Review of the BCI Competition IV

Michael Tangermann, Klaus-Robert Müller, Ad Aertsen, Niels Birbaumer, Christoph Braun, Clemens Brunner, Robert Leeb, Carsten Mehring, Kai J Miller, Gernot R Müller-Putz, Guido Nolte, Gert Pfurtscheller, Hubert Preissl, Gerwin Schalk, Alois Schlögl, Carmen Vidaurre, Stephan Waldert, Benjamin Blankertz, Michael Tangermann, Klaus-Robert Müller, Ad Aertsen, Niels Birbaumer, Christoph Braun, Clemens Brunner, Robert Leeb, Carsten Mehring, Kai J Miller, Gernot R Müller-Putz, Guido Nolte, Gert Pfurtscheller, Hubert Preissl, Gerwin Schalk, Alois Schlögl, Carmen Vidaurre, Stephan Waldert, Benjamin Blankertz

Abstract

The BCI competition IV stands in the tradition of prior BCI competitions that aim to provide high quality neuroscientific data for open access to the scientific community. As experienced already in prior competitions not only scientists from the narrow field of BCI compete, but scholars with a broad variety of backgrounds and nationalities. They include high specialists as well as students. The goals of all BCI competitions have always been to challenge with respect to novel paradigms and complex data. We report on the following challenges: (1) asynchronous data, (2) synthetic, (3) multi-class continuous data, (4) session-to-session transfer, (5) directionally modulated MEG, (6) finger movements recorded by ECoG. As after past competitions, our hope is that winning entries may enhance the analysis methods of future BCIs.

Keywords: BCI; brain-computer interface; competition.

Figures

Figure 1
Figure 1
Citations of the overview articles on previous competitions. The histogram shows how many times the editorial articles on BCI competitions I (Sajda et al., 2003), II (Blankertz et al., 2004), and III (Blankertz et al., 2006) have been cited in ISI-indexed journals. Data were retrieved from the ISI Web of Knowledge on December 1st 2011.
Figure 2
Figure 2
Citations of the articles by the competition winners. The histogram shows how many times the articles of the winning teams of BCI competition II (describing the winning algorithms) have been cited in ISI-indexed journals. Data were retrieved from the ISI Web of Knowledge on December 1st 2011.
Figure 3
Figure 3
(Data set 1 – trial structure). Training data was collected in the calibration runs. Arrows pointing left, right, or down have been presented as cues for imagining left hand, right hand, or foot movements. After a fixation cross was presented for 2 s, the directional cue was overlaid for 4 s. Then the screen was blank for 2 s. In the test runs used for evaluation, spoken words have been presented as cues.
Figure 4
Figure 4
(Data set 1 – glance at the neurophysiology). The first row displays the averaged spectra of the two chosen motor imagery tasks (red: left hand, green: right hand; blue: foot) in the training data. A selected subject-specific frequency band is shaded in gray. The second row shows the average amplitude envelope of that frequency band with 0 being the time point of cue presentation. The time interval which was used to calculate the spectra shown above is shaded. The bottommost row displays the (signed) r2-difference in log band-power between the individually chosen motor imagery tasks as scalp maps. Band-power was calculated in the frequency band that is shown in the topmost row and averaged across the time interval that is indicated in the middle row. Three of those seven data sets have been artificially generated, see main text.
Figure 5
Figure 5
(Data set 1 – histogram of results). Performance of the first five ranked submissions is shown in terms of their mean squared error (MSE) wrt. the true labels. Only results for the real (i.e., not artificially generated) data sets are shown. The mean across the four data sets is plotted as a horizontal red line. The MSE for constant prediction output of 0 are 0.507, 0.515, 0.491, 0.524 for data sets a, b, f, g, respectively.
Figure 6
Figure 6
(Data set 1 – distribution of classifier outputs). These (normalized) histograms display the distribution of the classifier outputs of the winning algorithm. Each row corresponds to one data set (a, b, f, g). The left column is a histogram for those time points in which the true label is −1, for the middle column it is 0 (no control), and for the right column it is 1. The true label is indicated by the blue triangle.
Figure 7
Figure 7
(Data set 1 – trace of classifier outputs). The labels of the true mental state are displayed in blue. The red line shows the classifier outputs of the winning algorithm. This example is a selected segment of 100 s taken from data set g in which the classification is quite successful. The MSE in the shown segment is 0.171.
Figure 8
Figure 8
(Data Set 1 – artificial). Left: spectra of the signal at all channel locations for the two conditions, eyes open and eyes closed. Right: scalp plot of the signal power at 10 Hz for the two conditions (eyes open and closed). The actual noise of the artificial data varied linearly in time between both conditions, depending of the task of the BCI user.
Figure 9
Figure 9
(Data Set 1 – artificial). Example of fast and slow baseline drifts that are observable in unfiltered BCI competition IV data. The figure depicts the time course of the amplitude of the EEG in one channel.
Figure 10
Figure 10
(Data Set 1 – artificial). Location and direction of selected dipoles in the head.
Figure 11
Figure 11
(Data Set 1 – artificial). Power topographies at the μ rhythm frequency generated by the dipoles.
Figure 12
Figure 12
(Data Set 1 – artificial). Spectra of the EEG signal in two discriminative channels. The discriminability between the classes is shown at the bottom of each spectrum. This Figure illustrates an example of asymmetry of the μ rhythm peak in each hemisphere. Also the harmonic of the μ rhythm is observable in the beta band.
Figure 13
Figure 13
(Data Set 1 – artificial). Top row: scalp plots of one eye movement and one eye blink generated for the synthetic EEG data sets of the BCI competition IV. Bottom row: corresponding time course of eye movements and blinks.
