分类问题中的组合方式问题，提出了一种基于CSP和Fisher线性分类器的二叉树组合方式（BCSP）。在该方式下，Fisher线性分类器和CSP以二叉树的方式进行排列。任务的分类采用二叉查找的方式进行。在BCSP中，使用的CSP滤波器和Fisher分类器的数目比传统的“一对它”方式更少。而且在N分类过程中，对CSP投影矩阵和分类器的计算也能保持在最多log2N级别，大大提高了分类的效率，提高了分类的准确率。
⑤在线BCI游戏平台的开发与实现。在对研究结果进行总结的基础上，设计了一套基于Neuroscan的在线BCI游戏系统。该系统可以通过脑电来进行Hangman游戏操作。该系统集成了训练模块，测试模块和游戏模块。能够完成从训练到实际操作的一整套功能。系统使用了C3、C4和O1通道来记录EEG信号，其中C3和C4通道的EEG信号用来提取左右手运动想象任务的脑电特征，O1通道的波作为确认信号。该系统采用了基于相空间重构的特征提取算法和Fisher线性分类器。对6个用户进行实验的结果表明，相空间特征均提高了运动想象任务的识别率，从而证明了相空间特征的有效性。
文章的最后对所有的研究工作进行了总结，指出了论文主要研究工作的内容和取得的成果，并对下一步的工作进行了展望。
Brain-Computer Interface (BCI) is a communication system that helps individualsto drive and control external devices using only their brain activity, withoutparticipation of peripheral nerves and muscles. BCI is an integrated disciplinesincluding neuroscience, signal processing and computer science etc. Over the past20years, BCI has become a research hotspot in the field of international intelligent science.The core of BCI research is how to translate the user’s EEG signals into the controllingcommands for the external devices. So the most important work of the BCI research isto find the proper signal processing and translating method, which can help todistinguish the mentality tasks by the computer quickly and accurately. Generally, theBCI system can be seen as a pattern recognition system. So a successful EEG-basedBCI system very much depends on whether the following two requirements can besatisfied:①The extracted EEG features are able to differentiate the task-oriented brainstates; and②The methods for classifying such features in real-time are efficient. Howto improve the performance of the features and design an efficient classificationalgorithm are two key points.
Nowadays, during the research of BCI based on motor imagery, many featureextraction methods and classification methods applied to EEG generally assume that theEEG signal is linear. However, many researches have shown that the EEG signals arenonlinear. To analyze the EEG signals by linear method will loss much nonlinearfeatures, then the capability of distinguishing different tasks will be decreased. Thispaper, we proposed a new feature extraction method based on the nonlinearcharacteristics of EEG. Then we verified the effectiveness of the new algorithm bysimulations. This paper includes the following aspects of content.
①We analyzed the nonlinear characters of EEG dynamical model. Using phasespace reconstruction technology to reconstruct the EEG signals obtained in the EEGmodel. Then we learned the changing principle of the attractors ofhe with the changesof parameters ofp eeandpe i. We also analyzed the nonlinear characters of the realEEG. The maximum Lyapunov indexes of the samples in the two BCI competition’sdatasets were calculated. The results show that almost all the maximum Lyapunovindexes of the samples are bigger than zero, which confirmed the argument of chaos inthe EEG. So the nonlinear analysis method can be used to analyze the EEG signals.
②Some normal chaos features, maximum Lyapunov index, correlation dimensionand Approximate Entropy (ApEn), are calculated. Those three characters were used asthe features of the BCI. The experimental results showed that the maximum Lyapunovindex and correlation dimension do not suit for differentiating the motor imagery tasks.However, the Approximate Entropy is a measure of the probability for producing newmodels in time series; it is more suitable for distinguishing different tasks. Based on theanalysis of the ApEn features, this paper proposed a feature extraction method andclassification method based on ApEn and time window. The proposed method cansimulate the online situation, and classify the tasks in each window. The simulationshows that the classifiers based on theApEn features can distinguish the tasks well.
③We proposed a feature extraction schemes based on phase space reconstruction.We proved the construction functions have the filtering capacities which can adjust theamplitude and phase of the signals. Then the phase space features can be distinguishedbetween different tasks more easily. Moreover, the features extracted in the proposedscheme can retain the merit of traditional features, at the same time they also contain theinformation of phase space, so it can improve the classification capabilities of theclassifiers. This paper used the benchmark datasets coming from the BCI competition2003and2005. The mutual information (MI) and the maximum steepness of MI areused as the evaluation standards which are also used in the BCI competitions. Thesimulations show that the proposed method is a competitive method. The classifier gotthe maximum MI0.67on the Graz2003dataset, which is the best result ever known.The simulations on Graz2005dataset also obtained some good results. The phase spacefeatures have the good results based on accuracy criteria and mean maximum steepnessof MI.
④In order to solve multi-classification problems using common spatial pattern(CSP), we proposed a combination method based on binary tree termed BCSP, whichput the CSP filters and Fisher classifiers on the nodes of the binary tree. Theclassification process bases on binary search. In BCSP, the number of the filters andclassifiers is less than "one versus rest" method. Moreover, The most calculating stepsto solve the N class problems islog2N, which improves the efficiency and results ofclassification largely.
⑤Developing and realized a BCI online game platform. We developed an onlinegame platform based on the research of this paper. The platform is a game system basedon Neuroscan, and user can play Hangman game by imaging left/right hand moving. The platform has training module, testing module and game module. The user can use itto complete all the training, testing and play actions. C3, C4and O1channels are usedto gather the EEG signal, and the EEG from C3and C4are used to extract the featuresof right/left hand motor imagery tasks. We also used rhythm in O1to act as theconfirming signals. Phase space features and Fisher classifiers are used in this system.Six people took part in the experiments, the experiments results show that the phasespace features improved the classification accuracy, and then it proved the effectivenessof the phase space features.
At the end of the dissertation, we summarized the research contents of this paper,and show the main achievements of the research. Finally, the author points out the nextwork of the future researches.
目前，在基于运动想象的脑-机接口研究中，对EEG进行特征提取和分类往往都建立在EEG信号是线性的这一假设的基础之上。然而，大量研究表明，EEG信号是非线性的，采用线性方法来对EEG信号进行处理，会导致其非线性特征丢失，从而减弱这些特征在区分不同意识任务时的性能。所以，本论文在针对EEG信号的非线性特性研究的基础上，根据目前特征提取和分类算法中存在的问题，提出了新的基于EEG非线性特性的特征提取算法，并通过仿真实验证明了其可行性。论文的主要研究内容包括以下几个方面：
①对EEG动力学模型的非线性特性进行分析。通过相空间重构技术，对求解得到的EEG信号进行了重构。得出了he的吸引子随着参数p ee和pe i变化的规律。从而证实了大脑中存在混沌这一观点。对实际测得的EEG信号进行了非线性特性的研究。计算了脑-机接口竞赛提供的两个基于运动想象的数据集中EEG样本的最大Lyapunov指数，计算结果表明，几乎所有的标准数据集当中的EEG样本的最大Lyapunov指数均大于零。进一步证实了大脑中存在混沌的论点，因而可以使用非线性分析方法来对EEG信号进行分析。
②分别计算了两个标准数据集样本的几种常见的混沌特征量，即最大Lyapunov指数、关联维数和近似熵，并分别使用最大Lyapunov指数、关联维数和近似熵作为运动想象的特征进行分类。结果表明，直接使用最大Lyapunov指数和关联维数作为运动想象任务的特征，不能很好的区分各种运动想象任务。而近似熵是衡量时间序列中产生新模式概率大小的一种度量，它更适合表示不同的意识任务。在对近似熵特征进行分析的基础上，提出了一种基于时间窗的近似熵特征提取和分类算法。该算法模拟在线脑-机接口的情况，在每个时间窗内对意识任务进行分类，实验结果表明，分类器能较好的区分左右手运动想象任务。
③提出了一套基于相空间重构的特征提取方法。从理论上证明了相空间重构函数具有滤波功能，并能够对EEG信号进行相位和幅度调节，从而使相空间的特征更能区别不同的脑电任务。基于相空间的特征提取方法保留了传统的线性特征提取方法的优势，又使获取的特征具有相空间的信息，因而提高了分类器的分类性能。本文使用了2003和2005两届脑机接口竞赛提供的数据进行了仿真，并采用了和竞赛相同的评价标准：互信息和最大互信息峭度。实验结果表明，该方法是一种极具竞争力的特征提取方法。采用相空间特征的Fisher分类器在Graz2003数据集取得了最大互信息值0.67，这是目前报道的最好结果。在对Graz2005数据集进行仿真的结果表明，相空间特征同样具有很好的效能，在平均最大互信息峭度和分类正确率的评价标准下均取得了很好的成绩。
④针对共空间模式（Common spatial pattern，CSP）在解决多分类问题中的组合方式问题，提出了一种基于CSP和Fisher线性分类器的二叉树组合方式（BCSP）。在该方式下，Fisher线性分类器和CSP以二叉树的方式进行排列。任务的分类采用二叉查找的方式进行。在BCSP中，使用的CSP滤波器和Fisher分类器的数目比传统的“一对它”方式更少。而且在N分类过程中，对CSP投影矩阵和分类器的计算也能保持在最多log2N级别，大大提高了分类的效率，提高了分类的准确率。
⑤在线BCI游戏平台的开发与实现。在对研究结果进行总结的基础上，设计了一套基于Neuroscan的在线BCI游戏系统。该系统可以通过脑电来进行Hangman游戏操作。该系统集成了训练模块，测试模块和游戏模块。能够完成从训练到实际操作的一整套功能。系统使用了C3、C4和O1通道来记录EEG信号，其中C3和C4通道的EEG信号用来提取左右手运动想象任务的脑电特征，O1通道的波作为确认信号。该系统采用了基于相空间重构的特征提取算法和Fisher线性分类器。对6个用户进行实验的结果表明，相空间特征均提高了运动想象任务的识别率，从而证明了相空间特征的有效性。
文章的最后对所有的研究工作进行了总结，指出了论文主要研究工作的内容和取得的成果，并对下一步的工作进行了展望。
Brain-Computer Interface (BCI) is a communication system that helps individualsto drive and control external devices using only their brain activity, withoutparticipation of peripheral nerves and muscles. BCI is an integrated disciplinesincluding neuroscience, signal processing and computer science etc. Over the past20years, BCI has become a research hotspot in the field of international intelligent science.The core of BCI research is how to translate the user’s EEG signals into the controllingcommands for the external devices. So the most important work of the BCI research isto find the proper signal processing and translating method, which can help todistinguish the mentality tasks by the computer quickly and accurately. Generally, theBCI system can be seen as a pattern recognition system. So a successful EEG-basedBCI system very much depends on whether the following two requirements can besatisfied:①The extracted EEG features are able to differentiate the task-oriented brainstates; and②The methods for classifying such features in real-time are efficient. Howto improve the performance of the features and design an efficient classificationalgorithm are two key points.
