EEG时空特征分析及其在BCI中的应用
|
摘要
脑机接口(Brain Computer Interface, BCI)是在人脑和计算机或其它外部设备之间建立的一种直接的信息交互和控制通道,它是不依赖于大脑正常输出通路(外围神经系统及肌肉组织)的全新的信息交互系统。BCI正成为脑科学、生物医学及康复工程、智能信息处理等领域的一个研究热点。本文主要针对非侵入式基于脑电(EEG)信号的BCI系统进行研究,本质上就是识别特定思维任务下的EEG特征模式,但由于EEG信号非平稳性且及其微弱,使得从高噪音环境下提取可靠信号特征非常困难。本文从EEG信号特点出发,主要在实验设计,神经生理学机理,特征提取算法,以及在线BCI系统设计等方面展开研究,并侧重于时空特征提取算法的研究。
本文的主要贡献和创新点体现在以下几个方面:
(1)神经生理学机理研究:本文研究了运动想象与事件相关去同步/同步(ERD/ERS)的持续时间之间的关系,通过大量实验发现了重复固定动作想象任务能产生持续的ERD/ERS现象,提出了一种任务相关持续去同步/同步(TRSD/TRSS)概念。由于TRSD/TRSS比ERD/ERS优势在于不仅具有非锁相性,而且也具有非锁时性,因此更适合于异步BCI系统。
(2)时空特征提取算法(TSP):研究并采用了独立剩余量分析(IRA)算法来提取具有时序结构的独立分量,并在此基础上进一步提取最优的空间滤波模式,最后结合互信息来进行特征选择,得到最优的时序空间特征模式,该算法能够同时提取EEG信号的时序特征以及空间特征,并提高分类准确率。
(3)公共空间频率模式(CSFP):为了在寻找最优空间模式的同时考虑频率模式对运动想象的作用,我们提出了一种对空间与频率模式同时优化的算法,并且扩展到多类情形下。用连续小波时频分析方法,并设计最优化代价函数来得到最大化某类协方差而最小化另外一类协方差的空间频率模式,从而得到最具辨别能力的空间滤波与频率模式。实验数据分析表明该算法能得到较好的分类性能。
(4)增量公共空间模式(ICSP):为了适应EEG信号的非平稳性,特征提取算法必须具有可自适应性。本文设计了一种基于增量学习模式的公共空间模式(Common Spatial Pattern, CSP)算法,能够实时更新特征模式,从而更加适合于在线BCI系统。
(5)非负稀疏张量分解(NTSF)与公共张量辨别分析(CTDA):张量分解算法近年来得到了广泛的研究并应用在信号处理领域,本文在非负张量分解算法基础上,研究了新型的稀疏性限制条件,提出了一种非负张量稀疏分解算法。应用在EEG信号的特征提取中,能够同时考虑EEG信号的时域、频率、空域等多维特征。由于在类别上设置了稀疏限制,从而保证了分解后得到最具有辨别能力的张量基,并通过投影到张量基上得到最优的特征系数。另外,本文把基于矩阵操作的CSP算法扩展到张量意义上,提出了一种公共张量辨别分析算法,该算法可以同时对角化多类EEG的高维协方差张量,并得到多维度上最优公共张量模式以及最佳分类特征。
(6)BCI游戏与3D虚拟环境下“脑驱车”系统:首先,设计了一种新型的BCI游戏用脑思维活动来打老鼠,采用了多种滑动窗口技术,并对不同的时间窗口长度进行了研究与分析,得到了具有快速反应能力的BCI系统,该研究为BCI开辟了一种新型应用娱乐功能。其次,针对异步BCI问题,开发了一种3D虚拟现实中意念驾驶汽车系统,利用了TRSD/TRSS的持续时间为BCI提供了一种额外的控制参数,据此可实现复杂的控制功能,如小车方向盘转动角度与小车速度的控制。另外在控制策略上研究了一种累积增量控制策略,并且具有一定的容错能力。该研究建立了一种新型、异步、自主的BCI系统,提供了更加接近自然的交互方式。
总之,本文研究了大脑在特定思维活动下的EEG信号模式以及动态变化特征,进一步揭示了思维想象运动的神经学机理,提出的多种特征提取算法能够从复杂EEG信号中读取不同肢体运动想象相关的时间-空间-频率模式,最高信息传输率可达到0.55bps,提高了现有BCI系统的性能与鲁棒性;设计了新型异步、自主的实时BCI系统,能够在复杂环境下控制外部装置,为残疾人辅助设备,新型BCI以及数字娱乐提供了技术原型与理论基础。
The BCI system aims at creating new direct information interaction and communicationchannels between brain and computer without depending on brain’s normal output channelsof peripheral nerves and muscles. The BCI research has drawn attention of scientists in brainscience, rehabilitation engineering, biomedical engineering and intelligent information pro-cessing. In this paper, we mainly focus on non-invasive BCI systems based on EEG signalsfrom which several motor imagery (MI) tasks can be recognized. Due to the non-stabilityand weakness of EEG signals, it is very difficult to extract reliable features from EEG signalswith high noise, especially for the spontaneous MI related EEG. According to the charac-teristic of EEG signals, we mainly research on several aspects including experiment design,neurophysiology mechanism, feature extraction algorithms and online BCI systems, and em-phasize particularly on EEG spatio-temporal feature extraction.
The main contributions and innovations of this paper have been listed as below:
(1) Neurophysiology mechanism. We investigated the relationship between MI andduration of ERD/ERS. Experimental results have demonstrated that repetitive fixed MI canproduce sustained ERD/ERS, which can be viewed as Task Related Sustained Desynchro-nization/Synchronization (TRSD/TRSS). The key advantages of TRSD/TRSS are not onlynon-phase-locked but also non-time-locked to the cue stimulus. Hence, it is more suitablefor asynchronous BCI.
(2) Temporal spatial pattern (TSP). We apply independent residual analysis to extractindependent components with temporal structure, from which we can further extract optimalspatial patterns. Finally, feature selection is performed using mutual information betweenlabels and features. Therefore, the optimal temporal and spatial features of EEG signals canbe obtained simultaneously and classification accuracy has been improved.
(3) Common spatial frequency pattern (CSFP). In order to consider the effects of fre-quency patterns for classification of MI during spatial pattern calculation. The proposed CSFP algorithm allows the simultaneous optimization of spatial and frequency patterns en-hancing discriminability of EEG signals by time-frequency analysis based on continuouswavelet transform. Experimental results has demonstrated that better performance can beachieved by CSFP when compared to common spatial pattern (CSP).
(4) Incremental common spatial pattern (ICSP). To deal with the non-stationary EEG,feature extraction algorithm must has self-adaptive ability. This paper proposed a novel ICSPalgorithm which can update spatial patterns in real time by incremental learning manner.Hence, it is very suitable for online BCI system.
(5) Non-negative tensor sparse factorization (NTSF) and Common tensor discrimina-tive analysis (CTDA). Tensor factorization has been widely focused recently. Based on thenon-negative tensor factorization algorithm, we proposed a new sparseness constraint con-dition and developed the non-negative tensor sparse factorization (NTSF) algorithm whichhas been used in feature extraction of EEG. By the sparseness on the condition mode, themaximal discriminative tensor bases on multi-modes can be obtained and optimal feature co-efficients have been achieved by projecting EEG to tensor bases. Furthermore, we extendedthe CSP based on matrix operation to tensor sense and proposed CTDA algorithm which candiagonalize high dimension covariance tensor of multi-class EEG and obtain common tensorpatterns and maximal discriminant features for classification.
(6) BCI game and“Mind-driven Car”. We developed two novel BCI applications.The first one is hit-rat game by different MI tasks (synchronous BCI). We have applied slid-ing window techniques to achieve fast response for BCI and analyzed classification perfor-mance with different window length. Furthermore, this game will open a new entertainmentapplication for BCI. The second one is driving a car in 3D Virtual Reality Environmentsby thought. The duration of ERD/ERS caused by MI can be modulated and used as an ad-ditional control parameter beyond simple binary decisions. By this strategy, the complexcontrol functions can be achieved such as control of steering wheel angle and car speed.Furthermore, by cumulative incremental control strategy, the steering wheel rotates moresmoothly, which make the BCI system has error tolerant ability. This system is an asyn-chronous, self-paced BCI which provides a more natural interaction manner.
In summary, this paper have investigated EEG patterns and dynamic features duringspecific mental tasks, and proposed several novel feature extraction algorithms which canextract temporal, spatial, and frequency patterns related to MI from complicated EEG sig-nals. We have improved classification accuracy and response speed of MI based BCI bythe novel feature extraction algorithms. The best information transfer rate of 0.55bps can be achieved by our methods. Furthermore, based on these algorithms, we developed anasynchronous, self-paced, real-time BCI system which provided more complicated controlfunctions. These results further reveal neurophysiology mechanism corresponding to MItasks, and provide technology prototype and theory basis for new BCI applications.