Figure 14
Figure 14
(Data Set 1 – artificial). Linear regression of the rank position (left) and performance of the method (right). The x-axis corresponds to the results submitted for the real EEG data sets, whereas y-axis corresponds to those of the synthetic EEG.
Figure 15
Figure 15
(Data Set 2a). Timing scheme of one session.
Figure 16
Figure 16
(Data Set 2a). Timing scheme of the paradigm.
Figure 17
Figure 17
(Data Set 2a). Left: electrode montage corresponding to the international 10–20 system. Right: electrode montage of the three monopolar EOG channels.
Figure 18
Figure 18
(Data Set 2b). Timing scheme of one session (for screening and feedback sessions).
Figure 19
Figure 19
(Data Set 2b). Electrode montage of the three monopolar EOG channels.
Figure 20
Figure 20
(Data Set 2b). Timing scheme of the paradigm. (A) The first two sessions (01T, 02T) contain training data without feedback, and (B) the last three sessions (03T, 04E, 05E) with smiley feedback.
Figure 21
Figure 21
(Data Set 3). Schematic overview of different recording techniques for BMIs (from Waldert et al., with permission).
Figure 22
Figure 22
(Data Set 3). Time course of a trial with time constraints (from Waldert et al., with permission).
Figure 23
Figure 23
(Data Set 3). Results of the BCI competition IV and, for comparison, the average result of applying a RLDA and linear SVM to the low-pass filtered and resampled activity of the data.
Figure 24
Figure 24
(Data Set 4). The ECoG signals in train_data (time, channel) and test_data (time, channel) were acquired from each electrode with respect to a scalp reference and ground before re-referencing with respect to the common average.
Figure 25
Figure 25
(Data Set 4 – event-related potential). Illustration that the characteristic changes in the power spectral density changes with activity are not due to an reproducible event-related potential shift (ERP). Two adjacent electrodes are shown in (A). One has an ERP, and one does not, but both have the characteristic peri-movement spectral changes. (B) Individual (gray) and averaged thumb movement (black, left) or index finger movement (black, right), locked to the first movement from the appropriate movement cue. (C) The normalized power spectral density (“PSD”) as a function of time. It demonstrates the classic spectral changes just prior to movement onset for both thumb and index finger. Note that the decrease in power at lower frequencies (α/β/μ range), and the increase in power at higher frequencies (above about 40 Hz) both begin before movement onset. (D) Individual and averaged raw potential traces around each of the first movements from appropriate thumb or index finger movement epochs. There is no significant event-related potential (ERP) effect for thumb, but there is for the index finger.
Figure 26
Figure 26
(Data Set 4). Time courses of finger flexion, broadband, LMP, and the raw electric potential. The LMP (Schalk et al., ; Kubanek et al., 2009) has been shown to hold information about different motor behaviors. Spectrally broadband change, corresponding to 1/f type change in the electric potential power spectrum (Miller et al., 2009a,b), can be captured as another powerful correlate of motor behavior. By synthesizing different features, more powerful brain-computer interfacing algorithms may be obtained.
Figure 27
Figure 27
(Data Set 4). Examples of the normalized power spectral density (PSD) of the potential time series around finger flexion. The PSD was calculated from 1 s windows centered at times of maximum flexion and also during rest. (A) Mean PSD of index finger movement samples (light trace) and rest samples (black trace). (B) Average time-varying PSD (scaled as percentage of mean power at each frequency) with respect to first index finger movement from each movement cue.
Figure 28
Figure 28
(Data Set 4). Cortical activation maps for movement of different fingers in one subject. The changes in power between 126 and 150 Hz are focused in the classic hand area of the brain. The spatial distribution for 76–100 Hz are nearly identical, as might be expected since both are reflections of the broadband feature highlighted in recent literature (Miller et al., 2009b). Low frequency changes are spatially much more broad, corresponding to fluctuations in the classic motor rhythms. Figure 29 shows that the spatial representations for high frequencies are very different for different finger movement types, within a general hand region. Electrode positions are shown with white dots, and power change with light and dark gray patches on the brain surface.
Figure 29
Figure 29
(Data Set 4). A blow-up of the sensorimotor region for high frequencies from Figure 28. Note that this variability across electrodes allows for robust segregation of different finger movements during classification.
Figure 30
Figure 30
(Data Set 4). Time course of ECoG in adjacent electrodes reveals individual digit representation. (A) X-ray of the ECoG array in situ, with three electrodes labeled, corresponding to the numbers in (C). (B) Flexion time course of each finger. (C) Projections of the time-frequency representation to broadband spectral change (Miller et al., 2009b). Each electrode is specifically and strongly correlated with one movement type (r = 0.46 for broadband from electrode 1 with thumb position; r = 0.47 for electrode 2 with index finger; r = 0.29 for electrode 3 with little finger; cross-combinations had a mean correlation of −0.09, indicating light hyperextension of other fingers while flexing the appropriate finger in this subject), over 10 min of continuous data (3.6 × 106 samples).