Nowadays, during the research of BCI based on motor imagery, many featureextraction methods and classification methods applied to EEG generally assume that theEEG signal is linear. However, many researches have shown that the EEG signals arenonlinear. To analyze the EEG signals by linear method will loss much nonlinearfeatures, then the capability of distinguishing different tasks will be decreased. Thispaper, we proposed a new feature extraction method based on the nonlinearcharacteristics of EEG. Then we verified the effectiveness of the new algorithm bysimulations. This paper includes the following aspects of content.
①We analyzed the nonlinear characters of EEG dynamical model. Using phasespace reconstruction technology to reconstruct the EEG signals obtained in the EEGmodel. Then we learned the changing principle of the attractors ofhe with the changesof parameters ofp eeandpe i. We also analyzed the nonlinear characters of the realEEG. The maximum Lyapunov indexes of the samples in the two BCI competition’sdatasets were calculated. The results show that almost all the maximum Lyapunovindexes of the samples are bigger than zero, which confirmed the argument of chaos inthe EEG. So the nonlinear analysis method can be used to analyze the EEG signals.
②Some normal chaos features, maximum Lyapunov index, correlation dimensionand Approximate Entropy (ApEn), are calculated. Those three characters were used asthe features of the BCI. The experimental results showed that the maximum Lyapunovindex and correlation dimension do not suit for differentiating the motor imagery tasks.However, the Approximate Entropy is a measure of the probability for producing newmodels in time series; it is more suitable for distinguishing different tasks. Based on theanalysis of the ApEn features, this paper proposed a feature extraction method andclassification method based on ApEn and time window. The proposed method cansimulate the online situation, and classify the tasks in each window. The simulationshows that the classifiers based on theApEn features can distinguish the tasks well.
③We proposed a feature extraction schemes based on phase space reconstruction.We proved the construction functions have the filtering capacities which can adjust theamplitude and phase of the signals. Then the phase space features can be distinguishedbetween different tasks more easily. Moreover, the features extracted in the proposedscheme can retain the merit of traditional features, at the same time they also contain theinformation of phase space, so it can improve the classification capabilities of theclassifiers. This paper used the benchmark datasets coming from the BCI competition2003and2005. The mutual information (MI) and the maximum steepness of MI areused as the evaluation standards which are also used in the BCI competitions. Thesimulations show that the proposed method is a competitive method. The classifier gotthe maximum MI0.67on the Graz2003dataset, which is the best result ever known.The simulations on Graz2005dataset also obtained some good results. The phase spacefeatures have the good results based on accuracy criteria and mean maximum steepnessof MI.
④In order to solve multi-classification problems using common spatial pattern(CSP), we proposed a combination method based on binary tree termed BCSP, whichput the CSP filters and Fisher classifiers on the nodes of the binary tree. Theclassification process bases on binary search. In BCSP, the number of the filters andclassifiers is less than "one versus rest" method. Moreover, The most calculating stepsto solve the N class problems islog2N, which improves the efficiency and results ofclassification largely.
⑤Developing and realized a BCI online game platform. We developed an onlinegame platform based on the research of this paper. The platform is a game system basedon Neuroscan, and user can play Hangman game by imaging left/right hand moving. The platform has training module, testing module and game module. The user can use itto complete all the training, testing and play actions. C3, C4and O1channels are usedto gather the EEG signal, and the EEG from C3and C4are used to extract the featuresof right/left hand motor imagery tasks. We also used rhythm in O1to act as theconfirming signals. Phase space features and Fisher classifiers are used in this system.Six people took part in the experiments, the experiments results show that the phasespace features improved the classification accuracy, and then it proved the effectivenessof the phase space features.
At the end of the dissertation, we summarized the research contents of this paper,and show the main achievements of the research. Finally, the author points out the nextwork of the future researches.
引文
[1]赵仑. ERPs实验教程[M].南京：东南大学出版社，2010.
[2] J.Vidal. Toword Direct Brain-Computer Communication [J]. Annual Review of Biophysicsand Bioengineering,1973,2(1):157-180.
[3] Wolpaw J R, Birbaumer N, Heetderks W J, et al. Brain-computer interface technology: areview of the first international meeting[J]. IEEE transactions on rehabilitation engineering,2000,8(2):164-173.
[4] Zhou S M, Gan J Q, Sepulveda F. Classifying mental tasks based on features of higher-orderstatistics from EEG signals in brain–computer interface[J]. Information Sciences,2008,178(6):1629-1640.
[5] Obermaier B, Muller G R, Pfurtscheller G." Virtual keyboard" controlled by spontaneousEEG activity[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering,2003,11(4):422-426.
[6] Scherer R, Muller G R, Neuper C, et al. An asynchronously controlled EEG-based virtualkeyboard: improvement of the spelling rate[J]. Biomedical Engineering, IEEE Transactionson,2004,51(6):979-984.
[7] Hochberg L R, Serruya M D, Friehs G M, et al. Neuronal ensemble control of prostheticdevices by a human with tetraplegia[J]. Nature,2006,442(7099):164-171.
[8] Mason S G, Birch G E. A general framework for brain-computer interface design[J]. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on,2003,11(1):70-85.
[9] Scherer R, Lee F, Schlogl A, et al. Toward self-paced brain–computer communication:navigation through virtual worlds[J]. Biomedical Engineering, IEEE Transactions on,2008,55(2):675-682.
[10] Hasan B A S, Gan J Q. Hangman BCI: An unsupervised adaptive self-paced Brain–ComputerInterface for playing games[J]. Computers in biology and medicine,2012,42(5):598-606.
[11]高诺,鲁守银,张运楚,等.脑机接口技术的研究现状及发展趋势[J].机器人技术与应用,2008(4):16-19.
[12] http://www.qstheory.cn/wz/gdian/201003/t20100303_22314.htm
[13]高上凯，浅谈脑一机接口的发展现状与挑战[J]，中国生物医学工程学报，200726（6）：801-809
[14] Scherer R, Pfurtscheller G. Thought-based interaction with the physical world[J]. Trends incognitive sciences,2013,17(10):490-492.
[15] Lance B J, Kerick S E, Ries A J, et al. Brain–Computer Interface Technologies in the ComingDecades[J]. Proceedings of the IEEE,2012,100(Special Centennial Issue):1585-1599.
[16] Wolpaw, Jonathan, and Elizabeth Winter Wolpaw, eds.Brain-computer interfaces: principlesand practice. Oxford University Press,2012.
[17]孙进,张征,周宏甫.基于脑机接口技术的康复机器人综述[J].机电工程技术,2010(4):13-16.
[18] Lotte F, Congedo M, Lécuyer A, et al. A review of classification algorithms for EEG-basedbrain–computer interfaces[J]. Journal of neural engineering,2007,4.
[19] Zander T O, Kothe C. Towards passive brain–computer interfaces: applying brain–computerinterface technology to human–machine systems in general[J]. Journal of Neural Engineering,2011,8(2):025005.