本文的主要贡献和创新点体现在以下几个方面:
(1)神经生理学机理研究:本文研究了运动想象与事件相关去同步/同步(ERD/ERS)的持续时间之间的关系,通过大量实验发现了重复固定动作想象任务能产生持续的ERD/ERS现象,提出了一种任务相关持续去同步/同步(TRSD/TRSS)概念。由于TRSD/TRSS比ERD/ERS优势在于不仅具有非锁相性,而且也具有非锁时性,因此更适合于异步BCI系统。
(2)时空特征提取算法(TSP):研究并采用了独立剩余量分析(IRA)算法来提取具有时序结构的独立分量,并在此基础上进一步提取最优的空间滤波模式,最后结合互信息来进行特征选择,得到最优的时序空间特征模式,该算法能够同时提取EEG信号的时序特征以及空间特征,并提高分类准确率。
(3)公共空间频率模式(CSFP):为了在寻找最优空间模式的同时考虑频率模式对运动想象的作用,我们提出了一种对空间与频率模式同时优化的算法,并且扩展到多类情形下。用连续小波时频分析方法,并设计最优化代价函数来得到最大化某类协方差而最小化另外一类协方差的空间频率模式,从而得到最具辨别能力的空间滤波与频率模式。实验数据分析表明该算法能得到较好的分类性能。
(4)增量公共空间模式(ICSP):为了适应EEG信号的非平稳性,特征提取算法必须具有可自适应性。本文设计了一种基于增量学习模式的公共空间模式(Common Spatial Pattern, CSP)算法,能够实时更新特征模式,从而更加适合于在线BCI系统。
(5)非负稀疏张量分解(NTSF)与公共张量辨别分析(CTDA):张量分解算法近年来得到了广泛的研究并应用在信号处理领域,本文在非负张量分解算法基础上,研究了新型的稀疏性限制条件,提出了一种非负张量稀疏分解算法。应用在EEG信号的特征提取中,能够同时考虑EEG信号的时域、频率、空域等多维特征。由于在类别上设置了稀疏限制,从而保证了分解后得到最具有辨别能力的张量基,并通过投影到张量基上得到最优的特征系数。另外,本文把基于矩阵操作的CSP算法扩展到张量意义上,提出了一种公共张量辨别分析算法,该算法可以同时对角化多类EEG的高维协方差张量,并得到多维度上最优公共张量模式以及最佳分类特征。
(6)BCI游戏与3D虚拟环境下“脑驱车”系统:首先,设计了一种新型的BCI游戏用脑思维活动来打老鼠,采用了多种滑动窗口技术,并对不同的时间窗口长度进行了研究与分析,得到了具有快速反应能力的BCI系统,该研究为BCI开辟了一种新型应用娱乐功能。其次,针对异步BCI问题,开发了一种3D虚拟现实中意念驾驶汽车系统,利用了TRSD/TRSS的持续时间为BCI提供了一种额外的控制参数,据此可实现复杂的控制功能,如小车方向盘转动角度与小车速度的控制。另外在控制策略上研究了一种累积增量控制策略,并且具有一定的容错能力。该研究建立了一种新型、异步、自主的BCI系统,提供了更加接近自然的交互方式。
总之,本文研究了大脑在特定思维活动下的EEG信号模式以及动态变化特征,进一步揭示了思维想象运动的神经学机理,提出的多种特征提取算法能够从复杂EEG信号中读取不同肢体运动想象相关的时间-空间-频率模式,最高信息传输率可达到0.55bps,提高了现有BCI系统的性能与鲁棒性;设计了新型异步、自主的实时BCI系统,能够在复杂环境下控制外部装置,为残疾人辅助设备,新型BCI以及数字娱乐提供了技术原型与理论基础。
The BCI system aims at creating new direct information interaction and communicationchannels between brain and computer without depending on brain’s normal output channelsof peripheral nerves and muscles. The BCI research has drawn attention of scientists in brainscience, rehabilitation engineering, biomedical engineering and intelligent information pro-cessing. In this paper, we mainly focus on non-invasive BCI systems based on EEG signalsfrom which several motor imagery (MI) tasks can be recognized. Due to the non-stabilityand weakness of EEG signals, it is very difficult to extract reliable features from EEG signalswith high noise, especially for the spontaneous MI related EEG. According to the charac-teristic of EEG signals, we mainly research on several aspects including experiment design,neurophysiology mechanism, feature extraction algorithms and online BCI systems, and em-phasize particularly on EEG spatio-temporal feature extraction.
The main contributions and innovations of this paper have been listed as below:
(1) Neurophysiology mechanism. We investigated the relationship between MI andduration of ERD/ERS. Experimental results have demonstrated that repetitive fixed MI canproduce sustained ERD/ERS, which can be viewed as Task Related Sustained Desynchro-nization/Synchronization (TRSD/TRSS). The key advantages of TRSD/TRSS are not onlynon-phase-locked but also non-time-locked to the cue stimulus. Hence, it is more suitablefor asynchronous BCI.
(2) Temporal spatial pattern (TSP). We apply independent residual analysis to extractindependent components with temporal structure, from which we can further extract optimalspatial patterns. Finally, feature selection is performed using mutual information betweenlabels and features. Therefore, the optimal temporal and spatial features of EEG signals canbe obtained simultaneously and classification accuracy has been improved.
(3) Common spatial frequency pattern (CSFP). In order to consider the effects of fre-quency patterns for classification of MI during spatial pattern calculation. The proposed CSFP algorithm allows the simultaneous optimization of spatial and frequency patterns en-hancing discriminability of EEG signals by time-frequency analysis based on continuouswavelet transform. Experimental results has demonstrated that better performance can beachieved by CSFP when compared to common spatial pattern (CSP).
(4) Incremental common spatial pattern (ICSP). To deal with the non-stationary EEG,feature extraction algorithm must has self-adaptive ability. This paper proposed a novel ICSPalgorithm which can update spatial patterns in real time by incremental learning manner.Hence, it is very suitable for online BCI system.
(5) Non-negative tensor sparse factorization (NTSF) and Common tensor discrimina-tive analysis (CTDA). Tensor factorization has been widely focused recently. Based on thenon-negative tensor factorization algorithm, we proposed a new sparseness constraint con-dition and developed the non-negative tensor sparse factorization (NTSF) algorithm whichhas been used in feature extraction of EEG. By the sparseness on the condition mode, themaximal discriminative tensor bases on multi-modes can be obtained and optimal feature co-efficients have been achieved by projecting EEG to tensor bases. Furthermore, we extendedthe CSP based on matrix operation to tensor sense and proposed CTDA algorithm which candiagonalize high dimension covariance tensor of multi-class EEG and obtain common tensorpatterns and maximal discriminant features for classification.
(6) BCI game and“Mind-driven Car”. We developed two novel BCI applications.The first one is hit-rat game by different MI tasks (synchronous BCI). We have applied slid-ing window techniques to achieve fast response for BCI and analyzed classification perfor-mance with different window length. Furthermore, this game will open a new entertainmentapplication for BCI. The second one is driving a car in 3D Virtual Reality Environmentsby thought. The duration of ERD/ERS caused by MI can be modulated and used as an ad-ditional control parameter beyond simple binary decisions. By this strategy, the complexcontrol functions can be achieved such as control of steering wheel angle and car speed.Furthermore, by cumulative incremental control strategy, the steering wheel rotates moresmoothly, which make the BCI system has error tolerant ability. This system is an asyn-chronous, self-paced BCI which provides a more natural interaction manner.
In summary, this paper have investigated EEG patterns and dynamic features duringspecific mental tasks, and proposed several novel feature extraction algorithms which canextract temporal, spatial, and frequency patterns related to MI from complicated EEG sig-nals. We have improved classification accuracy and response speed of MI based BCI bythe novel feature extraction algorithms. The best information transfer rate of 0.55bps can be achieved by our methods. Furthermore, based on these algorithms, we developed anasynchronous, self-paced, real-time BCI system which provided more complicated controlfunctions. These results further reveal neurophysiology mechanism corresponding to MItasks, and provide technology prototype and theory basis for new BCI applications.
引文
[1] J.R. Wolpaw, D.J. McFarland, and T.M. Vaughan. Brain-computer interface research at theWadsworth Center. Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. onNeural Systems and Rehabilitation], 8(2):222–226, 2000.
[2] K.R. Mu¨ller and B. Blankertz. Toward noninvasive brain-computer interfaces. IEEE Signal Pro-cessing Magazine, 23(5):125–128, 2006.
[3] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B. Kotchoubey, A. Kubler, J. Perelmouter,E. Taub, and H. Flor. A spelling device for the paralysed. Nature, 398(6725):297–8, 1999.
[4] J.R. Wolpaw, D.J. McFarland, and E. Bizzi. Control of a Two-Dimensional Movement Signal bya Noninvasive Brain-Computer Interface in Humans. Proceedings of the National Academy ofSciences of the United States of America, 101(51):17849–17854, 2004.
[5] J.R. Wolpaw, N. Birbaumer, D.J. McFarland, G. Pfurtscheller, and T.M. Vaughan. Brain–computerinterfaces for communication and control. Clinical Neurophysiology, 113(6):767–791, 2002.
[6] K.R. Muller, M. Krauledat, G. Dornhege, G. Curio, and B. Blankertz. Machine learning techniquesfor brain-computer interfaces. Biomed. Tech, 49(1):11–22, 2004.
[7] B. Hjorth. EEG analysis based on time domain properties. Electroencephalogr Clin Neurophysiol,29(3):306–10, 1970.
[8] A. Delorme and S. Makeig. EEGLAB: an open source toolbox for analysis of single-trial EEGdynamics including independent component analysis. J Neurosci Methods, 134(1):9–21, 2004.
[9] G. Pfurtscheller, D. Flotzinger, and J. Kalcher. Brain-computer interface: a new communicationdevice for handicapped persons. Journal of Microcomputer Applications, 16(3):293–299, 1993.
[10] J.R. Wolpaw, H. Ramoser, D.J. McFarland, and G. Pfurtscheller. EEG-based communication:improved accuracy by response verification. Rehabilitation Engineering, IEEE Transactions on[see also IEEE Trans. on Neural Systems and Rehabilitation], 6(3):326–333, 1998.
[11] J.R. Wolpaw, D.J. McFarland, T.M. Vaughan, and G. Schalk. The Wadsworth Center brain-computer interface (BCI) research and development program. Neural Systems and Rehabilita-tion Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering],11(2):1–4, 2003.