References

    1. Abrahamsen T. J., Hansen L. K. (2011). A cure for variance inflation in high dimensional kernel principal component analysis. J. Mach. Learn. Res. 12, 2027–2044
    1. Acqualagna L., Blankertz B. (2011). A gaze independent speller based on rapid serial visual presentation. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2011, 4560–4563
    1. Aloise F., Lasorsa I., Schettini F., Brouwer A., Mattila D., Babiloni F., Salinari S., Marciani M., Cincotti F. (2007). Multimodal stimulation for a P300-based BCI. Int. J. Bioelectromagn. 9, 128–130
    1. Anderson K. (2004). Targeting recovery: priorities of the spinal cord-injured population. J. Neurotrauma 21, 11371–1138310.1089/neu.2004.21.1831
    1. Ang K., Chin Z. Y., Zhang H., Guan C. (2008). “Filter bank common spatial pattern (FBCSP) in brain-computer interface,” in Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN’08), Hong Kong, 2391–2398
    1. Ang K., Quek C. (2006). “Rough set-based neuro-fuzzy system,” in Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN’06), Vancouver, 742–749
    1. Ang K. K., Chin Z. Y., Wang C., Guan C., Zhang H. (2012). Filter bank common spatial pattern algorithm on BCI competition iv datasets 2a and 2b. Front. Neurosci. 6:39.10.3389/fnins.2012.00039
    1. Ball T., Schulze-Bonhage A., Aertsen A., Mehring C. (2009). Differential representation of arm movement direction in relation to cortical anatomy and function. J. Neural Eng. 6, 016006.10.1088/1741-2560/6/1/016006
    1. Bießmann F., Meinecke F. C., Gretton A., Rauch A., Rainer G., Logothetis N., Müller K.-R. (2009). Temporal kernel canonical correlation analysis and its application in multimodal neuronal data analysis. Mach. Learn. 79, 5–2710.1007/s10994-009-5153-3
    1. Biessmann F., Plis S., Meinecke F. C., Eichele T., Müller K.-R. (2011). Analysis of multimodal neuroimaging data. IEEE Rev. Biomed. Eng. 4, 26–5810.1109/RBME.2011.2170675
    1. Bijma F., de Munck J., Huizenga H., Heethaar R. (2003). A mathematical approach to the temporal stationarity of background noise in MEG/EEG measurements. Neuroimage 20, 233–24310.1016/S1053-8119(03)00215-5
    1. Blanchard G., Blankertz B. (2004). BCI competition 2003 – data set IIa: spatial patterns of self-controlled brain rhythm modulations. IEEE Trans. Biomed. Eng. 51, 1062–106610.1109/TBME.2004.826691
    1. Blankertz B., Dornhege G., Schäfer C., Krepki R., Kohlmorgen J., Müller K. -R., Kunzmann V., Losch F., Curio G. (2003). Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis. IEEE Trans. Neural Syst. Rehabil. Eng. 11, 127–13110.1109/TNSRE.2003.814456
    1. Blankertz B., Kawanabe M., Tomioka R., Hohlefeld F., Nikulin V., Müller K.-R. (2008a). “Invariant common spatial patterns: alleviating nonstationarities in brain-computer interfacing,” in Advances in Neural Information Processing Systems 20, eds Platt J., Koller D., Singer Y., Roweis S. (Cambridge, MA: MIT Press; ), 113–120
    1. Blankertz B., Tomioka R., Lemm S., Kawanabe M., Müller K.-R. (2008b). Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process. Mag. 25, 41–5610.1109/MSP.2008.4408441
    1. Blankertz B., Lemm S., Treder M. S., Haufe S., Müller K.-R. (2011). Single-trial analysis and classification of ERP components – a tutorial. Neuroimage 56, 814–82510.1016/j.neuroimage.2010.06.048
    1. Blankertz B., Müller K.-R., Curio G., Vaughan T. M., Schalk G., Wolpaw J. R., Schlögl A., Neuper C., Pfurtscheller G., Hinterberger T., Schröder M., Birbaumer N. (2004). The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans. Biomed. Eng. 51, 1044–105110.1109/TBME.2004.826692
    1. Blankertz B., Müller K.-R., Krusienski D., Schalk G., Wolpaw J. R., Schlögl A., Pfurtscheller G., Millán Jdel R., Schröder M., Birbaumer N. (2006). The BCI competition III: validating alternative approachs to actual BCI problems. IEEE Trans. Neural Syst. Rehabil. Eng. 14, 153–15910.1109/TNSRE.2006.875642
    1. Blankertz B., Tangermann M., Vidaurre C., Fazli S., Sannelli C., Haufe S., Maeder C., Ramsey L. E., Sturm I., Curio G., Müller K.-R. (2010). The Berlin brain-computer interface: non-medical uses of BCI technology. Front. Neurosci. 4:198.10.3389/fnins.2010.00198
    1. Blankertz B., Vidaurre C. (2009). Towards a cure for BCI illiteracy: machine-learning based co-adaptive learning. BMC Neurosci. 10(Suppl. 1), P85.10.1186/1471-2202-10-S1-P85
    1. Bostanov V. (2004). BCI competition 2003 – data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram. IEEE Trans. Biomed. Eng. 51, 1057–106110.1109/TBME.2004.826702
    1. Bradberry T., Gentili R., Contreras-Vidal J. (2010). Reconstructing three-dimensional hand movements from noninvasive electroencephalographic signals. J. Neurosci. 30, 3432–343710.1523/JNEUROSCI.6107-09.2010