[20] Nicolas-Alonso L F, Gomez-Gil J. Brain computer interfaces, a review[J]. Sensors,2012,12(2):1211-1279.
[21] Wolpaw J R, Birbaumer N, McFarland D J, et al. Brain–computer interfaces forcommunication and control[J]. Clinical neurophysiology,2002,113(6):767-791.
[22]杨力才,李佰敏,李光林,等.脑-机接口技术综述[J][J].电子学报,2005(07)：1234-1241
[23] Regan, D. Human Brain Electrophysiology: Evoked Potentials and Evoked Magnetic Fieldsin Science and Medicine; Elsevier: New York, NY, USA,1989.
[24] Yijun, W.; Ruiping, W.; Xiaorong, G.; Bo, H.; Shangkai, G. A practical VEP-basedbrain-computer interface. IEEE Trans. Neural Syst. Rehabil. Eng.2006,14,234–240.
[25] Lee, P.; Hsieh, J.; Wu, C.; Shyu, K.; Wu, Y. Brain computer interface using flash onsetandoffset visual evoked potentials. Clin. Neurophysiol.2008,119,605–616.
[26] Sutter E E. The brain response interface: communication through visually-induced electricalbrain responses[J]. Journal of Microcomputer Applications,1992,15(1):31-45.
[27] Poryzala, Pawel, and Andrzej Materka."Cluster analysis of CCA coefficients for robustdetection of the asynchronous SSVEPs in brain–computer interfaces." Biomedical SignalProcessing and Control (2013).
[28] Chang M H, Baek H J, Lee S M, et al. An amplitude-modulated visual stimulation forreducing eye fatigue in SSVEP-based brain–computer interfaces[J]. Clinical Neurophysiology,2013.
[29] Hwang H J, Lim J H, Jung Y J, et al. Development of an SSVEP-based BCI spelling systemadopting a QWERTY-style LED keyboard[J]. Journal of neuroscience methods,2012,208(1):59-65.
[30] Xiaorong Gao,Dingfeng Xu,Ming Cheng. A BCI2based environmental controller for themotion2disabled[J]. IEEE Transaction on Neural Sys2tems and RehabilitationEngineering,2003,11(2):137-140.
[31] DENG Z, LI X, ZHENG K, et al.一种基于SSVEP的仿人机器人异步脑机接口控制系统[J].机器人,2011,33(2).
[32] Zhang Y, Xu P, Cheng K, et al. Multivariate synchronization index for frequency recognitionof SSVEP-based brain–computer interface[J]. Journal of neuroscience methods,2014,221:32-40.
[33] Hwang H J, Hwan Kim D, Han C H, et al. A new dual-frequency stimulation method toincrease the number of visual stimuli for multi-class SSVEP-based brain–computer interface(BCI)[J]. brain research,2013,1515:66-77.
[34] Macpherson H, Silberstein R, Pipingas A. Neurocognitive effects of multivitaminsupplementation on the steady state visually evoked potential (SSVEP) measure of brainactivity in elderly women[J]. Physiology&behavior,2012,107(3):346-354.
[35] Allison B Z, Brunner C, Altst tter C, et al. A hybrid ERD/SSVEP BCI for continuoussimultaneous two dimensional cursor control[J]. Journal of neuroscience methods,2012,209(2):299-307.
[36] Wu C H, Chang H C, Lee P L, et al. Frequency recognition in an SSVEP-based braincomputer interface using empirical mode decomposition and refined generalizedzero-crossing[J]. Journal of neuroscience methods,2011,196(1):170-181.
[37] Lopez-Gordo M A, Prieto A, Pelayo F, et al. Customized stimulation enhances performance ofindependent binary SSVEP-BCIs[J]. Clinical Neurophysiology,2011,122(1):128-133.
[38] Bakardjian H, Tanaka T, Cichocki A. Optimization of SSVEPbrain responses with applicationto eight-command Brain–Computer Interface[J]. Neuroscience letters,2010,469(1):34-38.
[39] Hajcak G, MacNamara A, Foti D, et al. The dynamic allocation of attention to emotion:Simultaneous and independent evidence from the late positive potential and steady statevisual evoked potentials[J]. Biological psychology,2013,92(3):447-455.
[40] Edlinger G, Prueckl R, Krausz G, et al. P4-24P300and SSVEP based brain-computerinterface for control of a smart home virtual environment[J]. Clinical Neurophysiology,2010,121: S126.
[41] Farwell L A, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizingevent-related brain potentials[J]. Electroencephalography and clinical Neurophysiology,1988,70(6):510-523.
[42] Aloise F, Schettini F, Aricò P, et al. P300-based brain–computer interface for environmentalcontrol: an asynchronous approach[J]. Journal of neural engineering,2011,8(2):025025.
[43] Zhang H, Guan C, Wang C. Asynchronous P300-based brain--computer interfaces: Acomputational approach with statistical models[J]. Biomedical Engineering, IEEETransactions on,2008,55(6):1754-1763.
[44]王金甲,杨成杰,胡备. P300脑机接口控制智能小车系统的设计与实现[J].生物医学工程学杂志,2013,2:001.
[45]邱天爽,马征.视觉P300脑机接口中的SOA扰动现象[J].数据采集与处理,2013,28(5):539-545.
[46]吴边，苏煜，张剑慧等，基于P300电位的新型BCI中文输入虚拟键盘系统，电子学报，2009，37（8）：1733-1745
[47] Akram F, Han H S, Kim T S. A P300-based brain computer interface system for wordstyping[J]. Computers in Biology and Medicine,2014,45:118-125.
[48] Amini Z, Abootalebi V, Sadeghi M T. Comparison of performance of different featureextraction methods in detection of P300[J]. Biocybernetics and Biomedical Engineering,2013,33(1):3-20.
[49] Shahriari Y, Erfanian A. Improving the performance of P300-based brain–computer interfacethrough subspace-based filtering[J]. Neurocomputing,2013,121:434-441.
[50] Pokorny C, Klobassa D S, Pichler G, et al. The auditory P300-based single-switchbrain–computer interface: Paradigm transition from healthy subjects to minimally consciouspatients[J]. Artificial intelligence in medicine,2013,59(2):81-90.
[51] Birbaumer, N.; Elbert, T.; Canavan, A.G.; Rockstroh, B. Slow potentials of the cerebralcortexand behavior. Physiol. Rev.1990,70,1–41.
[52] Hinterberger, T.; Schmidt, S.; Neumann, N.; Mellinger, J.; Blankertz, B.; Curio, G.; Birbaumer,N. Brain-computer communication and slow cortical potentials. IEEE Trans. Biomed. Eng.2004,51,1011–1018.
[53] Kaiser, J. Self-initiation of EEG-based communication in paralyzed patients. Clin.Neurophysiol.2001,112,551–554.
[54]胡瑞芬，李光，张锦，一种新的脑电特征提取方法研究。仪器仪表学报，2006，27（6）：2187-2188.
[55] Jeannerod, M. Mental imagery in the motor context. Neuropsychologia1995,33,1419–1432.
[56] Pfurtscheller, G.; Neuper, C.; Flotzinger, D.; Pregenzer, M. EEG-based discriminationbetween imagination of right and left hand movement. Electroencephalogr. Clin.Neurophysiol.1997,103,642–651.
[57] Pfurtscheller, G.; Neuper, C. Motor imagery and direct brain-computer communication. Proc.IEEE2001,89,1123–1134.
[58] Blankertz, B.; Sannelli, C.; Halder, S.; Hammer, E.M.; Kübler, A.; Müller, K.R.; Curio,G.;Dickhaus, T. Neurophysiological predictor of SMR-based BCI performance. Neuroimage2010,51,1303–1309.
[59] Tam W K, Tong K, Meng F, et al. A minimal set of electrodes for motor imagery BCI tocontrol an assistive device in chronic stroke subjects: a multi-session study[J]. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on,2011,19(6):617-627.
[60] Coyle D, Garcia J, Satti AR, et al. EEG-based continuous control of a game using a3channelmotor imagery BCI: BCI game[C]//Computational Intelligence, Cognitive Algorithms, Mind,and Brain (CCMB),2011IEEE Symposium on. IEEE,2011:1-7.
[61] D.J. McFarland, L. McCane, L.A. Miner, T.M. Vaughan, J.R. Wolpaw, EEG mu and betarhythm topographies with movement imagery and actual movement, Society for NeuroscienceAbstracts,1997, p.1277.
[62] D.J. McFarland, L. McCane, L.A. Miner, T.M. Vaughan, J.R. Wolpaw, EEG mu and betarhythm topographies with movement imagery and actual movement, Society for NeuroscienceAbstracts,1997, p.1277.
[63]程龙龙,明东,刘双迟,等.脑-机接口研究中想象动作电位的特征提取与分类算法[J].仪器仪表学报,2008,29(8):1772-1778.
[64] Wolpaw, J.R.; McFarland, D.J.; Vaughan, T.M. Brain-computer interface research at theWadsworth Center. IEEE Trans. Rehabil. Eng.2000,8,222–226.