[12] E.C. Leuthardt, G. Schalk, J.R. Wolpaw, J.G. Ojemann, and D.W. Moran. A brain–computerinterface using electrocorticographic signals in humans. Journal of Neural Engineering, 1(2):63–71, 2004.
[13] G. Pfurtscheller, C. Guger, G. Mu¨ller, G. Krausz, and C. Neuper. Brain oscillations control handorthosis in a tetraplegic. Neuroscience Letters, 292(3):211–214, 2000.
[14] J.R. Wolpaw, D. Flotzinger, G. Pfurtscheller, and D.J. McFarland. Timing of EEG-Based CursorControl. Journal of Clinical Neurophysiology, 14(6):529, 1997.
[15] A. Kubler, F. Nijboer, J. Mellinger, T.M. Vaughan, H. Pawelzik, G. Schalk, D.J. McFarland, N.Birbaumer, and J.R. Wolpaw. Patients with ALS can use sensorimotor rhythms to operate a brain-computer interface. Neurology, 64(10):1775–1777, 2005.
[16] G. Schalk, D.J. McFarland, T. Hinterberger, N. Birbaumer, and J.R. Wolpaw. BCI2000: a general-purpose brain-computer interface (BCI) system. Biomedical Engineering, IEEE Transactions on,51(6):1034–1043, 2004.
[17] G. Pfurtscheller, C. Brunner, A. Schlo¨gl, and F.H. Lopes da Silva. Mu rhythm (de) synchronizationand EEG single-trial classification of different motor imagery tasks. Neuroimage, 31(1):153–159,2006.
[18] G. Pfurtscheller and C. Neuper. Motor imagery and direct brain-computer communication. Pro-ceedings of the IEEE, 89(7):1123–1134, 2001.
[19] G. Pfurtscheller and A. Aranibar. Evaluation of event-related desynchronization (ERD) precedingand following voluntary self-paced movement. Electroencephalogr Clin Neurophysiol, 46(2):138–46, 1979.
[20] T.M. Vaughan, W.J. Heetderks, L.J. Trejo, W.Z. Rymer, M. Weinrich, M.M. Moore, A. Kubler, B.H.Dobkin, N. Birbaumer, E. Donchin, et al. Brain-computer interface technology: a review of theSecond International Meeting. Neural Systems and Rehabilitation Engineering, IEEE Transactionson, 11(2):94–109, 2003.
[21] G. Schalk, J.R. Wolpaw, D.J. McFarland, and G. Pfurtscheller. EEG-based communication: pres-ence of an error potential. Clinical Neurophysiology, 111(12):2138–2144, 2000.
[22] D.J. McFarland, W.A. Sarnacki, and J.R. Wolpaw. Brain–computer interface (BCI) operation:optimizing information transfer rates. Biological Psychology, 63(3):237–251, 2003.
[23] D.J. McFarland and J.R. Wolpaw. EEG-Based Communication and Control: Speed–AccuracyRelationships. Applied Psychophysiology and Biofeedback, 28(3):217–231, 2003.
[24] C. Neuper and G. Pfurtscheller. Event-related dynamics of cortical rhythms: frequency-specificfeatures and functional correlates. International Journal of Psychophysiology, 43(1):41–58, 2001.
[25] D.J. McFarland, C.W. Anderson, K.R. Muller, A. Schlogl, and D.J. Krusienski. BCI meeting2005-workshop on BCI signal processing: feature extraction and translation. Neural Systems andRehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engi-neering], 14(2):135–138, 2006.
[26] M. Cheng, W. Jia, X. Gao, S. Gao, and F. Yang. Mu rhythm-based cursor control: an of?ineanalysis. Clinical Neurophysiology, 115(4):745–751, 2004.
[27] Y. Li, X. Gao, H. Liu, and S. Gao. Classification of single-trial electroencephalogram during fingermovement. Biomedical Engineering, IEEE Transactions on, 51(6):1019–1025, 2004.
[28] M. Cheng, X. Gao, S. Gao, and D. Xu. Design and implementation of a brain-computer interfacewith high transfer rates. Biomedical Engineering, IEEE Transactions on, 49(10):1181–1186, 2002.
[29] X. Gao, D. Xu, M. Cheng, and S. Gao. A BCI-based environmental controller for the motion-disabled. Neural Systems and Rehabilitation Engineering, IEEE Transactions on [see also IEEETrans. on Rehabilitation Engineering], 11(2):137–140, 2003.
[30] B. Blankertz, K.R. Muller, D.J. Krusienski, G. Schalk, J.R. Wolpaw, A. Schlogl, G. Pfurtscheller,J.D.R. Millan, M. Schroder, and N. Birbaumer. The BCI competition III: validating alternativeapproaches to actual BCI problems. IEEE Transactions on Neural Systems and RehabilitationEngineering, 14(2):153–159, 2006.
[31] G. Blanchard and B. Blankertz. BCI competition 2003-data set IIa: spatial patterns of self-controlled brain rhythm modulations. Biomedical Engineering, IEEE Transactions on, 51(6):1062–1066, 2004.
[32] N. Xu, X. Gao, B. Hong, X. Miao, S. Gao, and F. Yang. BCI competition 2003-data set IIb: enhanc-ing P300 wave detection using ICA-based subspace projections for BCI applications. BiomedicalEngineering, IEEE Transactions on, 51(6):1067–1072, 2004.
[33] Y. Wang, Z. Zhang, Y. Li, X. Gao, S. Gao, and F. Yang. BCI competition 2003-data set IV: Analgorithm based on CSSD and FDA for classifying single-trial EEG. Biomedical Engineering,IEEE Transactions on, 51(6):1081–1086, 2004.
[34] J. Mu¨ller-Gerking, G. Pfurtscheller, and H. Flyvbjerg. Designing optimal spatial filters for single-trial EEG classification in a movement task. Clinical Neurophysiology, 110(5):787–798, 1999.
[35] S.G. Mason and G.E. Birch. A general framework for brain-computer interface design. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabil-itation Engineering], 11(1):70–85, 2003.
[36] D.J. McFarland and J.R. Wolpaw. Sensorimotor rhythm-based brain-computer interface (BCI): fea-ture selection by regression improves performance. Neural Systems and Rehabilitation Engineer-ing, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering], 13(3):372–379,2005.
[37] B. Blankertz, G. Curio, and K.R. Mu¨ller. Classifying Single Trial EEG: Towards Brain ComputerInterfacing. Advances in Neural Information Processing Systems 14: Proceedings of the 2002 [sic]Conference, 2002.
[38] C. Brunner, B. Graimann, J.E. Huggins, S.P. Levine, and G. Pfurtscheller. Phase relationshipsbetween different subdural electrode recordings in man. Neuroscience Letters, 375(2):69–74, 2005.
[39] G. Dornhege, B. Blankertz, G. Curio, and K.R. Mu¨ller. Combining features for BCI. Advances inNeural Inf. Proc. Systems (NIPS 02), 15:1115–1122, 2003.
[40] Y. Gao, M.J. Black, E. Bienenstock, S. Shoham, and J.P. Donoghue. Probabilistic Inference ofHand Motion from Neural Activity in Motor Cortex. Advances in Neural Information ProcessingSystems 14: Proceedings of the 2002 [sic] Conference, 2002.
[41] D.J. McFarland, W.A. Sarnacki, T.M. Vaughan, and J.R. Wolpaw. Brain-computer interface (BCI)operation: signal and noise during early training sessions. Clinical Neurophysiology, 116(1):56–62, 2005.
[42] O. Chapelle, P. Haffner, and V.N. Vapnik. Support vector machines for histogram-based imageclassification. Neural Networks, IEEE Transactions on, 10(5):1055–1064, 1999.
[43] M.A.L. Nicolelis. Actions from thoughts. Nature, 409(6818):403–407, 2001.
[44] J. Wessberg, C.R. Stambaugh, J.D. Kralik, P.D. Beck, M. Laubach, J.K. Chapin, J. Kim, S.J. Biggs,M.A. Srinivasan, and M.A. Nicolelis. Real-time prediction of hand trajectory by ensembles ofcortical neurons in primates. Nature, 408(6810):361–5, 2000.
[45] D.M. Taylor, S.I.H. Tillery, and A.B. Schwartz. Direct Cortical Control of 3D NeuroprostheticDevices. Science, 296(5574):1829, 2002.
[46] J.K. Chapin, K.A. Moxon, R.S. Markowitz, and M.A.L. Nicolelis. Real-time control of a robotarm using simultaneously recorded neurons in the motor cortex. Nature Neuroscience, 2:664–670,1999.
[47] L.R. Hochberg, M.D. Serruya, G.M. Friehs, J.A. Mukand, M. Saleh, A.H. Caplan, A. Branner, D.Chen, R.D. Penn, and J.P. Donoghue. Neuronal ensemble control of prosthetic devices by a humanwith tetraplegia. Nature, 442:164–171, 2006.
[48] P.R. Kennedy, R.A.E. Bakay, M.M. Moore, K. Adams, J. Goldwaithe, N.S. Inc, and G.A. Atlanta.Direct control of a computer from the human central nervous system. Rehabilitation Engineering,IEEE Transactions on [see also IEEE Trans. on Neural Systems and Rehabilitation], 8(2):198–202,2000.
[49] P.G. Patil, J.M. Carmena, M.A.L. Nicolelis, and D.A. Turner. Ensemble recordings of human sub-cortical neurons as a source of motor control signals for a brain-machine interface. Neurosurgery,55(1):27–35, 2004.
[50] E.A. Curran and M.J. Stokes. Learning to control brain activity: A review of the productionand control of EEG components for driving brain–computer interface (BCI) systems. Brain andCognition, 51(3):326–336, 2003.
[51] G.E. Fabiani, D.J. McFarland, J.R. Wolpaw, and G. Pfurtscheller. Conversion of EEG activity intocursor movement by a brain-computer interface (BCI). Neural Systems and Rehabilitation Engi-neering, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering], 12(3):331–338, 2004.