    1. Bradberry T., Rong F., Contreras-Vidal J. (2009). Decoding center-out hand velocity from MEG signals during visuomotor adaptation. Neuroimage 47, 1691–170010.1016/j.neuroimage.2009.06.023
    1. Brunner C., Billinger M., Vidaurre C., Neuper C. (2011). A comparison of univariate, vector, bilinear autoregressive, and band power features for brain-computer interfaces. Med. Biol. Eng. Comput. 49, 1337–134610.1007/s11517-011-0828-x
    1. Brunner C., Naeem M., Leeb R., Graimann B., Pfurtscheller G. (2007). Spatial filtering and selection of optimized components in four class motor imagery EEG data using independent components analysis. Pattern Recognit. Lett. 28, 957–96410.1016/j.patrec.2007.01.002
    1. Buch E., Weber C., Cohen L., Braun C., Dimyan M., Ard T., Mellinger J., Caria A., Soekadar S., Fourkas A., Birbaumer N. (2008). Think to move: a neuromagnetic brain-computer interface (BCI) system for chronik stroke. Stroke 39, 910–91710.1161/STROKEAHA.107.505313
    1. Carlqvist H., Nikulin V., Strömberg J., Brismar T. (2004). Amplitude and phase relationship between alpha and beta oscillations in the human electroencephalogram. J. Med. Biol. Eng. Comput. 43, 599–60710.1007/BF02351033
    1. Crone N. E., Miglioretti D. L., Gordon B., Lesser R. P. (1998a). Functional mapping of human sensorimotor cortex with electrocorticographic spectral analysis. II. Event-related synchronization in the gamma band. Brain 121(Pt 12), 2301–231510.1093/brain/121.12.2301
    1. Crone N., Miglioretti D., Gordon B., Sieracki J., Wilson M., Uematsu S., Lesser R. (1998b). Functional mapping of human sensorimotor cortex with electrocorticographic spectral analysis. I. Alpha and beta event-related desynchronization. Brain 121, 2271.10.1093/brain/121.12.2301
    1. Dähne S., Höhne J., Tangermann M. (2011). “Adaptive classification improves control performance in ERP-based BCIs,” in Proceedings of the 5th International BCI Conference, Graz, 92–95
    1. Millán J. D., Rupp R., Müller-Putz G., Murray-Smith R., Giugliemma C., Tangermann M., Vidaurre C., Cincotti F., Kübler A., Leeb R., Neuper C., Müller K.-R., Mattia D. (2010). Combining brain-computer interfaces and assistive technologies: state-of-the-art and challenges. Front. Neurosci. 4:161.10.3389/fnins.2010.00161
    1. Dornhege G., Blankertz B., Curio G., Müller K.-R. (2004). Boosting bit rates in non-invasive EEG single-trial classifications by feature combination and multi-class paradigms. IEEE Trans. Biomed. Eng. 51, 993–100210.1109/TBME.2004.827088
    1. Fatourechi M., Bashashati A., Ward R. K., Birch G. E. (2007). EMG and EOG artifacts in brain computer interface systems: a survey. Clin. Neurophysiol. 118, 480–49410.1016/j.clinph.2006.10.019
    1. Fazli S., Mehnert J., Steinbrink J., Curio G., Villringer A., Müller K. R., Blankertz B. (2012). Enhanced performance by a hybrid NIRS-EEG brain computer interface. Neuroimage 59, 519–52910.1016/j.neuroimage.2011.07.084
    1. Flamary R., Rakotomamonjy A. (2012). Decoding finger movements from ECoG signals using switching linear models. Front. Neurosci. 6:29.10.3389/fnins.2012.00029
    1. Freeman W. (2004a). Origin, structure, and role of background EEG activity. Part 1. Analytic amplitude. Clin. Neurophysiol. 115, 2077–208910.1016/j.clinph.2004.02.028
    1. Freeman W. (2004b). Origin, structure, and role of background EEG activity. Part 2. Analytic phase. Clin. Neurophysiol. 115, 2089–210710.1016/j.clinph.2004.02.028
    1. Freeman W. (2005). Origin, structure, and role of background EEG activity. Part 3. Neural frame classification. Clin. Neurophysiol. 116, 1118–112910.1016/j.clinph.2004.12.023
    1. Freeman W. (2006). Origin, structure, and role of background EEG activity. Part 4. Neural frame simulation. Clin. Neurophysiol. 117, 572–58910.1016/j.clinph.2005.10.025
    1. Galan F., Oliva F., Guardia J. (2007). Using mental tasks transitions detection to improve spontaneous mental activity classification. Med. Biol. Eng. Comput. 45, 603–60910.1007/s11517-007-0197-7
    1. Gargiulo G., Calvo R. A., Bifulco P., Cesarelli M., Jin C., Mohamed A., van Schaik A. (2010). A new EEG recording system for passive dry electrodes. Clin. Neurophysiol. 121, 686–69310.1016/j.clinph.2009.12.025
    1. Georgopoulos A., Langheim F., Leuthold A., Merkle A. (2005). Magnetoencephalographic signals predict movement trajectory in space. Exp. Brain Res. 167, 132–13510.1007/s00221-005-0028-8
    1. Georgopoulos A. P., Kalaska J. F., Caminiti R., Massey J. T. (1982). On the relations between the direction of two-dimensional arm movements and cell discharge in primate motor cortex. J. Neurosci. 2, 1527–1537
    1. Geselowitz D. (1967). On bioelectric potentials in an inhomogeneous volume conductor. Biophys. J. 7, 1–1110.2142/biophys.7.1
    1. Hammon P., Makeig S., Poizner H., Todorov E., de Sa V. (2008). Predicting reaching targets from human EEG. IEEE Signal Process. Mag. 25, 69–7710.1109/MSP.2008.4408443