[65] Elisabeth V.C,.Friedrich, Dennis J. McFarland, Christa Neuper, Theresa M. Vaughan, PeterBrunner, Jonathan R. Wolpaw. A scanning protocol for a sensorimotor rhythm-basedbrain–computer interface, Biological Psychology,2009,80:169-175.
[66] Boulay C B, Sarnacki W A, Wolpaw J R, et al. Trained modulation of sensorimotor rhythmscan affect reaction time[J]. Clinical Neurophysiology,2011,122(9):1820-1826.
[67] Krusienski D J, McFarland D J, Wolpaw J R. Value of amplitude, phase, and coherencefeatures for a sensorimotor rhythm-based brain–computer interface[J]. Brain research bulletin,2012,87(1):130-134.
[68] Brain-computer interfaces: principles and practice[M]. Oxford University Press,2012.
[69] Blankertz, B.; Losch, F.; Krauledat, M.; Dornhege, G.; Curio, G.; Muller, K.R. The berlinbrain-computer interface: Accurate performance from first-session in BCI-Na ve subjects.IEEE Trans. Biomed. Eng.2008,55,2452–2462.
[70] Vidaurre C, Pascual J, Ramos-Murguialday A, et al. Neuromuscular electrical stimulationinduced brain patterns to decode motor imagery[J]. Clinical Neurophysiology,2013,124(9):1824-1834.
[71] Haufe S, Meinecke F, G rgen K, et al. On the interpretation of weight vectors of linearmodels in multivariate neuroimaging[J]. NeuroImage,2014,87:96-110.
[72] Hammer E M, Halder S, Blankertz B, et al. Psychological predictors of SMR-BCIperformance[J]. Biological psychology,2012,89(1):80-86.
[73] Pfurtscheller, G.; Neuper, C.; Muller, G.R.; Obermaier, B.; Krausz, G.; Schlogl, A.; Scherer,R.;Graimann, B.; Keinrath, C.; Skliris, D.; et al. Graz-BCI: State of the art and clinicalapplications.IEEE Trans. Neural Sys. Rehabil. Eng.2003,11,1–4.
[74] Solis-Escalante T, Müller-Putz G R, Pfurtscheller G, et al. Cue-induced beta rebound duringwithholding of overt and covert foot movement[J]. Clinical Neurophysiology,2012,123(6):1182-1190.
[75] Pfurtscheller G. S14.1Event-related desynchronization/synchronization: state of the art[J].Clinical Neurophysiology,2011,122: S34-S35.
[76] Solis-Escalante T, Müller-Putz G, Brunner C, et al. Analysis of sensorimotor rhythms for theimplementation of a brain switch for healthy subjects[J]. Biomedical Signal Processing andControl,2010,5(1):15-20.
[77] Christa Neuper, Reinhold Scherer, Selina Wriessnegger, Gert Pfurtscheller, Motor imageryand action observation: Modulation of sensorimotor brain rhythms during mental control of abrain–computer interface.Clinical Neurophysiology,2009，120：239-247
[78] Reinhold Scherer, Gernot R. Müller, Christa Neuper, Bernhard Graimann, and GertPfurtscheller, An Asynchronously Controlled EEG-Based Virtual Keyboard: Improvement ofthe Spelling Rate.IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL.51,NO.6,2004,pp:979-984
[79] G. Pfurtschellera, F.H. Lopes da Silva. Event-related EEG/MEG synchronization anddesynchronization: basic principles. Clinical Neurophysiology,1999,110:1842-1857
[80] Pfurtscheller G, Leeb R, Faller J, et al. Brain-computer interface systems used for virtualreality control[J]. Kim, J.-J.(ed.) Virtual Reality,2011.
[81] Bai, O.; Rathi, V.; Lin, P.; Huang, D.; Battapady, H.; Fei, D.; Schneider, L.; Houdayer,E.;Chen, X.; Hallett, M. Prediction of human voluntary movement before it occurs.Clin.Neurophysiol.2011,122,364–372.
[82] Mousavi E A, Maller J J, Fitzgerald P B, et al. Wavelet common spatial pattern inasynchronous offline brain computer interfaces[J]. Biomedical Signal Processing and Control,2011,6(2):121-128.
[83] Velasco-álvarez F, Ron-Angevin R. Asynchronous brain-computer interface to navigate invirtual environments using one motor imagery[M]//Bio-Inspired Systems: Computational andAmbient Intelligence. Springer Berlin Heidelberg,2009:698-705.
[84] Kus R, Valbuena D, Zygierewicz J, et al. Asynchronous BCI based on motor imagery withautomated calibration and neurofeedback training[J]. Neural Systems and RehabilitationEngineering, IEEE Transactions on,2012,20(6):823-835.
[85] Hasan B A S, Gan J Q. Hangman BCI: An unsupervised adaptive self-paced Brain–ComputerInterface for playing games[J]. Computers in biology and medicine,2012,42(5):598-606.
[86]段放,高小榕.一种基于运动想象的脑-机接口时空滤波器迭代算法[J].中国生物医学工程学报,2011,30(001):11-16.
[87]徐宝国,宋爱国,费树岷.在线脑机接口中脑电信号的特征提取与分类方法[J].电子学报,2011,39(5):1025-1030.
[88]刘冲,赵海滨,李春胜,等.基于CSP与SVM算法的运动想象脑电信号分类[J].东北大学学报:自然科学版,2010(8):1098-1101.
[89] C.J. Stam, Nonlinear dynamical analysis of EEG and MEG:Review of an emerging field,Clinical Neurophysiology116(2005)2266–2301
[90] Sabesan S, Iasemidis L D, Tsakalis K, et al. Use of dynamical measures in prediction andcontrol of focal and generalized epilepsy[J]. Osorio, I.; Zaveri, HP.; Frei, MG,2011:307-320.
[91] Raiesdana S, Goplayegani S. Study on chaos anti-control for hippocampal models ofepilepsy[J]. Neurocomputing,2013,111:54-69.
[92] Huang G, Zhang D, Meng J, et al. Interactions between two neural populations: A mechanismof chaos and oscillation in neural mass model[J]. Neurocomputing,2011,74(6):1026-1034.
[93] Parvinnia E, Sabeti M, Zolghadri Jahromi M, et al. Classification of EEG Signals usingadaptive weighted distance nearest neighbor algorithm[J]. Journal of King SaudUniversity-Computer and Information Sciences,2014,26(1):1-6.
[94] G. Pfurtscheller, Functional brain imaging based on ERD/ERS, Vision research.41(10-11)(2001)1257-1260.
[95] G. Pfurtscheller, A. Aranbibar, Evaluation of event-related desynchronization preceding andfollowing voluntary self-paced movement, Electroencephalogr. Clin. Neurophysiol.46(2)(1979)138-146
[96] B. Blankertz, R. Tomioka, S. Lemm,M. Kawanabe, K. R. Muller, Optimizing spatial filters forrobust EEG single-trial analysis, Signal Processing Magazine, IEEE.25(1)(2008)41-56.
[97] G. Pfurtscheller, C. Brunner, A. Schl¨ogl, F. H. Lopes da Silva, Mu rhythm(de)synchronization and EEG single-trial classification of different motor imagery tasks,NeuroImage.31(1)(2006)153-159.
[98] Pfurtscheller G, Neuper C, Schlogl A, et al. Separability of EEG signals recorded during rightand left motor imagery using adaptive autoregressive parameters[J]. RehabilitationEngineering, IEEE Transactions on,1998,6(3):316-325.
[99] Huang L, Gu J, Li R, et al. A Novel BCI Classifier Based on Autoregressive Model andSupport Vector Machine[J].Advanced Materials Research,2013,694:2522-2525.
[100] Soetraprawata D, Turnip A. Autoregressive Integrated Adaptive Neural Networks Classifierfor EEG-P300Classification[J]. Mechatronics, Electrical Power, and Vehicular Technology,2013,4(1):1-8.
[101] Zhang Y, Xu P, Guo D, et al. Prediction of SSVEP-based BCI performance by theresting-state EEG network[J]. Journal of neural engineering,2013,10(6):066017.
[102] Bhat, Rohit, et al."BCI-Touch based system, a multimodal CAD interface for objectmanipulation." ASME IMECE Conference Proceedings.2013.
[103] Upadhyay R, Kankar P K, Padhy P K, et al. Classification of drowsy and controlled EEGsignals[C]//Engineering (NUiCONE),2012Nirma University International Conference on.IEEE,2012:1-4.
[104] Guo L, Rivero D, Dorado J, et al. Automatic epileptic seizure detection in EEGs based on linelength feature and artificial neural networks[J]. Journal of neuroscience methods,2010,191(1):101-109.
[105] Nonclercq A, Urbain C, Verheulpen D, et al. Sleep spindle detection throughamplitude–frequency normal modelling[J]. Journal of neuroscience methods,2013,214(2):192-203.
[106] Garg G, Suri S, Singh V, et al. Wavelet Energy based Neural Fuzzy Model for AutomaticMotor Imagery Classification[J]. International Journal of Computer Applications,2011,28.