[52] C. Guger, H. Ramoser, and G. Pfurtscheller. Real-time EEG analysis with subject-specific spatialpatterns for abrain-computer interface (BCI). Rehabilitation Engineering, IEEE Transactions on[see also IEEE Trans. on Neural Systems and Rehabilitation], 8(4):447–456, 2000.
[53] G. Pfurtscheller, C. Neuper, C. Guger, W. Harkam, H. Ramoser, A. Schlogl, B. Obermaier, andM. Pregenzer. Current trends in Graz brain-computer interface (BCI) research. RehabilitationEngineering, IEEE Transactions on [see also IEEE Trans. on Neural Systems and Rehabilitation],8(2):216–219, 2000.
[54] G. Pfurtscheller, G.R. Muller-Putz, J. Pfurtscheller, and R. Rupp. EEG-Based Asynchronous BCIControls Functional Electrical Stimulation in a Tetraplegic Patient. Eurasip Journal On AppliedSignal Processing, 19:3152, 2005.
[55] G. Pfurtscheller, R. Leeb, C. Keinrath, D. Friedman, C. Neuper, C. Guger, and M. Slater. Walkingfrom thought. Brain Research, 1071(1):145–152, 2006.
[56] B. Blankertz, G. Dornhege, S. Lemm, M. Krauledat, G. Curio, and K.R. Mu¨ller. The Berlin Brain-Computer Interface: Machine learning based detection of user specific brain states. Journal ofUniversal Computer Science, 12(6):581–607, 2006.
[57] B. Blankertz, G. Dornhege, M. Krauledat, K.R. Mu¨ller, and G. Curio. The non-invasive BerlinBrain–Computer Interface: Fast acquisition of effective performance in untrained subjects. Neu-roimage, 37(2):539–550, 2007.
[58] B. Blankertz, G. Dornhege, M. Krauledat, M. Schro¨der, J. Williamson, R. Murray-Smith, and K.R.Mu¨ller. The Berlin Brain-Computer Interface presents the novel mental typewriter Hex-o-Spell.In Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course2006, pages 108–109, 2006.
[59] R. Wang, X. Gao, and S. Gao. Frequency Selection for SSVEP-based Binocular Rivalry. NeuralEngineering, 2005. Conference Proceedings. 2nd International IEEE EMBS Conference on, pages600–603, 2005.
[60] Y. Wang, Z. Zhang, X. Gao, and S. Gao. Lead selection for SSVEP-based brain-computer interface.Engineering in Medicine and Biology Society, 2004. EMBC 2004. Conference Proceedings. 26thAnnual International Conference of the, 2, 2004.
[61] Y. Wang, B. Hong, X. Gao, and S. Gao. Implementation of a Brain-Computer Interface Based onThree States of Motor Imagery. Engineering in Medicine and Biology Society, 2007. EMBS 2007.29th Annual International Conference of the IEEE, pages 5059–5062, 2007.
[62] M. Middendorf, G. McMillan, G. Calhoun, and K.S. Jones. Brain-computer interfaces based on thesteady-state visual-evokedresponse. Rehabilitation Engineering, IEEE Transactions on [see alsoIEEE Trans. on Neural Systems and Rehabilitation], 8(2):211–214, 2000.
[63] E.E. Sutter. The brain response interface: communication through visually-induced electrical brainresponses. Journal of Microcomputer Applications, 15(1):31–45, 1992.
[64] E. Donchin, D. Karis, T.R. Bashore, M.G.H. Coles, and G. Gratton. Cognitive psychophysiol-ogy and human information processing. Psychophysiology: Systems, processes, and applications,pages 244–267, 1986.
[65] L.A. FARWELL and E. DONCHIN. Talking off the top of your head: toward a mental prosthe-sis utilizing event-related brain potentials. Electroencephalography and clinical neurophysiology,70(6):510–523, 1988.
[66] N. Birbaumer, T. Elbert, A.G. Canavan, and B. Rockstroh. Slow potentials of the cerebral cortexand behavior, 1990.
[67] N. Birbaumer, A. Kubler, N. Ghanayim, T. Hinterberger, J. Perelmouter, J. Kaiser, I. Iversen, B.Kotchoubey, N. Neumann, and H. Flor. The thought translation device (TTD) for completelyparalyzedpatients. Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. onNeural Systems and Rehabilitation], 8(2):190–193, 2000.
[68] N. Birbaumer, T. Hinterberger, A. Kubler, and N. Neumann. The thought-translation device (TTD):neurobehavioral mechanisms and clinical outcome. Neural Systems and Rehabilitation Engineer-ing, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering], 11(2):120–123,2003.
[69] S.R. Filipovic′, M. Jahanshahi, and J.C. Rothwell. Uncoupling of contingent negative variationand alpha band event-related desynchronization in a go/no-go task. Clinical Neurophysiology,112(7):1307–1315, 2001.
[70] J. Annett. Motor imagery: Perception or action? Neuropsychologia, 33(11):1395–1417, 1995.
[71] G. Pfurtscheller and A. Aranibar. Event-related cortical desynchronization detected by power mea-surements of scalp EEG. Electroencephalogr Clin Neurophysiol, 42(6):817–26, 1977.
[72] G. Pfurtscheller and F.H. Lopes da Silva. Event-related EEG/MEG synchronization and desyn-chronization: basic principles. Clinical Neurophysiology, 110(11):1842–1857, 1999.
[73] L. Zhang. Temporal Independent Component Analysis for Separating Noisy Signals. Lecture NotesIn Computer Science, pages 1064–1069, 2004.
[74] S. Amari and A. Cichocki. Adaptive blind signal processing - neural network approaches. Pro-ceedings of the IEEE, 86(10):2026–2048, 1998.
[75] D.T. Pham. Mutual information approach to blind separation of stationary sources. InformationTheory, IEEE Transactions on, 48(7):1935–1946, 2002.
[76] S. Amari and J.F. Cardoso. Blind Source Separation-Semiparametric Statistical Approach. SignalProcessing, IEEE Transactions on, 45(11), 1997.
[77] L. Q. Zhang, S. Amari, and A. Cichocki. Geometrical structures of fir manifold and multichannelblind deconvolution. Journal of VLIS for Signal Processing Systems, (31):31–44, 2002.
[78] L. Q. Zhang, A. Cichocki, and S. Amari. Self-adaptive blind source separation based on activationfunctions adaptation. Neural Networks, IEEE Transactions on, 15(2), Mar 2004.
[79] Christopher J. James and Oliver J. Gibson. Temporally constrained ica: An application to artifactrejection in electromagnetic brain signal analysis. 50(9):1108–1116, Sep 2003.
[80] W. Lu and J. C. Rajapakse. Ica with reference. In Proc. 3rd Int.Conf. Independent ComponentAnalysis and Blind Signal Separation:ICA2001, pages 120–125, 2001.
[81] G.Pfurtscheller, Ch.Neuper, et al. Eeg-based discrimination between imagination of right and lefthand movement. Electroencephalography and clinical Neurophysiology, 103:342–651, 1997.
[82] Z.J. Koles and A.C. Soong. EEG source localization: implementing the spatio-temporal decompo-sition approach. Electroencephalogr Clin Neurophysiol, 107(5):343–52, 1998.
[83] A. Blum and P. Langley. Selection of Relevant Features and Examples in Machine Learning.Artificial Intelligence, 97(1-2):245–271, 1997.
[84] N. Kwak and C.H. Choi. Improved mutual information feature selector for neural networks insu-pervised learning. Neural Networks, 1999. IJCNN’99. International Joint Conference on, 2, 1999.
[85] Y. Li and C. Guan. A Semi-supervised SVM Learning Algorithm for Joint Feature Extraction andClassification in Brain Computer Interfaces. Engineering in Medicine and Biology Society, 2006.EMBS’06. 28th Annual International Conference of the IEEE, pages 2570–2573, 2006.
[86] R. Tomioka, J. Hill, B. Blankertz, and K. Aihara. Adapting Spatial Filtering Methods for Nonsta-tionary BCIs. transformation, 10:1.
[87] Y.N. Rao and J.C. Principe. An RLS type algorithm for generalized eigendecomposition. NeuralNetworks for Signal Processing XI, 2001. Proceedings of the 2001 IEEE Signal Processing SocietyWorkshop, pages 263–272, 2001.
[88] G.H. Golub and C.F. Van Loan. Matrix Computations. Johns Hopkins University Press, 1996.
[89] H.Ramoser, J.Mu¨ller-Gerking, and G.Pfurtscheller. Optimal spatial filtering of single trial eegduring imagined hand movement. 8(40):441–446, Dec 2000.
[90] J.Mu¨ller-Gerking, G.Pfurtscheller, and H.Flyvbjerg. Designing optimal spatial filters for single-trial eeg classification in a movement tast. Clinical Neurophysiology, 110:787–798, 1999.
[91] S. Lemm, B. Blankertz, G. Curio, and K.R. Muller. Spatio-Spectral Filters for Improving theClassification of Single Trial EEG. Biomedical Engineering, IEEE Transactions on, 52(9):1541–1548, 2005.
[92] G. Dornhege, B. Blankertz, M. Krauledat, F. Losch, G. Curio, and K.R. Muller. Optimizing spatio-temporal filters for improving brain-computer interfacing. Advances in Neural Information Pro-cessing Systems (NIPS), 5:315–322, 2006.
[93] G. Dornhege, B. Blankertz, M. Krauledat, F. Losch, G. Curio, and K.R. Mu¨ller. Combined op-timization of spatial and temporal filters for improving brain-computer interfacing. BiomedicalEngineering, IEEE Transactions on, 53(11):2274–2281, 2006.