    1. Haufe S., Treder M. S., Gugler M. F., Sagebaum M., Curio G., Blankertz B. (2011). EEG potentials predict upcoming emergency brakings during simulated driving. J. Neural Eng. 8, 056001.10.1088/1741-2560/8/5/056001
    1. Henninghausen E., Heil M., Rösler F. (1993). A correction method for dc drift artifacts. Electroencephalogr. Clin. Neurophysiol. 86, 199–20410.1016/0013-4694(93)90008-J
    1. Hochberg L., Serruya M., Friehs G., Mukand J., Saleh M., Caplan A., Branner A., Chen D., Penn R., Donoghue J. (2006). Neuronal ensemble control of prosthetic devices by a human with tetraplegia. Nature 442, 164–17110.1038/nature04970
    1. Höhne J., Schreuder M., Blankertz B., Tangermann M. (2011). A novel 9-class auditory ERP paradigm driving a predictive text entry system. Front. Neurosci. 5:99.10.3389/fnins.2011.00099
    1. Huber P., Kleiner B., Gasser T., Dumermuth G. (1971). Statistical methods for investigating phase relations in stationary stochastic processes. IEEE Trans. Acoust. 19, 78–86
    1. Huizenga H., de Munck J., Waldorp L., Grasman R. P. (2002). Spatiotemporal EEG/MEG source analysis based on a parametric noise covariance model. IEEE Trans. Biomed. Eng. 49, 533–53910.1109/TBME.2002.1001967
    1. Jerbi K., Lachaux J., N’Diaye K., Pantazis D., Leahy R., Garnero L., Baillet S. (2007). Coherent neural representation of hand speed in humans revealed by MEG imaging. Proc. Natl. Acad. Sci. U.S.A. 104, 7676–768110.1073/pnas.0609632104
    1. Kaper M., Meinicke P., Grossekathoefer U., Lingner T., Ritter H. (2004). BCI competition 2003 – data set IIb: support vector machines for the P300 speller paradigm. IEEE Trans. Biomed. Eng. 51, 1073–107610.1109/TBME.2004.826698
    1. Koles Z. J. (1991). The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. Electroencephalogr. Clin. Neurophysiol. 79, 440–44710.1016/0013-4694(91)90163-X
    1. Krauledat M., Shenoy P., Blankertz B., Rao R. P. N., Müller K.-R. (2007). “Adaptation in CSP-based BCI systems,” in Toward Brain-Computer Interfacing, eds Dornhege G., Millán Jdel R., Hinterberger T., McFarland D., Müller K.-R. (Cambridge, MA: MIT Press; ), 305–309
    1. Kubanek J., Miller K., Ojemann J., Wolpaw J., Schalk G. (2009). Decoding flexion of individual fingers using electrocorticographic signals in humans. J. Neural Eng. 6, 066001.10.1088/1741-2560/6/6/066001
    1. Kübler A., Kotchoubey B., Kaiser J., Wolpaw J., Birbaumer N. (2001). Brain-computer communication: unlocking the locked in. Psychol. Bull. 127, 358–37510.1037/0033-2909.127.3.358
    1. Leeb R., Lee F., Keinrath C., Scherer R., Bischof H., Pfurtscheller G. (2007). Brain-computer communication: motivation, aim and impact of exploring a virtual apartment. IEEE Trans. Neural Syst. Rehabil. Eng. 15, 473–48210.1109/TNSRE.2007.906956
    1. Lemm S., Blankertz B., Dickhaus T., Müller K.-R. (2011). Introduction to machine learning for brain imaging. Neuroimage 56, 387–39910.1016/j.neuroimage.2010.11.004
    1. Lemm S., Schafer C., Curio G. (2004). BCI competition 2003 – data set III: probabilistic modeling of sensorimotor mu rhythms for classification of imaginary hand movements. IEEE Trans. Biomed. Eng. 51, 1077–108010.1109/TBME.2004.827076
    1. Leuthardt E., Schalk G., Wolpaw J., Ojemann J., Moran D. (2004). A brain-computer interface using electrocorticographic signals in humans. J. Neural Eng. 1, 63–7110.1088/1741-2560/1/2/001
    1. Liang N., Bougrain L. (2012). Decoding finger flexion from band-specific ECoG signals in humans. Front. Neurosci. 6:29.10.3389/fnins.2012.00029
    1. Liu T., Goldberg L., Gao S., Hong B. (2010). An online brain-computer interface using non-flashing visual evoked potentials. J. Neural Eng. 7, 036003.10.1088/1741-2560/7/3/036003
    1. Lotte F., Guan C. (2011). Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Trans. Biomed. Eng. 58, 355–36210.1109/TBME.2010.2082539
    1. Luo A., Sullivan T. J. (2010). A user-friendly SSVEP-based brain-computer interface using a time-domain classifier. J. Neural Eng. 7, 26010.10.1088/1741-2560/7/2/026010
    1. Lv J., Li Y., Gu Z. (2010). Decoding hand movement velocity from electrocorticogram signals during a drawing task. Biomed. Eng. Online 9, 1–2110.1186/1475-925X-9-1
    1. Mazaheri A., Jensen O. (2008). Asymmetric amplitude modulations of brain oscillations generate slow evoked responses. J. Neurosci. 28, 7781–778710.1523/JNEUROSCI.1631-08.2008
    1. McFarland D., Miner L. A., Vaughan T. M., Wolpaw J. (2000). Mu and beta rhythm topographies during motor imagery and actual movements. Brain Topogr. 12, 177–18610.1023/A:1023437823106
    1. Mehring C., Rickert J., Vaadia E., Cardoso de Oliveira S., Aertsen A., Rotter S. (2003). Inference of hand movements from local field potentials in monkey motor cortex. Nat. Neurosci. 6, 1253–125410.1038/nn1158