[107] Abibullaev B, An J. Classification of frontal cortex haemodynamic responses during cognitivetasks using wavelet transforms and machine learning algorithms[J]. Medical engineering&physics,2012,34(10):1394-1410.
[108] Park C, Looney D, Ahrabian A, et al. Classification of motor imagery BCI using multivariateempirical mode decomposition[J]. Neural Systems and Rehabilitation Engineering, IEEETransactions on,2013,21(1):10-22.
[109] Rodríguez-Bermúdez G, García-Laencina P J, Roca-González J, et al. Efficient featureselection and linear discrimination of EEG signals[J]. Neurocomputing,2013,115:161-165.
[110] R. Palaniappan, and N. J. Huan, Effects of Hidden Unit Sizes and Autoregressive Features inMental Task Classification, World Academy of Science, Engineering and Technology.12(2005)171-176.
[111] Schl gl A. The electroencephalogram and the adaptive autoregressive model: theory andapplications[M]. Germany: Shaker,2000.[112]张爱华,杨彬,黄玲,等.基于傅里叶变换的脑机接口系统实现方法[J].兰州理工大学学报,2008,34(4):77-82.
[113] Q. Xu, H. Zhou, Y. J. Wang, J. Huang, Fuzzy support vector machine for classification ofEEG signals using wavelet-based features, Medical Engineering&Physics.31(2009)858-865.
[114] M. C. Casdagli, L. D. Iasemidis, R.S. Savi, R. L. Gilmore, S. N. Roper, J. Chris Sackellares,Non-linearity in invasive EEG recordings from patients with temporal lobe epilepsy,Electroencephalography and clinical Neurophysiology.102(2)(1997)98-105.
[115] C. J. Stam, Nonlinear dynamical analysis of EEG and MEG: review of an emerging field,Clinical Neurophysiology.116(10)(2005)2266-2301.
[116] J.P. Dietrich. Phase Space Reconstruction using the frequency domain. Diploma Thesis,University of Potsdam.(2008)
[117] D. T. Liley, P. J. Cadusch,M. P. Dafilis. A spatially continuous mean field theory ofelectrocortical activity. Computation in Neural Systems.13(1)(2002)67-113.
[118] Carlino E, Sigaudo M, Pollo A, et al. Nonlinear analysis of electroencephalogram at rest andduring cognitive tasks in patients with schizophrenia[J]. Journal of psychiatry&neuroscience:JPN,2012,37(4):259.
[119] Fang X, Hu Z, Shi P. Neural mass model driven nonlinear EEG analysis[M]//Medical ImagingandAugmented Reality. Springer Berlin Heidelberg,2010:457-466.
[120] Yuan Q, Zhou W, Li S, et al. Epileptic EEG classification based on extreme learning machineand nonlinear features[J]. Epilepsy research,2011,96(1):29-38.
[121] A. Banitalebi, S. K. Setarehdan, G. A. Hossein-Zadeh. A technique based on chaos for braincomputer interfacing, In Computer Conference,2009. CSICC2009.14th International CSI.IEEE.(2009)464-469.
[122]吕金虎，混沌时间序列分析及其应用，武汉大学出版社，2005年
[123]陆振波，时间序列混沌动力学分析及其在水声中的应用，海军工程大学博士论文。
[124]唐旭东.一种基于混沌过程神经元水下机器人运动控制方法[J].控制与决策,2010,25(2):213-217.
[125]李娟,杨琳,刘金龙,等.基于自适应混沌粒子群优化算法的多目标无功优化[J].电力系统保护与控制,2011,39(9):26-31.
[126]罗志增,李亚飞,孟明,等.脑电信号的混沌分析和小波包变换特征提取算法[J].仪器仪表学报,2011,32(001):33-39.
[127]王瑞琪,李珂,张承慧.基于混沌多目标遗传算法的微网系统容量优化[J].电力系统保护与控制,2011,39(22):16-22.
[128]李春来,禹思敏.一个新的超混沌系统及其自适应追踪控制[J].物理学报,2012,61(4):040504.
[129]许喆,刘崇新,杨韬.一种新型混沌系统的分析及电路实现[J].物理学报,2010(1):131-139.
[130]卢侃，孙建华。混沌学传奇，上海：上海翻译出版公司，1991.
[131] Lorent E N. Deterministic non-periodic flow. spectral vorticity equations[J]. J. Afmos. Sci,1963,19.
[132] Li T Y, Yorke J A. Period three implies chaos[J]. American mathematical monthly,1975:985-992.
[133] Janjarasjitt S, Scher M S, Loparo K A. Nonlinear dynamical analysis of the neonatal EEGtime series: the relationship between sleep state and complexity[J]. Clinical neurophysiology,2008,119(8):1812-1823.
[134] http://zh.wikipedia.org/wiki/%E8%AE%A1%E7%9B%92%E7%BB%B4%E6%95%B0
[135] Takens F. Detecting strange attractors in turbulence[M]//Dynamical systems and turbulence,Warwick1980. Springer Berlin Heidelberg,1981:366-381.
[136] BCI Competition II:2003, URL.
[137] BCI Competition III:2005, URL
[138] Lotte F, Congedo M, Lécuyer A, et al. A review of classification algorithms for EEG-basedbrain–computer interfaces[J]. Journal of neural engineering,2007,4.
[139] R.A. Fisher, The use of multiple measurements in taxonomic problems, Ann. Eugen.7(1936)179-188.
[140] Cortes C, Vapnik V. Support vector machine[J]. Machine learning,1995,20(3):273-297.
[141] J. Muller-Gerking, G. Pfurtscheller, and H. Flyvbjerg,“Designing optimal spatial filters forsingle-trial EEG classification in a movement task,” Clin. Neurophysiol., vol.110, no.5, pp.787–798,1999.
[142] Dornhege G, Blankertz B, Krauledat M, et al. Combined optimization of spatial and temporalfilters for improving brain-computer interfacing[J]. Biomedical Engineering, IEEETransactions on,2006,53(11):2274-2281.
[143] M. Naeem, C. Brunner, R. Leeb, et al., Separability of four-class motor imagery data usinginde-pendent component analysis, Journal of Neural Engineering, vol.32006,208-216
[144] C. Brunner, M. Naeem, R. Leeb, et al., Spatialˉltering and selection of optimizedcomponents in four class motor imagery EEG data using independent components analysis,Pattern Recognition Letters, vol.28(8),2007,957-964
[145] Dornhege G, Blankertz B, Curio G, et al. Boosting bit rates in noninvasive EEG single-trialclassifications by feature combination and multiclass paradigms [J]. Biomedical Engineering,IEEE Transactions on,2004,51(6):993-1002.
[146]刘广权,黄淦,朱向阳.共空域模式方法在多类别分类中的应用[J].中国生物医学工程学报,2009,28(6):935-938.
[147] Dornhege G, Blankertz B, Curio G, et al. Increase Information Transfer Rates in BCI by CSPExtension to Multi-class[C]//NIPS.2003.
[148] C. Brunner, R. Leeb, G. R. Muller-Putz, et al., BCI Competition2008-Graz data setB,http://bbci.de/competition/iv/
[149] Townsend G, Graimann B, Pfurtscheller G. A comparison of common spatial patterns withcomplex band power features in a four-class BCI experiment [J]. Biomedical Engineering,IEEE Transactions on,2006,53(4):642-651.
[2] J.Vidal. Toword Direct Brain-Computer Communication [J]. Annual Review of Biophysicsand Bioengineering,1973,2(1):157-180.
[3] Wolpaw J R, Birbaumer N, Heetderks W J, et al. Brain-computer interface technology: areview of the first international meeting[J]. IEEE transactions on rehabilitation engineering,2000,8(2):164-173.
[4] Zhou S M, Gan J Q, Sepulveda F. Classifying mental tasks based on features of higher-orderstatistics from EEG signals in brain–computer interface[J]. Information Sciences,2008,178(6):1629-1640.
[5] Obermaier B, Muller G R, Pfurtscheller G." Virtual keyboard" controlled by spontaneousEEG activity[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering,2003,11(4):422-426.
[6] Scherer R, Muller G R, Neuper C, et al. An asynchronously controlled EEG-based virtualkeyboard: improvement of the spelling rate[J]. Biomedical Engineering, IEEE Transactionson,2004,51(6):979-984.
[7] Hochberg L R, Serruya M D, Friehs G M, et al. Neuronal ensemble control of prostheticdevices by a human with tetraplegia[J]. Nature,2006,442(7099):164-171.
[8] Mason S G, Birch G E. A general framework for brain-computer interface design[J]. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on,2003,11(1):70-85.
[9] Scherer R, Lee F, Schlogl A, et al. Toward self-paced brain–computer communication:navigation through virtual worlds[J]. Biomedical Engineering, IEEE Transactions on,2008,55(2):675-682.