[94] V. Bostanov and B. Kotchoubey. The t-CWT: A new ERP detection and quantification methodbased on the continuous wavelet transform and Student’s t-statistics. Clinical Neurophysiology,117(12):2627–2644, 2006.
[95] M. M?rup, L.K. Hansen, and S.M. Arnfred. ERPWAVELAB A toolbox for multi-channel anal-ysis of time–frequency transformed event related potentials. Journal of Neuroscience Methods,161(2):361–368, 2007.
[96] N. Yamawaki, C. Wilke, Z. Liu, and B. He. An enhanced time-frequency-spatial approach formotor imagery classification. Neural Systems and Rehabilitation Engineering, IEEE transactionson, 14(2):250, 2006.
[97] F.L. Hitchcock. The expression of a tensor or a polyadic as a sum of products. J. Math. Phys,6(1):164–189, 1927.
[98] R.B. Cattell.“Parallel proportional profiles”and other principles for determining the choice offactors by rotation. Psychometrika, 9(4):267–283, 1944.
[99] R.B. CATTELL. The three basic factor-analytic research designs-their interrelations and deriva-tives. Psychol Bull, 49(5):499–520, 1952.
[100] L.R. Tucker. The extension of factor analysis to three-dimensional matrices. Contributions toMathematical Psychology, pages 109–127, 1964.
[101] L.R. Tucker. Some mathematical notes on three-mode factor analysis. Psychometrika, 31(3):279–311, 1966.
[102] J.D. Carroll and J.J. Chang. Analysis of individual differences in multidimensional scaling via ann-way generalization of“Eckart-Young”decomposition. Psychometrika, 35(3):283–319, 1970.
[103] R.A. Harshman. Foundations of the PARAFAC procedure: Models and conditions for an”explana-tory”multi-modal factor analysis. UCLA Working Papers in Phonetics, 16:1–84, 1970.
[104] C.J. Appellof and E.R. Davidson. Strategies for analyzing data from video ?uorometric monitoringof liquid chromatographic ef?uents. Analytical Chemistry, 53(13):2053–2056, 1981.
[105] L. De Lathauwer and B. De Moor. From matrix to tensor: Multilinear algebra and signal processing.Mathematics in Sig. Proc., IMA Conf. Series, Warwick, Dec, pages 17–19, 1996.
[106] N.D. Sidiropoulos, R. Bro, and G.B. Giannakis. Parallel factor analysis in sensor array processing.Signal Processing, IEEE Transactions on [see also Acoustics, Speech, and Signal Processing, IEEETransactions on], 48(8):2377–2388, 2000.
[107] P. Comon. Tensor decompositions. Mathematics in Signal Processing V, pages 1–24, 2001.
[108] V.S. GRIGORASCU and P.A. REGALIA. Tensor displacement structures and polyspectral match-ing. Fast Reliable Algorithms for Matrices with Structure, 1999.
[109] T.G. Kolda. Multilinear operators for higher-order decompositions. Technical report, TechnicalReport SAND2006-2081, Sandia National Laboratories, Livermore, CA. http://csmr. ca. sandia.gov/ tgkolda/pubs/SAND2006-2081. pdf, 2006.
[110] M.A.O. Vasilescu and D. Terzopoulos. Multilinear analysis of image ensembles: Tensorfaces.Proc. European Conf. on Computer Vision (ECCV 2002), pages 447–460.
[111] E. Acar, S.A. C? amtepe, M.S. Krishnamoorthy, and B. Yener. Modeling and multiway analysisof chatroom tensors. Intelligence and Security Informatics: IEEE Intl. Conf. on Intelligence andSecurity Informatics, ISI, pages 19–20, 2005.
[112] J. Sun, S. Papadimitriou, and P.S. Yu. Window-based tensor analysis on high-dimensional andmulti-aspect streams. ICDM06: Proceedings of the 6th IEEE Conference on Data Mining, pages1076–1080.
[113] C.F. Beckmann and S.M. Smith. Tensorial extensions of independent component analysis for mul-tisubject FMRI analysis. Neuroimage, 25(1):294–311, 2005.
[114] E. Mart??nez-Montes, P.A. Valde′s-Sosa, F. Miwakeichi, R.I. Goldman, and M.S. Cohen. Concur-rent EEG/fMRI analysis by multiway Partial Least Squares. Neuroimage, 22(3):1023–1034, 2004.
[115] M. M?rup, L.K. Hansen, C.S. Herrmann, J. Parnas, and S.M. Arnfred. Parallel Factor Analysisas an exploratory tool for wavelet transformed event-related EEG. Neuroimage, 29(3):938–947,2006.
[116] D.D. Lee and H.S. Seung. Learning the parts of objects by non-negative matrix factorization.Nature, 401(6755):788–791, 1999.
[117] D.D. Lee and H.S. Seung. Algorithms for non-negative matrix factorization. Advances in NeuralInformation Processing Systems, 13:556–562, 2001.
[118] B.A. Olshausen et al. Emergence of simple-cell receptive field properties by learning a sparse codefor natural images. Nature, 381(6583):607–609, 1996.
[119] GF Harpur. Low entropy coding with unsupervised neural networks. Unpublished doctoral disser-tation, Cambridge University, 1997.
[120] P.O. Hoyer. Non-negative Matrix Factorization with Sparseness Constraints. The Journal of Ma-chine Learning Research, 5:1457–1469, 2004.
[121] T. Gruber, P. Malinowski, and M.M. Muller. Modulation of oscillatory brain activity and evokedpotentials in a repetition priming task in the human EEG. European Journal of Neuroscience,19(4):1073–1082, 2004.
[122] C.S. Herrmann, M. Grigutsch, and N.A. Busch. EEG oscillations and wavelet analysis. Event-Related Potentials-A Methods Handbook, pages 229–259, 2005.
[123] C.S. Herrmann, M.H.J. Munk, and A.K. Engel. Cognitive functions of gamma-band activity: mem-ory match and utilization. Trends in Cognitive Sciences, 8(8):347–355, 2004.
[124] J.P. Lachaux, N. George, C. Tallon-Baudry, J. Martinerie, L. Hugueville, L. Minotti, P. Kahane, andB. Renault. The many faces of the gamma band response to complex visual stimuli. Neuroimage,25(2):491–501, 2005.
[125] M.D. Serruya, N.G. Hatsopoulos, L. Paninski, M.R. Fellows, and J.P. Donoghue. Instant neuralcontrol of a movement signal. Nature, 416(6877):141–2, 2002.
[126] S. Musallam, B.D. Corneil, B. Greger, H. Scherberger, and R.A. Andersen. Cognitive ControlSignals for Neural Prosthetics. Science, 305(5681):258–262, 2004.
[127] J.M. Carmena, M.A. Lebedev, R.E. Crist, J.E. O’Doherty, D.M. Santucci, D.F. Dimitrov, P.G. Patil,C.S. Henriquez, and M.A.L. Nicolelis. Learning to control a brain-machine interface for reachingand grasping by primates. PLoS Biology, 1(2):e2, 2003.
[128] G. Santhanam, S.I. Ryu, B.M. Yu, A. Afshar, and K.V. Shenoy. A high-performance brain-computer interface. Nature, 442(7099):195–198, 2006.
[129] G. Pfurtscheller, C. Neuper, G.R. Muller, B. Obermaier, G. Krausz, A. Schlogl, R. Scherer, B.Graimann, C. Keinrath, D. Skliris, et al. Graz-BCI: state of the art and clinical applications. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabil-itation Engineering], 11(2):1–4, 2003.
[130] E.E. Fetz. Real-time control of a robotic arm by neuronal ensembles. Nature Neuroscience, 2:583–584, 1999.
[131] J.P. Donoghue. Connecting cortex to machines: recent advances in brain interfaces. Nature Neu-roscience, 5(supp):1085–1088, 2002.
[132] A. Cichocki and S. Amari. Adaptive blind signal and image processing, volume 1. Wiley, May2002.
[133] A. Alkan and M.K. Kiymik. Comparison of AR and Welch Methods in Epileptic Seizure Detection.Journal of Medical Systems, 30(6):413–419, 2006.
[134] M. Pregenzer and G. Pfurtscheller. Frequency component selection for an EEG-based brain tocomputerinterface. Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. onNeural Systems and Rehabilitation], 7(4):413–419, 1999.
[135] C.C. Chang and C.J. Lin. LIBSVM: a library for support vector machines. Software available athttp://www. csie. ntu. edu. tw/cjlin/libsvm, 80:604–611, 2001.
[2] K.R. Mu¨ller and B. Blankertz. Toward noninvasive brain-computer interfaces. IEEE Signal Pro-cessing Magazine, 23(5):125–128, 2006.
[3] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B. Kotchoubey, A. Kubler, J. Perelmouter,E. Taub, and H. Flor. A spelling device for the paralysed. Nature, 398(6725):297–8, 1999.
[4] J.R. Wolpaw, D.J. McFarland, and E. Bizzi. Control of a Two-Dimensional Movement Signal bya Noninvasive Brain-Computer Interface in Humans. Proceedings of the National Academy ofSciences of the United States of America, 101(51):17849–17854, 2004.
[5] J.R. Wolpaw, N. Birbaumer, D.J. McFarland, G. Pfurtscheller, and T.M. Vaughan. Brain–computerinterfaces for communication and control. Clinical Neurophysiology, 113(6):767–791, 2002.
[6] K.R. Muller, M. Krauledat, G. Dornhege, G. Curio, and B. Blankertz. Machine learning techniquesfor brain-computer interfaces. Biomed. Tech, 49(1):11–22, 2004.
[7] B. Hjorth. EEG analysis based on time domain properties. Electroencephalogr Clin Neurophysiol,29(3):306–10, 1970.