    1. Mensh B. D., Werfel J., Seung H. S. (2004). BCI competition 2003 – data set Ia: combining gamma-band power with slow cortical potentials to improve single-trial classification of electroencephalographic signals. IEEE Trans. Biomed. Eng. 51, 1052–105610.1109/TBME.2004.827081
    1. Milekovic T., Fischer J., Pistohl T., Ruescher J., Schulze-Bonhage A., Aertsen A., Rickert J., Ball T., Mehring C. (2012). An online brain-machine interface using decoding of movement direction from the human electrocorticogram. J. Neural Eng. 9, 046003.10.1088/1741-2560/9/4/046003
    1. Miller K., Leuthardt E., Schalk G., Rao R., Anderson N., Moran D., Miller J., Ojemann J. (2007). Spectral changes in cortical surface potentials during motor movement. J. Neurosci. 27, 2424.10.1523/JNEUROSCI.3886-06.2007
    1. Miller K., Schalk G., Fetz E., den Nijs M., Ojemann J., Rao R. (2010). Cortical activity during motor execution, motor imagery, and imagery-based online feedback. Proc. Natl. Acad. Sci. U.S.A. 107, 4430.10.1073/pnas.0912149107
    1. Miller K., Sorensen L., Ojemann J., Den Nijs M. (2009a). Power-law scaling in the brain surface electric potential. PLoS Comput. Biol. 5, e1000609.10.1371/journal.pcbi.1000609
    1. Miller K., Zanos S., Fetz E., den Nijs M., Ojemann J. (2009b). Decoupling the cortical power spectrum reveals real-time representation of individual finger movements in humans. J. Neurosci. 29, 3132–313710.1523/JNEUROSCI.5506-08.2009
    1. Müller K.-R., Tangermann M., Dornhege G., Krauledat M., Curio G., Blankertz B. (2008). Machine learning for real-time single-trial EEG-analysis: from brain-computer interfacing to mental state monitoring. J. Neurosci. Methods 167, 82–9010.1016/j.jneumeth.2007.09.022
    1. Müller-Putz G. R., Breitwieser C., Tangermann M., Schreuder M., Tavella M., Leeb R., Cincotti F., Leotta F., Neuper C. (2011). Tobi hybrid BCI: principle of a new assistive method. Int. J. Bioelectromagn. 13, 144–145
    1. Naeem M., Brunner C., Leeb R., Graimann B., Pfurtscheller G. (2006). Seperability of four-class motor imagery data using independent components analysis. J. Neural Eng. 3, 208–21610.1088/1741-2560/3/3/003
    1. Nikulin V. V., Linkenkaer-Hansen K., Nolte G., Curio G. (2010). Non-zero mean and asymmetry of neuronal oscillations have different implications for evoked responses. Clin. Neurophysiol. 121, 186–19310.1016/j.clinph.2010.02.012
    1. Nikulin V. V., Linkenkaer-Hansen K., Nolte G., Lemm S., Müller K.-R., Ilmoniemi R. J., Curio G. (2007). A novel mechanism for evoked responses in human brain. Eur. J. Neurosci. 25, 3146–315410.1111/j.1460-9568.2007.05553.x
    1. Nikulin V. V., Nolte G., Curio G. (2011). A novel method for reliable and fast extraction of neuronal EEG/MEG oscillations on the basis of spatio-spectral decomposition. Neuroimage 55, 1528–153510.1016/j.neuroimage.2011.01.057
    1. Nolte G., Dassios G. (2005). Analytic expansion of the EEG lead field for realistic volume conductors. Phys. Med. Biol. 50, 3807–382310.1088/0031-9155/50/16/010
    1. Pfurtscheller G. (1981). Central beta rhythm during sensorimotor activities in man. Electroencephalogr. Clin. Neurophysiol. 51, 253–26410.1016/0013-4694(81)90139-5
    1. Pfurtscheller G., Allison B. Z., Bauernfeind G., Brunner C., Escalante T. S., Scherer R., Zander T. O., Mueller-Putz G., Neuper C., Birbaumer N. (2010). The hybrid BCI. Front. Neurosci. 4:30.10.3389/fnpro.2010.00003
    1. Pfurtscheller G., da Silva F. H. L. (1999). Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin. Neurophysiol. 110, 1842–185710.1016/S1388-2457(99)00141-8
    1. Pfurtscheller G., Lopes da Silva F. (1999). “Functional meaning of event-related desynchronization (ERD) and synchronization (ERS),” in Event-Related Desynchronization. Handbook of Electroencephalography and Clinical Neurophysiology, Vol. 6, eds Pfurtscheller G., Lopes da Silva F. (Amsterdam: Elsevier; ), 51–66
    1. Pfurtscheller G., Stancak A., Jr., Neuper C. (1996). Event-related synchronization (ERS) in the alpha band–an electrophysiological correlate of cortical idling: a review. Int. J. Psychophysiol. 24, 39–4610.1016/S0167-8760(96)00066-9
    1. Pistohl T., Ball T., Schulze-Bonhage A., Aertsen A., Mehring C. (2008). Prediction of arm movement trajectories from ECoG-recordings in humans. J. Neurosci. Methods 167, 105–11410.1016/j.jneumeth.2007.10.001
    1. Popescu F., Fazli S., Badower Y., Blankertz B., Müller K.-R. (2007). Single trial classification of motor imagination using 6 dry EEG electrodes. PLoS ONE 2, e637.10.1371/journal.pone.0000637
    1. Porbadnigk A. K., Antons J.-N., Blankertz B., Treder M. S., Schleicher R., Möller S., Curio G. (2010). Using ERPs for assessing the (sub)conscious perception of noise. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2010, 2690–2693