[10] Hasan B A S, Gan J Q. Hangman BCI: An unsupervised adaptive self-paced Brain–ComputerInterface for playing games[J]. Computers in biology and medicine,2012,42(5):598-606.
[11]高诺,鲁守银,张运楚,等.脑机接口技术的研究现状及发展趋势[J].机器人技术与应用,2008(4):16-19.
[12] http://www.qstheory.cn/wz/gdian/201003/t20100303_22314.htm
[13]高上凯，浅谈脑一机接口的发展现状与挑战[J]，中国生物医学工程学报，200726（6）：801-809
[14] Scherer R, Pfurtscheller G. Thought-based interaction with the physical world[J]. Trends incognitive sciences,2013,17(10):490-492.
[15] Lance B J, Kerick S E, Ries A J, et al. Brain–Computer Interface Technologies in the ComingDecades[J]. Proceedings of the IEEE,2012,100(Special Centennial Issue):1585-1599.
[16] Wolpaw, Jonathan, and Elizabeth Winter Wolpaw, eds.Brain-computer interfaces: principlesand practice. Oxford University Press,2012.
[17]孙进,张征,周宏甫.基于脑机接口技术的康复机器人综述[J].机电工程技术,2010(4):13-16.
[18] Lotte F, Congedo M, Lécuyer A, et al. A review of classification algorithms for EEG-basedbrain–computer interfaces[J]. Journal of neural engineering,2007,4.
[19] Zander T O, Kothe C. Towards passive brain–computer interfaces: applying brain–computerinterface technology to human–machine systems in general[J]. Journal of Neural Engineering,2011,8(2):025005.
[20] Nicolas-Alonso L F, Gomez-Gil J. Brain computer interfaces, a review[J]. Sensors,2012,12(2):1211-1279.
[21] Wolpaw J R, Birbaumer N, McFarland D J, et al. Brain–computer interfaces forcommunication and control[J]. Clinical neurophysiology,2002,113(6):767-791.
[22]杨力才,李佰敏,李光林,等.脑-机接口技术综述[J][J].电子学报,2005(07)：1234-1241
[23] Regan, D. Human Brain Electrophysiology: Evoked Potentials and Evoked Magnetic Fieldsin Science and Medicine; Elsevier: New York, NY, USA,1989.
[24] Yijun, W.; Ruiping, W.; Xiaorong, G.; Bo, H.; Shangkai, G. A practical VEP-basedbrain-computer interface. IEEE Trans. Neural Syst. Rehabil. Eng.2006,14,234–240.
[25] Lee, P.; Hsieh, J.; Wu, C.; Shyu, K.; Wu, Y. Brain computer interface using flash onsetandoffset visual evoked potentials. Clin. Neurophysiol.2008,119,605–616.
[26] Sutter E E. The brain response interface: communication through visually-induced electricalbrain responses[J]. Journal of Microcomputer Applications,1992,15(1):31-45.
[27] Poryzala, Pawel, and Andrzej Materka."Cluster analysis of CCA coefficients for robustdetection of the asynchronous SSVEPs in brain–computer interfaces." Biomedical SignalProcessing and Control (2013).
[28] Chang M H, Baek H J, Lee S M, et al. An amplitude-modulated visual stimulation forreducing eye fatigue in SSVEP-based brain–computer interfaces[J]. Clinical Neurophysiology,2013.
[29] Hwang H J, Lim J H, Jung Y J, et al. Development of an SSVEP-based BCI spelling systemadopting a QWERTY-style LED keyboard[J]. Journal of neuroscience methods,2012,208(1):59-65.
[30] Xiaorong Gao,Dingfeng Xu,Ming Cheng. A BCI2based environmental controller for themotion2disabled[J]. IEEE Transaction on Neural Sys2tems and RehabilitationEngineering,2003,11(2):137-140.
[31] DENG Z, LI X, ZHENG K, et al.一种基于SSVEP的仿人机器人异步脑机接口控制系统[J].机器人,2011,33(2).
[32] Zhang Y, Xu P, Cheng K, et al. Multivariate synchronization index for frequency recognitionof SSVEP-based brain–computer interface[J]. Journal of neuroscience methods,2014,221:32-40.
[33] Hwang H J, Hwan Kim D, Han C H, et al. A new dual-frequency stimulation method toincrease the number of visual stimuli for multi-class SSVEP-based brain–computer interface(BCI)[J]. brain research,2013,1515:66-77.
[34] Macpherson H, Silberstein R, Pipingas A. Neurocognitive effects of multivitaminsupplementation on the steady state visually evoked potential (SSVEP) measure of brainactivity in elderly women[J]. Physiology&behavior,2012,107(3):346-354.
[35] Allison B Z, Brunner C, Altst tter C, et al. A hybrid ERD/SSVEP BCI for continuoussimultaneous two dimensional cursor control[J]. Journal of neuroscience methods,2012,209(2):299-307.
[36] Wu C H, Chang H C, Lee P L, et al. Frequency recognition in an SSVEP-based braincomputer interface using empirical mode decomposition and refined generalizedzero-crossing[J]. Journal of neuroscience methods,2011,196(1):170-181.
[37] Lopez-Gordo M A, Prieto A, Pelayo F, et al. Customized stimulation enhances performance ofindependent binary SSVEP-BCIs[J]. Clinical Neurophysiology,2011,122(1):128-133.
[38] Bakardjian H, Tanaka T, Cichocki A. Optimization of SSVEPbrain responses with applicationto eight-command Brain–Computer Interface[J]. Neuroscience letters,2010,469(1):34-38.
[39] Hajcak G, MacNamara A, Foti D, et al. The dynamic allocation of attention to emotion:Simultaneous and independent evidence from the late positive potential and steady statevisual evoked potentials[J]. Biological psychology,2013,92(3):447-455.
[40] Edlinger G, Prueckl R, Krausz G, et al. P4-24P300and SSVEP based brain-computerinterface for control of a smart home virtual environment[J]. Clinical Neurophysiology,2010,121: S126.
[41] Farwell L A, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizingevent-related brain potentials[J]. Electroencephalography and clinical Neurophysiology,1988,70(6):510-523.
[42] Aloise F, Schettini F, Aricò P, et al. P300-based brain–computer interface for environmentalcontrol: an asynchronous approach[J]. Journal of neural engineering,2011,8(2):025025.
[43] Zhang H, Guan C, Wang C. Asynchronous P300-based brain--computer interfaces: Acomputational approach with statistical models[J]. Biomedical Engineering, IEEETransactions on,2008,55(6):1754-1763.
[44]王金甲,杨成杰,胡备. P300脑机接口控制智能小车系统的设计与实现[J].生物医学工程学杂志,2013,2:001.
[45]邱天爽,马征.视觉P300脑机接口中的SOA扰动现象[J].数据采集与处理,2013,28(5):539-545.
[46]吴边，苏煜，张剑慧等，基于P300电位的新型BCI中文输入虚拟键盘系统，电子学报，2009，37（8）：1733-1745
[47] Akram F, Han H S, Kim T S. A P300-based brain computer interface system for wordstyping[J]. Computers in Biology and Medicine,2014,45:118-125.
[48] Amini Z, Abootalebi V, Sadeghi M T. Comparison of performance of different featureextraction methods in detection of P300[J]. Biocybernetics and Biomedical Engineering,2013,33(1):3-20.
[49] Shahriari Y, Erfanian A. Improving the performance of P300-based brain–computer interfacethrough subspace-based filtering[J]. Neurocomputing,2013,121:434-441.
[50] Pokorny C, Klobassa D S, Pichler G, et al. The auditory P300-based single-switchbrain–computer interface: Paradigm transition from healthy subjects to minimally consciouspatients[J]. Artificial intelligence in medicine,2013,59(2):81-90.
[51] Birbaumer, N.; Elbert, T.; Canavan, A.G.; Rockstroh, B. Slow potentials of the cerebralcortexand behavior. Physiol. Rev.1990,70,1–41.
[52] Hinterberger, T.; Schmidt, S.; Neumann, N.; Mellinger, J.; Blankertz, B.; Curio, G.; Birbaumer,N. Brain-computer communication and slow cortical potentials. IEEE Trans. Biomed. Eng.2004,51,1011–1018.
[53] Kaiser, J. Self-initiation of EEG-based communication in paralyzed patients. Clin.Neurophysiol.2001,112,551–554.
[54]胡瑞芬，李光，张锦，一种新的脑电特征提取方法研究。仪器仪表学报，2006，27（6）：2187-2188.
[55] Jeannerod, M. Mental imagery in the motor context. Neuropsychologia1995,33,1419–1432.
[56] Pfurtscheller, G.; Neuper, C.; Flotzinger, D.; Pregenzer, M. EEG-based discriminationbetween imagination of right and left hand movement. Electroencephalogr. Clin.Neurophysiol.1997,103,642–651.
[57] Pfurtscheller, G.; Neuper, C. Motor imagery and direct brain-computer communication. Proc.IEEE2001,89,1123–1134.