[8] A. Delorme and S. Makeig. EEGLAB: an open source toolbox for analysis of single-trial EEGdynamics including independent component analysis. J Neurosci Methods, 134(1):9–21, 2004.
[9] G. Pfurtscheller, D. Flotzinger, and J. Kalcher. Brain-computer interface: a new communicationdevice for handicapped persons. Journal of Microcomputer Applications, 16(3):293–299, 1993.
[10] J.R. Wolpaw, H. Ramoser, D.J. McFarland, and G. Pfurtscheller. EEG-based communication:improved accuracy by response verification. Rehabilitation Engineering, IEEE Transactions on[see also IEEE Trans. on Neural Systems and Rehabilitation], 6(3):326–333, 1998.
[11] J.R. Wolpaw, D.J. McFarland, T.M. Vaughan, and G. Schalk. The Wadsworth Center brain-computer interface (BCI) research and development program. Neural Systems and Rehabilita-tion Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering],11(2):1–4, 2003.
[12] E.C. Leuthardt, G. Schalk, J.R. Wolpaw, J.G. Ojemann, and D.W. Moran. A brain–computerinterface using electrocorticographic signals in humans. Journal of Neural Engineering, 1(2):63–71, 2004.
[13] G. Pfurtscheller, C. Guger, G. Mu¨ller, G. Krausz, and C. Neuper. Brain oscillations control handorthosis in a tetraplegic. Neuroscience Letters, 292(3):211–214, 2000.
[14] J.R. Wolpaw, D. Flotzinger, G. Pfurtscheller, and D.J. McFarland. Timing of EEG-Based CursorControl. Journal of Clinical Neurophysiology, 14(6):529, 1997.
[15] A. Kubler, F. Nijboer, J. Mellinger, T.M. Vaughan, H. Pawelzik, G. Schalk, D.J. McFarland, N.Birbaumer, and J.R. Wolpaw. Patients with ALS can use sensorimotor rhythms to operate a brain-computer interface. Neurology, 64(10):1775–1777, 2005.
[16] G. Schalk, D.J. McFarland, T. Hinterberger, N. Birbaumer, and J.R. Wolpaw. BCI2000: a general-purpose brain-computer interface (BCI) system. Biomedical Engineering, IEEE Transactions on,51(6):1034–1043, 2004.
[17] G. Pfurtscheller, C. Brunner, A. Schlo¨gl, and F.H. Lopes da Silva. Mu rhythm (de) synchronizationand EEG single-trial classification of different motor imagery tasks. Neuroimage, 31(1):153–159,2006.
[18] G. Pfurtscheller and C. Neuper. Motor imagery and direct brain-computer communication. Pro-ceedings of the IEEE, 89(7):1123–1134, 2001.
[19] G. Pfurtscheller and A. Aranibar. Evaluation of event-related desynchronization (ERD) precedingand following voluntary self-paced movement. Electroencephalogr Clin Neurophysiol, 46(2):138–46, 1979.
[20] T.M. Vaughan, W.J. Heetderks, L.J. Trejo, W.Z. Rymer, M. Weinrich, M.M. Moore, A. Kubler, B.H.Dobkin, N. Birbaumer, E. Donchin, et al. Brain-computer interface technology: a review of theSecond International Meeting. Neural Systems and Rehabilitation Engineering, IEEE Transactionson, 11(2):94–109, 2003.
[21] G. Schalk, J.R. Wolpaw, D.J. McFarland, and G. Pfurtscheller. EEG-based communication: pres-ence of an error potential. Clinical Neurophysiology, 111(12):2138–2144, 2000.
[22] D.J. McFarland, W.A. Sarnacki, and J.R. Wolpaw. Brain–computer interface (BCI) operation:optimizing information transfer rates. Biological Psychology, 63(3):237–251, 2003.
[23] D.J. McFarland and J.R. Wolpaw. EEG-Based Communication and Control: Speed–AccuracyRelationships. Applied Psychophysiology and Biofeedback, 28(3):217–231, 2003.
[24] C. Neuper and G. Pfurtscheller. Event-related dynamics of cortical rhythms: frequency-specificfeatures and functional correlates. International Journal of Psychophysiology, 43(1):41–58, 2001.
[25] D.J. McFarland, C.W. Anderson, K.R. Muller, A. Schlogl, and D.J. Krusienski. BCI meeting2005-workshop on BCI signal processing: feature extraction and translation. Neural Systems andRehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engi-neering], 14(2):135–138, 2006.
[26] M. Cheng, W. Jia, X. Gao, S. Gao, and F. Yang. Mu rhythm-based cursor control: an of?ineanalysis. Clinical Neurophysiology, 115(4):745–751, 2004.
[27] Y. Li, X. Gao, H. Liu, and S. Gao. Classification of single-trial electroencephalogram during fingermovement. Biomedical Engineering, IEEE Transactions on, 51(6):1019–1025, 2004.
[28] M. Cheng, X. Gao, S. Gao, and D. Xu. Design and implementation of a brain-computer interfacewith high transfer rates. Biomedical Engineering, IEEE Transactions on, 49(10):1181–1186, 2002.
[29] X. Gao, D. Xu, M. Cheng, and S. Gao. A BCI-based environmental controller for the motion-disabled. Neural Systems and Rehabilitation Engineering, IEEE Transactions on [see also IEEETrans. on Rehabilitation Engineering], 11(2):137–140, 2003.
[30] B. Blankertz, K.R. Muller, D.J. Krusienski, G. Schalk, J.R. Wolpaw, A. Schlogl, G. Pfurtscheller,J.D.R. Millan, M. Schroder, and N. Birbaumer. The BCI competition III: validating alternativeapproaches to actual BCI problems. IEEE Transactions on Neural Systems and RehabilitationEngineering, 14(2):153–159, 2006.
[31] G. Blanchard and B. Blankertz. BCI competition 2003-data set IIa: spatial patterns of self-controlled brain rhythm modulations. Biomedical Engineering, IEEE Transactions on, 51(6):1062–1066, 2004.
[32] N. Xu, X. Gao, B. Hong, X. Miao, S. Gao, and F. Yang. BCI competition 2003-data set IIb: enhanc-ing P300 wave detection using ICA-based subspace projections for BCI applications. BiomedicalEngineering, IEEE Transactions on, 51(6):1067–1072, 2004.
[33] Y. Wang, Z. Zhang, Y. Li, X. Gao, S. Gao, and F. Yang. BCI competition 2003-data set IV: Analgorithm based on CSSD and FDA for classifying single-trial EEG. Biomedical Engineering,IEEE Transactions on, 51(6):1081–1086, 2004.
[34] J. Mu¨ller-Gerking, G. Pfurtscheller, and H. Flyvbjerg. Designing optimal spatial filters for single-trial EEG classification in a movement task. Clinical Neurophysiology, 110(5):787–798, 1999.
[35] S.G. Mason and G.E. Birch. A general framework for brain-computer interface design. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabil-itation Engineering], 11(1):70–85, 2003.
[36] D.J. McFarland and J.R. Wolpaw. Sensorimotor rhythm-based brain-computer interface (BCI): fea-ture selection by regression improves performance. Neural Systems and Rehabilitation Engineer-ing, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering], 13(3):372–379,2005.
[37] B. Blankertz, G. Curio, and K.R. Mu¨ller. Classifying Single Trial EEG: Towards Brain ComputerInterfacing. Advances in Neural Information Processing Systems 14: Proceedings of the 2002 [sic]Conference, 2002.
[38] C. Brunner, B. Graimann, J.E. Huggins, S.P. Levine, and G. Pfurtscheller. Phase relationshipsbetween different subdural electrode recordings in man. Neuroscience Letters, 375(2):69–74, 2005.
[39] G. Dornhege, B. Blankertz, G. Curio, and K.R. Mu¨ller. Combining features for BCI. Advances inNeural Inf. Proc. Systems (NIPS 02), 15:1115–1122, 2003.
[40] Y. Gao, M.J. Black, E. Bienenstock, S. Shoham, and J.P. Donoghue. Probabilistic Inference ofHand Motion from Neural Activity in Motor Cortex. Advances in Neural Information ProcessingSystems 14: Proceedings of the 2002 [sic] Conference, 2002.
[41] D.J. McFarland, W.A. Sarnacki, T.M. Vaughan, and J.R. Wolpaw. Brain-computer interface (BCI)operation: signal and noise during early training sessions. Clinical Neurophysiology, 116(1):56–62, 2005.
[42] O. Chapelle, P. Haffner, and V.N. Vapnik. Support vector machines for histogram-based imageclassification. Neural Networks, IEEE Transactions on, 10(5):1055–1064, 1999.
[43] M.A.L. Nicolelis. Actions from thoughts. Nature, 409(6818):403–407, 2001.
[44] J. Wessberg, C.R. Stambaugh, J.D. Kralik, P.D. Beck, M. Laubach, J.K. Chapin, J. Kim, S.J. Biggs,M.A. Srinivasan, and M.A. Nicolelis. Real-time prediction of hand trajectory by ensembles ofcortical neurons in primates. Nature, 408(6810):361–5, 2000.
[45] D.M. Taylor, S.I.H. Tillery, and A.B. Schwartz. Direct Cortical Control of 3D NeuroprostheticDevices. Science, 296(5574):1829, 2002.
[46] J.K. Chapin, K.A. Moxon, R.S. Markowitz, and M.A.L. Nicolelis. Real-time control of a robotarm using simultaneously recorded neurons in the motor cortex. Nature Neuroscience, 2:664–670,1999.
[47] L.R. Hochberg, M.D. Serruya, G.M. Friehs, J.A. Mukand, M. Saleh, A.H. Caplan, A. Branner, D.Chen, R.D. Penn, and J.P. Donoghue. Neuronal ensemble control of prosthetic devices by a humanwith tetraplegia. Nature, 442:164–171, 2006.