    1. Porbadnigk A. K., Scholler S., Blankertz B., Ritz A., Born M., Scholl R., Müller K.-R., Curio G., Treder M. S. (2011). Revealing the neural response to imperceptible peripheral flicker with machine learning. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2011, 3692–3695
    1. Quek M., Boland D., Williamson J., Murray-Smith R., Tavella M., Perdikis S., Schreuder M., Tangermann M. (2011). “Simulating the feel of brain-computer interfaces for design, development and social interaction,” in Proceedings of the 2011 Annual Conference on Human Factors in Computing Systems, CHI ’11, New York, NY: ACM, 25–28
    1. Rakotomamonjy A., Guigue V. (2008). BCI competition III: dataset II- ensemble of SVMs for BCI P300 speller. IEEE Trans. Biomed. Eng. 55, 1147–115410.1109/TBME.2008.915728
    1. Ramoser H., Müller-Gerking J., Pfurtscheller G. (2000). Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehabil. Eng. 8, 441–44610.1109/86.895946
    1. Ramsey L., Tangermann M., Haufe S., Blankertz B. (2009). Practicing fast-decision BCI using a “goalkeeper” paradigm. BMC Neurosci. 10(Suppl. 1), P69.10.1186/1471-2202-10-S1-P69
    1. Rickert J., Cardoso de Oliveira S., Vaadia E., Aertsen A., Rotter S., Mehring C. (2005). Encoding of movement direction in different frequency ranges of motor cortical local field potentials. J. Neurosci. 25, 8815–882410.1523/JNEUROSCI.0816-05.2005
    1. Saab J., Battes B., Grosse-Wentrup M. (2011). Simultaneous EEG Recordings with Dry and Wet elecTrodes in Motor-Imagery. Graz: Verlag der Technischen Universität Graz, 312–315
    1. Sajda P., Gerson A., Müller K.-R., Blankertz B., Parra L. (2003). A data analysis competition to evaluate machine learning algorithms for use in brain-computer interfaces. IEEE Trans. Neural Syst. Rehabil. Eng. 11, 184–18510.1109/TNSRE.2003.814453
    1. Sannelli C., Braun M., Tangermann M., Müller K.-R. (2008). “Estimating noise and dimensionality in BCI data sets: towards BCI illiteracy comprehension,” in Proceedings of the 4th International Brain-Computer Interface Workshop and Training Course 2008, Verlag der Technischen Universität Graz, Graz, 26–31
    1. Sannelli C., Vidaurre C., Müller K.-R., Blankertz B. (2011). Common spatial pattern patches – an optimized filter ensemble for adaptive brain-computer interfaces. J. Neural Eng. 8, 025012.10.1088/1741-2560/8/2/025012
    1. Sardouie S. H., Shamsollahi M. B. (2012). Discriminating meg signals recorded during hand movements using selection of efficient features. Front. Neurosci. 6:42.10.3389/fnins.2012.00042
    1. Schaeff S., Treder M., Venthur B., Blankertz B. (2011). Motion-based ERP spellers in a covert attention paradigm. Neurosci. Lett. 500, e11.10.1016/j.neulet.2011.05.094
    1. Schalk G., Kubánek J., Miller K., Anderson N., Leuthardt E., Ojemann J., Limbrick D., Moran D., Gerhardt L., Wolpaw J. (2007). Decoding two-dimensional movement trajectories using electrocorticographic signals in humans. J. Neural Eng. 4, 264–27510.1088/1741-2560/4/3/012
    1. Schalk G., McFarland D., Hinterberger T., Birbaumer N., Wolpaw J. (2004). BCI2000: a general-purpose brain-computer interface (BCI) system. IEEE Trans. Biomed. Eng. 51, 1034–104310.1109/TBME.2004.827072
    1. Schalk G., Miller K., Anderson N., Wilson J., Smyth M., Ojemann J., Moran D., Wolpaw J., Leuthardt E. (2008). Two-dimensional movement control using electrocorticographic signals in humans. J. Neural Eng. 5, 75.10.1088/1741-2560/5/1/008
    1. Schlögl A., Keinrath C., Zimmermann D., Scherer R., Leeb R., Pfurtscheller G. (2007a). A fully automated correction method of EOG artifacts in EEG recordings. Clin. Neurophysiol. 118, 98–10410.1016/j.clinph.2006.09.003
    1. Schlögl A., Kronegg J., Huggins J., Mason S. (2007b). “Evaluation criteria in BCI research,” in Toward Brain-Computer Interfacing, Chapt. 19, eds Dornhege G., Millán J., Hinterberger T., McFarland D. J., Müller K.-R. (Cambridge: MIT Press; ), 327–342
    1. Schreuder M., Blankertz B., Tangermann M. (2010). A new auditory multi-class brain-computer interface paradigm: spatial hearing as an informative cue. PLoS ONE 5, e9813.10.1371/journal.pone.0009813
    1. Schreuder M., Rost T., Tangermann M. (2011). Listen, you are writing! Speeding up online spelling with a dynamic auditory BCI. Front. Neurosci. 5:112.10.3389/fnins.2011.00112
    1. Schröder M., Bogdan M., Rosenstiel W., Hinterberger T., Birbaumer N. (2003). “Automated EEG feature selection for brain computer interfaces,” in Proceedings of the First International IEEE EMBS Conference on Neural Engineering, Capri, 626–629
    1. Shenoy P., Krauledat M., Blankertz B., Rao R. P. N., Müller K.-R. (2006). Towards adaptive classification for BCI. J. Neural Eng. 3, R13–R2310.1088/1741-2560/3/1/R02