[58] Blankertz, B.; Sannelli, C.; Halder, S.; Hammer, E.M.; Kübler, A.; Müller, K.R.; Curio,G.;Dickhaus, T. Neurophysiological predictor of SMR-based BCI performance. Neuroimage2010,51,1303–1309.
[59] Tam W K, Tong K, Meng F, et al. A minimal set of electrodes for motor imagery BCI tocontrol an assistive device in chronic stroke subjects: a multi-session study[J]. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on,2011,19(6):617-627.
[60] Coyle D, Garcia J, Satti AR, et al. EEG-based continuous control of a game using a3channelmotor imagery BCI: BCI game[C]//Computational Intelligence, Cognitive Algorithms, Mind,and Brain (CCMB),2011IEEE Symposium on. IEEE,2011:1-7.
[61] D.J. McFarland, L. McCane, L.A. Miner, T.M. Vaughan, J.R. Wolpaw, EEG mu and betarhythm topographies with movement imagery and actual movement, Society for NeuroscienceAbstracts,1997, p.1277.
[62] D.J. McFarland, L. McCane, L.A. Miner, T.M. Vaughan, J.R. Wolpaw, EEG mu and betarhythm topographies with movement imagery and actual movement, Society for NeuroscienceAbstracts,1997, p.1277.
[63]程龙龙,明东,刘双迟,等.脑-机接口研究中想象动作电位的特征提取与分类算法[J].仪器仪表学报,2008,29(8):1772-1778.
[64] Wolpaw, J.R.; McFarland, D.J.; Vaughan, T.M. Brain-computer interface research at theWadsworth Center. IEEE Trans. Rehabil. Eng.2000,8,222–226.
[65] Elisabeth V.C,.Friedrich, Dennis J. McFarland, Christa Neuper, Theresa M. Vaughan, PeterBrunner, Jonathan R. Wolpaw. A scanning protocol for a sensorimotor rhythm-basedbrain–computer interface, Biological Psychology,2009,80:169-175.
[66] Boulay C B, Sarnacki W A, Wolpaw J R, et al. Trained modulation of sensorimotor rhythmscan affect reaction time[J]. Clinical Neurophysiology,2011,122(9):1820-1826.
[67] Krusienski D J, McFarland D J, Wolpaw J R. Value of amplitude, phase, and coherencefeatures for a sensorimotor rhythm-based brain–computer interface[J]. Brain research bulletin,2012,87(1):130-134.
[68] Brain-computer interfaces: principles and practice[M]. Oxford University Press,2012.
[69] Blankertz, B.; Losch, F.; Krauledat, M.; Dornhege, G.; Curio, G.; Muller, K.R. The berlinbrain-computer interface: Accurate performance from first-session in BCI-Na ve subjects.IEEE Trans. Biomed. Eng.2008,55,2452–2462.
[70] Vidaurre C, Pascual J, Ramos-Murguialday A, et al. Neuromuscular electrical stimulationinduced brain patterns to decode motor imagery[J]. Clinical Neurophysiology,2013,124(9):1824-1834.
[71] Haufe S, Meinecke F, G rgen K, et al. On the interpretation of weight vectors of linearmodels in multivariate neuroimaging[J]. NeuroImage,2014,87:96-110.
[72] Hammer E M, Halder S, Blankertz B, et al. Psychological predictors of SMR-BCIperformance[J]. Biological psychology,2012,89(1):80-86.
[73] Pfurtscheller, G.; Neuper, C.; Muller, G.R.; Obermaier, B.; Krausz, G.; Schlogl, A.; Scherer,R.;Graimann, B.; Keinrath, C.; Skliris, D.; et al. Graz-BCI: State of the art and clinicalapplications.IEEE Trans. Neural Sys. Rehabil. Eng.2003,11,1–4.
[74] Solis-Escalante T, Müller-Putz G R, Pfurtscheller G, et al. Cue-induced beta rebound duringwithholding of overt and covert foot movement[J]. Clinical Neurophysiology,2012,123(6):1182-1190.
[75] Pfurtscheller G. S14.1Event-related desynchronization/synchronization: state of the art[J].Clinical Neurophysiology,2011,122: S34-S35.
[76] Solis-Escalante T, Müller-Putz G, Brunner C, et al. Analysis of sensorimotor rhythms for theimplementation of a brain switch for healthy subjects[J]. Biomedical Signal Processing andControl,2010,5(1):15-20.
[77] Christa Neuper, Reinhold Scherer, Selina Wriessnegger, Gert Pfurtscheller, Motor imageryand action observation: Modulation of sensorimotor brain rhythms during mental control of abrain–computer interface.Clinical Neurophysiology,2009，120：239-247
[78] Reinhold Scherer, Gernot R. Müller, Christa Neuper, Bernhard Graimann, and GertPfurtscheller, An Asynchronously Controlled EEG-Based Virtual Keyboard: Improvement ofthe Spelling Rate.IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL.51,NO.6,2004,pp:979-984
[79] G. Pfurtschellera, F.H. Lopes da Silva. Event-related EEG/MEG synchronization anddesynchronization: basic principles. Clinical Neurophysiology,1999,110:1842-1857
[80] Pfurtscheller G, Leeb R, Faller J, et al. Brain-computer interface systems used for virtualreality control[J]. Kim, J.-J.(ed.) Virtual Reality,2011.
[81] Bai, O.; Rathi, V.; Lin, P.; Huang, D.; Battapady, H.; Fei, D.; Schneider, L.; Houdayer,E.;Chen, X.; Hallett, M. Prediction of human voluntary movement before it occurs.Clin.Neurophysiol.2011,122,364–372.
[82] Mousavi E A, Maller J J, Fitzgerald P B, et al. Wavelet common spatial pattern inasynchronous offline brain computer interfaces[J]. Biomedical Signal Processing and Control,2011,6(2):121-128.
[83] Velasco-álvarez F, Ron-Angevin R. Asynchronous brain-computer interface to navigate invirtual environments using one motor imagery[M]//Bio-Inspired Systems: Computational andAmbient Intelligence. Springer Berlin Heidelberg,2009:698-705.
[84] Kus R, Valbuena D, Zygierewicz J, et al. Asynchronous BCI based on motor imagery withautomated calibration and neurofeedback training[J]. Neural Systems and RehabilitationEngineering, IEEE Transactions on,2012,20(6):823-835.
[85] Hasan B A S, Gan J Q. Hangman BCI: An unsupervised adaptive self-paced Brain–ComputerInterface for playing games[J]. Computers in biology and medicine,2012,42(5):598-606.
[86]段放,高小榕.一种基于运动想象的脑-机接口时空滤波器迭代算法[J].中国生物医学工程学报,2011,30(001):11-16.
[87]徐宝国,宋爱国,费树岷.在线脑机接口中脑电信号的特征提取与分类方法[J].电子学报,2011,39(5):1025-1030.
[88]刘冲,赵海滨,李春胜,等.基于CSP与SVM算法的运动想象脑电信号分类[J].东北大学学报:自然科学版,2010(8):1098-1101.
[89] C.J. Stam, Nonlinear dynamical analysis of EEG and MEG:Review of an emerging field,Clinical Neurophysiology116(2005)2266–2301
[90] Sabesan S, Iasemidis L D, Tsakalis K, et al. Use of dynamical measures in prediction andcontrol of focal and generalized epilepsy[J]. Osorio, I.; Zaveri, HP.; Frei, MG,2011:307-320.
[91] Raiesdana S, Goplayegani S. Study on chaos anti-control for hippocampal models ofepilepsy[J]. Neurocomputing,2013,111:54-69.
[92] Huang G, Zhang D, Meng J, et al. Interactions between two neural populations: A mechanismof chaos and oscillation in neural mass model[J]. Neurocomputing,2011,74(6):1026-1034.
[93] Parvinnia E, Sabeti M, Zolghadri Jahromi M, et al. Classification of EEG Signals usingadaptive weighted distance nearest neighbor algorithm[J]. Journal of King SaudUniversity-Computer and Information Sciences,2014,26(1):1-6.
[94] G. Pfurtscheller, Functional brain imaging based on ERD/ERS, Vision research.41(10-11)(2001)1257-1260.
[95] G. Pfurtscheller, A. Aranbibar, Evaluation of event-related desynchronization preceding andfollowing voluntary self-paced movement, Electroencephalogr. Clin. Neurophysiol.46(2)(1979)138-146
[96] B. Blankertz, R. Tomioka, S. Lemm,M. Kawanabe, K. R. Muller, Optimizing spatial filters forrobust EEG single-trial analysis, Signal Processing Magazine, IEEE.25(1)(2008)41-56.
[97] G. Pfurtscheller, C. Brunner, A. Schl¨ogl, F. H. Lopes da Silva, Mu rhythm(de)synchronization and EEG single-trial classification of different motor imagery tasks,NeuroImage.31(1)(2006)153-159.
[98] Pfurtscheller G, Neuper C, Schlogl A, et al. Separability of EEG signals recorded during rightand left motor imagery using adaptive autoregressive parameters[J]. RehabilitationEngineering, IEEE Transactions on,1998,6(3):316-325.