[48] P.R. Kennedy, R.A.E. Bakay, M.M. Moore, K. Adams, J. Goldwaithe, N.S. Inc, and G.A. Atlanta.Direct control of a computer from the human central nervous system. Rehabilitation Engineering,IEEE Transactions on [see also IEEE Trans. on Neural Systems and Rehabilitation], 8(2):198–202,2000.
[49] P.G. Patil, J.M. Carmena, M.A.L. Nicolelis, and D.A. Turner. Ensemble recordings of human sub-cortical neurons as a source of motor control signals for a brain-machine interface. Neurosurgery,55(1):27–35, 2004.
[50] E.A. Curran and M.J. Stokes. Learning to control brain activity: A review of the productionand control of EEG components for driving brain–computer interface (BCI) systems. Brain andCognition, 51(3):326–336, 2003.
[51] G.E. Fabiani, D.J. McFarland, J.R. Wolpaw, and G. Pfurtscheller. Conversion of EEG activity intocursor movement by a brain-computer interface (BCI). Neural Systems and Rehabilitation Engi-neering, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering], 12(3):331–338, 2004.
[52] C. Guger, H. Ramoser, and G. Pfurtscheller. Real-time EEG analysis with subject-specific spatialpatterns for abrain-computer interface (BCI). Rehabilitation Engineering, IEEE Transactions on[see also IEEE Trans. on Neural Systems and Rehabilitation], 8(4):447–456, 2000.
[53] G. Pfurtscheller, C. Neuper, C. Guger, W. Harkam, H. Ramoser, A. Schlogl, B. Obermaier, andM. Pregenzer. Current trends in Graz brain-computer interface (BCI) research. RehabilitationEngineering, IEEE Transactions on [see also IEEE Trans. on Neural Systems and Rehabilitation],8(2):216–219, 2000.
[54] G. Pfurtscheller, G.R. Muller-Putz, J. Pfurtscheller, and R. Rupp. EEG-Based Asynchronous BCIControls Functional Electrical Stimulation in a Tetraplegic Patient. Eurasip Journal On AppliedSignal Processing, 19:3152, 2005.
[55] G. Pfurtscheller, R. Leeb, C. Keinrath, D. Friedman, C. Neuper, C. Guger, and M. Slater. Walkingfrom thought. Brain Research, 1071(1):145–152, 2006.
[56] B. Blankertz, G. Dornhege, S. Lemm, M. Krauledat, G. Curio, and K.R. Mu¨ller. The Berlin Brain-Computer Interface: Machine learning based detection of user specific brain states. Journal ofUniversal Computer Science, 12(6):581–607, 2006.
[57] B. Blankertz, G. Dornhege, M. Krauledat, K.R. Mu¨ller, and G. Curio. The non-invasive BerlinBrain–Computer Interface: Fast acquisition of effective performance in untrained subjects. Neu-roimage, 37(2):539–550, 2007.
[58] B. Blankertz, G. Dornhege, M. Krauledat, M. Schro¨der, J. Williamson, R. Murray-Smith, and K.R.Mu¨ller. The Berlin Brain-Computer Interface presents the novel mental typewriter Hex-o-Spell.In Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course2006, pages 108–109, 2006.
[59] R. Wang, X. Gao, and S. Gao. Frequency Selection for SSVEP-based Binocular Rivalry. NeuralEngineering, 2005. Conference Proceedings. 2nd International IEEE EMBS Conference on, pages600–603, 2005.
[60] Y. Wang, Z. Zhang, X. Gao, and S. Gao. Lead selection for SSVEP-based brain-computer interface.Engineering in Medicine and Biology Society, 2004. EMBC 2004. Conference Proceedings. 26thAnnual International Conference of the, 2, 2004.
[61] Y. Wang, B. Hong, X. Gao, and S. Gao. Implementation of a Brain-Computer Interface Based onThree States of Motor Imagery. Engineering in Medicine and Biology Society, 2007. EMBS 2007.29th Annual International Conference of the IEEE, pages 5059–5062, 2007.
[62] M. Middendorf, G. McMillan, G. Calhoun, and K.S. Jones. Brain-computer interfaces based on thesteady-state visual-evokedresponse. Rehabilitation Engineering, IEEE Transactions on [see alsoIEEE Trans. on Neural Systems and Rehabilitation], 8(2):211–214, 2000.
[63] E.E. Sutter. The brain response interface: communication through visually-induced electrical brainresponses. Journal of Microcomputer Applications, 15(1):31–45, 1992.
[64] E. Donchin, D. Karis, T.R. Bashore, M.G.H. Coles, and G. Gratton. Cognitive psychophysiol-ogy and human information processing. Psychophysiology: Systems, processes, and applications,pages 244–267, 1986.
[65] L.A. FARWELL and E. DONCHIN. Talking off the top of your head: toward a mental prosthe-sis utilizing event-related brain potentials. Electroencephalography and clinical neurophysiology,70(6):510–523, 1988.
[66] N. Birbaumer, T. Elbert, A.G. Canavan, and B. Rockstroh. Slow potentials of the cerebral cortexand behavior, 1990.
[67] N. Birbaumer, A. Kubler, N. Ghanayim, T. Hinterberger, J. Perelmouter, J. Kaiser, I. Iversen, B.Kotchoubey, N. Neumann, and H. Flor. The thought translation device (TTD) for completelyparalyzedpatients. Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. onNeural Systems and Rehabilitation], 8(2):190–193, 2000.
[68] N. Birbaumer, T. Hinterberger, A. Kubler, and N. Neumann. The thought-translation device (TTD):neurobehavioral mechanisms and clinical outcome. Neural Systems and Rehabilitation Engineer-ing, IEEE Transactions on [see also IEEE Trans. on Rehabilitation Engineering], 11(2):120–123,2003.
[69] S.R. Filipovic′, M. Jahanshahi, and J.C. Rothwell. Uncoupling of contingent negative variationand alpha band event-related desynchronization in a go/no-go task. Clinical Neurophysiology,112(7):1307–1315, 2001.
[70] J. Annett. Motor imagery: Perception or action? Neuropsychologia, 33(11):1395–1417, 1995.
[71] G. Pfurtscheller and A. Aranibar. Event-related cortical desynchronization detected by power mea-surements of scalp EEG. Electroencephalogr Clin Neurophysiol, 42(6):817–26, 1977.
[72] G. Pfurtscheller and F.H. Lopes da Silva. Event-related EEG/MEG synchronization and desyn-chronization: basic principles. Clinical Neurophysiology, 110(11):1842–1857, 1999.
[73] L. Zhang. Temporal Independent Component Analysis for Separating Noisy Signals. Lecture NotesIn Computer Science, pages 1064–1069, 2004.
[74] S. Amari and A. Cichocki. Adaptive blind signal processing - neural network approaches. Pro-ceedings of the IEEE, 86(10):2026–2048, 1998.
[75] D.T. Pham. Mutual information approach to blind separation of stationary sources. InformationTheory, IEEE Transactions on, 48(7):1935–1946, 2002.
[76] S. Amari and J.F. Cardoso. Blind Source Separation-Semiparametric Statistical Approach. SignalProcessing, IEEE Transactions on, 45(11), 1997.
[77] L. Q. Zhang, S. Amari, and A. Cichocki. Geometrical structures of fir manifold and multichannelblind deconvolution. Journal of VLIS for Signal Processing Systems, (31):31–44, 2002.
[78] L. Q. Zhang, A. Cichocki, and S. Amari. Self-adaptive blind source separation based on activationfunctions adaptation. Neural Networks, IEEE Transactions on, 15(2), Mar 2004.
[79] Christopher J. James and Oliver J. Gibson. Temporally constrained ica: An application to artifactrejection in electromagnetic brain signal analysis. 50(9):1108–1116, Sep 2003.
[80] W. Lu and J. C. Rajapakse. Ica with reference. In Proc. 3rd Int.Conf. Independent ComponentAnalysis and Blind Signal Separation:ICA2001, pages 120–125, 2001.
[81] G.Pfurtscheller, Ch.Neuper, et al. Eeg-based discrimination between imagination of right and lefthand movement. Electroencephalography and clinical Neurophysiology, 103:342–651, 1997.
[82] Z.J. Koles and A.C. Soong. EEG source localization: implementing the spatio-temporal decompo-sition approach. Electroencephalogr Clin Neurophysiol, 107(5):343–52, 1998.
[83] A. Blum and P. Langley. Selection of Relevant Features and Examples in Machine Learning.Artificial Intelligence, 97(1-2):245–271, 1997.
[84] N. Kwak and C.H. Choi. Improved mutual information feature selector for neural networks insu-pervised learning. Neural Networks, 1999. IJCNN’99. International Joint Conference on, 2, 1999.
[85] Y. Li and C. Guan. A Semi-supervised SVM Learning Algorithm for Joint Feature Extraction andClassification in Brain Computer Interfaces. Engineering in Medicine and Biology Society, 2006.EMBS’06. 28th Annual International Conference of the IEEE, pages 2570–2573, 2006.
[86] R. Tomioka, J. Hill, B. Blankertz, and K. Aihara. Adapting Spatial Filtering Methods for Nonsta-tionary BCIs. transformation, 10:1.
[87] Y.N. Rao and J.C. Principe. An RLS type algorithm for generalized eigendecomposition. NeuralNetworks for Signal Processing XI, 2001. Proceedings of the 2001 IEEE Signal Processing SocietyWorkshop, pages 263–272, 2001.
[88] G.H. Golub and C.F. Van Loan. Matrix Computations. Johns Hopkins University Press, 1996.