    1. Silvoni S., Ramos-Murguialday A., Cavinato M., Volpato C., Cisotto G., Turolla A., Piccione F., Birbaumer N. (2011). Brain-computer interface in stroke: a review of progress. Clin. EEG Neurosci. 42, 245–25210.1177/155005941104200410
    1. Simons R., Miller G., Weerts T., Lang P. J. (1981). Correcting baseline drift artifact in slow potential recording. Psychophysiology 19, 691–70010.1111/j.1469-8986.1982.tb02526.x
    1. Sugiyama M., Krauledat M., Müller K.-R. (2007). Covariate shift adaptation by importance weighted cross validation. J. Mach. Learn. Res. 8, 1027–1061
    1. Tangermann M., Schreuder M., Dähne S., Höhne J., Regler S., Ramsay A., Quek M., Williamson J., Murray-Smith R. (2011). Optimized stimulation events for a visual ERP BCI. Int. J. Bioelectromagn. 13, 119–120
    1. Treder M. S., Schmidt N. M., Blankertz B. (2011). Gaze-independent brain-computer interfaces based on covert attention and feature attention. J. Neural Eng. 8, 066003.10.1088/1741-2560/8/6/066003
    1. Velliste M., Perel S., Spalding M., Whitford A., Schwartz A. (2008). Cortical control of a prosthetic arm for self-feeding. Nature 453, 1098–110110.1038/nature06996
    1. Vidaurre C., Sannelli C., Müller K.-R., Blankertz B. (2011). Co-adaptive calibration to improve BCI efficiency. J. Neural Eng. 8, 025009.10.1088/1741-2560/8/2/025009
    1. Vidaurre C., Schlögl A. (2008). “Comparison of adaptive features with linear discriminant classifier for Brain Computer Interfaces,” in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2008, 173–176
    1. von Bünau P., Meinecke F. C., Király F., Müller K.-R. (2009). Finding stationary subspaces in multivariate time series. Phys. Rev. Lett. 103, 214101.10.1103/PhysRevLett.103.214101
    1. Waldert S., Pistohl T., Braun C., Ball T., Aertsen A., Mehring C. (2009). A review on directional information in neural signals for brain-machine interfaces. J. Physiol. Paris 103, 244–25410.1016/j.jphysparis.2009.08.007
    1. Waldert S., Preissl H., Demandt E., Braun C., Birbaumer N., Aertsen A., Mehring C. (2008). Hand movement direction decoded from MEG and EEG. J. Neurosci. 28, 1000–100810.1523/JNEUROSCI.5171-07.2008
    1. Wang W., Sudre G. P., Xu Y., Kass R. E., Collinger J. L., Degenhart A. D., Bagic A. I., Weber D. J. (2010). Decoding and cortical source localization for intended movement direction with MEG. J. Neurophysiol. 104, 2451–246110.1152/jn.01088.2009
    1. Wang Y., Makeig S. (2010). Predicting intended movement direction using EEG from human posterior parietal cortex. Lect. Notes Artif. Int. 5638, 437–446
    1. Wang Y., Zhang Z., Li Y., Gao X., Gao S., Yang F. (2004). BCI competition 2003 – data set IV: an algorithm based on CSSD and FDA for classifying single-trial EEG. IEEE Trans. Biomed. Eng. 51, 1081–108610.1109/TBME.2004.827561
    1. Wei Q., Gao X., Gao S. (2006). Feature extraction and subset selection for classifying single-trial ECoG during motor imagery. Conf. Proc. IEEE Eng. Med. Biol. Soc. 1, 1589–1592
    1. Winkler I., Haufe S., Tangermann M. (2011). Automatic classification of artifactual ICA-components for artifact removal in EEG signals. Behav. Brain Funct. 7, 30.10.1186/1744-9081-7-30
    1. Witte M., Galan F., Waldert S., Aertsen A., Rotter S., Birbaumer N., Braun C., Mehring C. (2010). “An on-line BCI system using hand movement recognition from MEG,” in 4th International BCI Meeting 2010, Asilomar
    1. Wojcikiewicz W., Vidaurre C., Kawanabe M. (2011). “Stationary common spatial patterns: towards robust classification of non-stationary eeg signals,” in Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, Prague, 577–580
    1. Wolpaw J. R., Birbaumer N., McFarland D. J., Pfurtscheller G., Vaughan T. M. (2002). Brain-computer interfaces for communication and control. Clin. Neurophysiol. 113, 767–79110.1016/S1388-2457(02)00057-3
    1. Xu N., Gao X., Hong B., Miao X., Gao S., Yang F. (2004). BCI competition 2003 – data set IIb: enhancing P300 wave detection using ICA-based subspace projections for BCI applications. IEEE Trans. Biomed. Eng. 51, 1067–107210.1109/TBME.2004.824143
    1. Zander T. O., Lehne M., Ihme K., Jatzev S., Correia J., Kothe C., Picht B., Nijboer F. (2011). A dry EEG-system for scientific research and brain-computer interfaces. Front. Neurosci. 5:53.10.3389/fnins.2011.00053
    1. Zhang D., Wang Y., Gao X., Hong B., Gao S. (2007). An algorithm for idle-state detection in motor-imagery-based brain-computer interface. Comput. Intell Neurosci. 2007, 39714.10.1155/2007/39714
    1. Zhang H., Guan C., Ang K. K., Chin Z. Y. (2012). Learning discriminative patterns for self-paced EEG-based motor imagery detection. Front. Neurosci. 6:7.10.3389/fnins.2012.00007

Source: PubMed

Sponsoren und Mitarbeiter

Krankheiten

Drogeninterventionen

3
Abonnieren