[99] Huang L, Gu J, Li R, et al. A Novel BCI Classifier Based on Autoregressive Model andSupport Vector Machine[J].Advanced Materials Research,2013,694:2522-2525.
[100] Soetraprawata D, Turnip A. Autoregressive Integrated Adaptive Neural Networks Classifierfor EEG-P300Classification[J]. Mechatronics, Electrical Power, and Vehicular Technology,2013,4(1):1-8.
[101] Zhang Y, Xu P, Guo D, et al. Prediction of SSVEP-based BCI performance by theresting-state EEG network[J]. Journal of neural engineering,2013,10(6):066017.
[102] Bhat, Rohit, et al."BCI-Touch based system, a multimodal CAD interface for objectmanipulation." ASME IMECE Conference Proceedings.2013.
[103] Upadhyay R, Kankar P K, Padhy P K, et al. Classification of drowsy and controlled EEGsignals[C]//Engineering (NUiCONE),2012Nirma University International Conference on.IEEE,2012:1-4.
[104] Guo L, Rivero D, Dorado J, et al. Automatic epileptic seizure detection in EEGs based on linelength feature and artificial neural networks[J]. Journal of neuroscience methods,2010,191(1):101-109.
[105] Nonclercq A, Urbain C, Verheulpen D, et al. Sleep spindle detection throughamplitude–frequency normal modelling[J]. Journal of neuroscience methods,2013,214(2):192-203.
[106] Garg G, Suri S, Singh V, et al. Wavelet Energy based Neural Fuzzy Model for AutomaticMotor Imagery Classification[J]. International Journal of Computer Applications,2011,28.
[107] Abibullaev B, An J. Classification of frontal cortex haemodynamic responses during cognitivetasks using wavelet transforms and machine learning algorithms[J]. Medical engineering&physics,2012,34(10):1394-1410.
[108] Park C, Looney D, Ahrabian A, et al. Classification of motor imagery BCI using multivariateempirical mode decomposition[J]. Neural Systems and Rehabilitation Engineering, IEEETransactions on,2013,21(1):10-22.
[109] Rodríguez-Bermúdez G, García-Laencina P J, Roca-González J, et al. Efficient featureselection and linear discrimination of EEG signals[J]. Neurocomputing,2013,115:161-165.
[110] R. Palaniappan, and N. J. Huan, Effects of Hidden Unit Sizes and Autoregressive Features inMental Task Classification, World Academy of Science, Engineering and Technology.12(2005)171-176.
[111] Schl gl A. The electroencephalogram and the adaptive autoregressive model: theory andapplications[M]. Germany: Shaker,2000.[112]张爱华,杨彬,黄玲,等.基于傅里叶变换的脑机接口系统实现方法[J].兰州理工大学学报,2008,34(4):77-82.
[113] Q. Xu, H. Zhou, Y. J. Wang, J. Huang, Fuzzy support vector machine for classification ofEEG signals using wavelet-based features, Medical Engineering&Physics.31(2009)858-865.
[114] M. C. Casdagli, L. D. Iasemidis, R.S. Savi, R. L. Gilmore, S. N. Roper, J. Chris Sackellares,Non-linearity in invasive EEG recordings from patients with temporal lobe epilepsy,Electroencephalography and clinical Neurophysiology.102(2)(1997)98-105.
[115] C. J. Stam, Nonlinear dynamical analysis of EEG and MEG: review of an emerging field,Clinical Neurophysiology.116(10)(2005)2266-2301.
[116] J.P. Dietrich. Phase Space Reconstruction using the frequency domain. Diploma Thesis,University of Potsdam.(2008)
[117] D. T. Liley, P. J. Cadusch,M. P. Dafilis. A spatially continuous mean field theory ofelectrocortical activity. Computation in Neural Systems.13(1)(2002)67-113.
[118] Carlino E, Sigaudo M, Pollo A, et al. Nonlinear analysis of electroencephalogram at rest andduring cognitive tasks in patients with schizophrenia[J]. Journal of psychiatry&neuroscience:JPN,2012,37(4):259.
[119] Fang X, Hu Z, Shi P. Neural mass model driven nonlinear EEG analysis[M]//Medical ImagingandAugmented Reality. Springer Berlin Heidelberg,2010:457-466.
[120] Yuan Q, Zhou W, Li S, et al. Epileptic EEG classification based on extreme learning machineand nonlinear features[J]. Epilepsy research,2011,96(1):29-38.
[121] A. Banitalebi, S. K. Setarehdan, G. A. Hossein-Zadeh. A technique based on chaos for braincomputer interfacing, In Computer Conference,2009. CSICC2009.14th International CSI.IEEE.(2009)464-469.
[122]吕金虎，混沌时间序列分析及其应用，武汉大学出版社，2005年
[123]陆振波，时间序列混沌动力学分析及其在水声中的应用，海军工程大学博士论文。
[124]唐旭东.一种基于混沌过程神经元水下机器人运动控制方法[J].控制与决策,2010,25(2):213-217.
[125]李娟,杨琳,刘金龙,等.基于自适应混沌粒子群优化算法的多目标无功优化[J].电力系统保护与控制,2011,39(9):26-31.
[126]罗志增,李亚飞,孟明,等.脑电信号的混沌分析和小波包变换特征提取算法[J].仪器仪表学报,2011,32(001):33-39.
[127]王瑞琪,李珂,张承慧.基于混沌多目标遗传算法的微网系统容量优化[J].电力系统保护与控制,2011,39(22):16-22.
[128]李春来,禹思敏.一个新的超混沌系统及其自适应追踪控制[J].物理学报,2012,61(4):040504.
[129]许喆,刘崇新,杨韬.一种新型混沌系统的分析及电路实现[J].物理学报,2010(1):131-139.
[130]卢侃，孙建华。混沌学传奇，上海：上海翻译出版公司，1991.
[131] Lorent E N. Deterministic non-periodic flow. spectral vorticity equations[J]. J. Afmos. Sci,1963,19.
[132] Li T Y, Yorke J A. Period three implies chaos[J]. American mathematical monthly,1975:985-992.
[133] Janjarasjitt S, Scher M S, Loparo K A. Nonlinear dynamical analysis of the neonatal EEGtime series: the relationship between sleep state and complexity[J]. Clinical neurophysiology,2008,119(8):1812-1823.
[134] http://zh.wikipedia.org/wiki/%E8%AE%A1%E7%9B%92%E7%BB%B4%E6%95%B0
[135] Takens F. Detecting strange attractors in turbulence[M]//Dynamical systems and turbulence,Warwick1980. Springer Berlin Heidelberg,1981:366-381.
[136] BCI Competition II:2003, URL
[137] BCI Competition III:2005, URL
[138] Lotte F, Congedo M, Lécuyer A, et al. A review of classification algorithms for EEG-basedbrain–computer interfaces[J]. Journal of neural engineering,2007,4.
[139] R.A. Fisher, The use of multiple measurements in taxonomic problems, Ann. Eugen.7(1936)179-188.
[140] Cortes C, Vapnik V. Support vector machine[J]. Machine learning,1995,20(3):273-297.
[141] J. Muller-Gerking, G. Pfurtscheller, and H. Flyvbjerg,“Designing optimal spatial filters forsingle-trial EEG classification in a movement task,” Clin. Neurophysiol., vol.110, no.5, pp.787–798,1999.
[142] Dornhege G, Blankertz B, Krauledat M, et al. Combined optimization of spatial and temporalfilters for improving brain-computer interfacing[J]. Biomedical Engineering, IEEETransactions on,2006,53(11):2274-2281.
[143] M. Naeem, C. Brunner, R. Leeb, et al., Separability of four-class motor imagery data usinginde-pendent component analysis, Journal of Neural Engineering, vol.32006,208-216
[144] C. Brunner, M. Naeem, R. Leeb, et al., Spatialˉltering and selection of optimizedcomponents in four class motor imagery EEG data using independent components analysis,Pattern Recognition Letters, vol.28(8),2007,957-964
[145] Dornhege G, Blankertz B, Curio G, et al. Boosting bit rates in noninvasive EEG single-trialclassifications by feature combination and multiclass paradigms [J]. Biomedical Engineering,IEEE Transactions on,2004,51(6):993-1002.
[146]刘广权,黄淦,朱向阳.共空域模式方法在多类别分类中的应用[J].中国生物医学工程学报,2009,28(6):935-938.
[147] Dornhege G, Blankertz B, Curio G, et al. Increase Information Transfer Rates in BCI by CSPExtension to Multi-class[C]//NIPS.2003.
[148] C. Brunner, R. Leeb, G. R. Muller-Putz, et al., BCI Competition2008-Graz data setB,http://bbci.de/competition/iv/
[149] Townsend G, Graimann B, Pfurtscheller G. A comparison of common spatial patterns withcomplex band power features in a four-class BCI experiment [J]. Biomedical Engineering,IEEE Transactions on,2006,53(4):642-651.