[89] H.Ramoser, J.Mu¨ller-Gerking, and G.Pfurtscheller. Optimal spatial filtering of single trial eegduring imagined hand movement. 8(40):441–446, Dec 2000.
[90] J.Mu¨ller-Gerking, G.Pfurtscheller, and H.Flyvbjerg. Designing optimal spatial filters for single-trial eeg classification in a movement tast. Clinical Neurophysiology, 110:787–798, 1999.
[91] S. Lemm, B. Blankertz, G. Curio, and K.R. Muller. Spatio-Spectral Filters for Improving theClassification of Single Trial EEG. Biomedical Engineering, IEEE Transactions on, 52(9):1541–1548, 2005.
[92] G. Dornhege, B. Blankertz, M. Krauledat, F. Losch, G. Curio, and K.R. Muller. Optimizing spatio-temporal filters for improving brain-computer interfacing. Advances in Neural Information Pro-cessing Systems (NIPS), 5:315–322, 2006.
[93] G. Dornhege, B. Blankertz, M. Krauledat, F. Losch, G. Curio, and K.R. Mu¨ller. Combined op-timization of spatial and temporal filters for improving brain-computer interfacing. BiomedicalEngineering, IEEE Transactions on, 53(11):2274–2281, 2006.
[94] V. Bostanov and B. Kotchoubey. The t-CWT: A new ERP detection and quantification methodbased on the continuous wavelet transform and Student’s t-statistics. Clinical Neurophysiology,117(12):2627–2644, 2006.
[95] M. M?rup, L.K. Hansen, and S.M. Arnfred. ERPWAVELAB A toolbox for multi-channel anal-ysis of time–frequency transformed event related potentials. Journal of Neuroscience Methods,161(2):361–368, 2007.
[96] N. Yamawaki, C. Wilke, Z. Liu, and B. He. An enhanced time-frequency-spatial approach formotor imagery classification. Neural Systems and Rehabilitation Engineering, IEEE transactionson, 14(2):250, 2006.
[97] F.L. Hitchcock. The expression of a tensor or a polyadic as a sum of products. J. Math. Phys,6(1):164–189, 1927.
[98] R.B. Cattell.“Parallel proportional profiles”and other principles for determining the choice offactors by rotation. Psychometrika, 9(4):267–283, 1944.
[99] R.B. CATTELL. The three basic factor-analytic research designs-their interrelations and deriva-tives. Psychol Bull, 49(5):499–520, 1952.
[100] L.R. Tucker. The extension of factor analysis to three-dimensional matrices. Contributions toMathematical Psychology, pages 109–127, 1964.
[101] L.R. Tucker. Some mathematical notes on three-mode factor analysis. Psychometrika, 31(3):279–311, 1966.
[102] J.D. Carroll and J.J. Chang. Analysis of individual differences in multidimensional scaling via ann-way generalization of“Eckart-Young”decomposition. Psychometrika, 35(3):283–319, 1970.
[103] R.A. Harshman. Foundations of the PARAFAC procedure: Models and conditions for an”explana-tory”multi-modal factor analysis. UCLA Working Papers in Phonetics, 16:1–84, 1970.
[104] C.J. Appellof and E.R. Davidson. Strategies for analyzing data from video ?uorometric monitoringof liquid chromatographic ef?uents. Analytical Chemistry, 53(13):2053–2056, 1981.
[105] L. De Lathauwer and B. De Moor. From matrix to tensor: Multilinear algebra and signal processing.Mathematics in Sig. Proc., IMA Conf. Series, Warwick, Dec, pages 17–19, 1996.
[106] N.D. Sidiropoulos, R. Bro, and G.B. Giannakis. Parallel factor analysis in sensor array processing.Signal Processing, IEEE Transactions on [see also Acoustics, Speech, and Signal Processing, IEEETransactions on], 48(8):2377–2388, 2000.
[107] P. Comon. Tensor decompositions. Mathematics in Signal Processing V, pages 1–24, 2001.
[108] V.S. GRIGORASCU and P.A. REGALIA. Tensor displacement structures and polyspectral match-ing. Fast Reliable Algorithms for Matrices with Structure, 1999.
[109] T.G. Kolda. Multilinear operators for higher-order decompositions. Technical report, TechnicalReport SAND2006-2081, Sandia National Laboratories, Livermore, CA. http://csmr. ca. sandia.gov/ tgkolda/pubs/SAND2006-2081. pdf, 2006.
[110] M.A.O. Vasilescu and D. Terzopoulos. Multilinear analysis of image ensembles: Tensorfaces.Proc. European Conf. on Computer Vision (ECCV 2002), pages 447–460.
[111] E. Acar, S.A. C? amtepe, M.S. Krishnamoorthy, and B. Yener. Modeling and multiway analysisof chatroom tensors. Intelligence and Security Informatics: IEEE Intl. Conf. on Intelligence andSecurity Informatics, ISI, pages 19–20, 2005.
[112] J. Sun, S. Papadimitriou, and P.S. Yu. Window-based tensor analysis on high-dimensional andmulti-aspect streams. ICDM06: Proceedings of the 6th IEEE Conference on Data Mining, pages1076–1080.
[113] C.F. Beckmann and S.M. Smith. Tensorial extensions of independent component analysis for mul-tisubject FMRI analysis. Neuroimage, 25(1):294–311, 2005.
[114] E. Mart??nez-Montes, P.A. Valde′s-Sosa, F. Miwakeichi, R.I. Goldman, and M.S. Cohen. Concur-rent EEG/fMRI analysis by multiway Partial Least Squares. Neuroimage, 22(3):1023–1034, 2004.
[115] M. M?rup, L.K. Hansen, C.S. Herrmann, J. Parnas, and S.M. Arnfred. Parallel Factor Analysisas an exploratory tool for wavelet transformed event-related EEG. Neuroimage, 29(3):938–947,2006.
[116] D.D. Lee and H.S. Seung. Learning the parts of objects by non-negative matrix factorization.Nature, 401(6755):788–791, 1999.
[117] D.D. Lee and H.S. Seung. Algorithms for non-negative matrix factorization. Advances in NeuralInformation Processing Systems, 13:556–562, 2001.
[118] B.A. Olshausen et al. Emergence of simple-cell receptive field properties by learning a sparse codefor natural images. Nature, 381(6583):607–609, 1996.
[119] GF Harpur. Low entropy coding with unsupervised neural networks. Unpublished doctoral disser-tation, Cambridge University, 1997.
[120] P.O. Hoyer. Non-negative Matrix Factorization with Sparseness Constraints. The Journal of Ma-chine Learning Research, 5:1457–1469, 2004.
[121] T. Gruber, P. Malinowski, and M.M. Muller. Modulation of oscillatory brain activity and evokedpotentials in a repetition priming task in the human EEG. European Journal of Neuroscience,19(4):1073–1082, 2004.
[122] C.S. Herrmann, M. Grigutsch, and N.A. Busch. EEG oscillations and wavelet analysis. Event-Related Potentials-A Methods Handbook, pages 229–259, 2005.
[123] C.S. Herrmann, M.H.J. Munk, and A.K. Engel. Cognitive functions of gamma-band activity: mem-ory match and utilization. Trends in Cognitive Sciences, 8(8):347–355, 2004.
[124] J.P. Lachaux, N. George, C. Tallon-Baudry, J. Martinerie, L. Hugueville, L. Minotti, P. Kahane, andB. Renault. The many faces of the gamma band response to complex visual stimuli. Neuroimage,25(2):491–501, 2005.
[125] M.D. Serruya, N.G. Hatsopoulos, L. Paninski, M.R. Fellows, and J.P. Donoghue. Instant neuralcontrol of a movement signal. Nature, 416(6877):141–2, 2002.
[126] S. Musallam, B.D. Corneil, B. Greger, H. Scherberger, and R.A. Andersen. Cognitive ControlSignals for Neural Prosthetics. Science, 305(5681):258–262, 2004.
[127] J.M. Carmena, M.A. Lebedev, R.E. Crist, J.E. O’Doherty, D.M. Santucci, D.F. Dimitrov, P.G. Patil,C.S. Henriquez, and M.A.L. Nicolelis. Learning to control a brain-machine interface for reachingand grasping by primates. PLoS Biology, 1(2):e2, 2003.
[128] G. Santhanam, S.I. Ryu, B.M. Yu, A. Afshar, and K.V. Shenoy. A high-performance brain-computer interface. Nature, 442(7099):195–198, 2006.
[129] G. Pfurtscheller, C. Neuper, G.R. Muller, B. Obermaier, G. Krausz, A. Schlogl, R. Scherer, B.Graimann, C. Keinrath, D. Skliris, et al. Graz-BCI: state of the art and clinical applications. NeuralSystems and Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. on Rehabil-itation Engineering], 11(2):1–4, 2003.
[130] E.E. Fetz. Real-time control of a robotic arm by neuronal ensembles. Nature Neuroscience, 2:583–584, 1999.
[131] J.P. Donoghue. Connecting cortex to machines: recent advances in brain interfaces. Nature Neu-roscience, 5(supp):1085–1088, 2002.
[132] A. Cichocki and S. Amari. Adaptive blind signal and image processing, volume 1. Wiley, May2002.
[133] A. Alkan and M.K. Kiymik. Comparison of AR and Welch Methods in Epileptic Seizure Detection.Journal of Medical Systems, 30(6):413–419, 2006.
[134] M. Pregenzer and G. Pfurtscheller. Frequency component selection for an EEG-based brain tocomputerinterface. Rehabilitation Engineering, IEEE Transactions on [see also IEEE Trans. onNeural Systems and Rehabilitation], 7(4):413–419, 1999.
[135] C.C. Chang and C.J. Lin. LIBSVM: a library for support vector machines. Software available athttp://www. csie. ntu. edu. tw/cjlin/libsvm, 80:604–611, 2001.