[goals |news |data sets |schedule |submission |download |organizers |references ]
Data sets 1:‹motor imagery, uncued classifier application›(description)
provided by theBerlin BCIgroup:Technische Universität Berlin (Machine Learning Laboratory) andFraunhofer FIRST (Intelligent Data Analysis Group)(Klaus-Robert Müller,Benjamin Blankertz, Carmen Vidaurre,Guido Nolte), and Campus Benjamin Franklin of the Charité - University Medicine Berlin, Department of Neurology, Neurophysics Group (Gabriel Curio)
EEG, motor imagery (2 classes of left hand, right hand, foot); evaluation data is continuous EEG which contains also periods of idle state
[64 EEG channels (0.05-200Hz), 1000Hz sampling rate, 2 classes (+ idle state), 7 subjects]
Data sets 2a:‹4-class motor imagery› (description)
provided by theInstitute for Knowledge Discovery(Laboratory of Brain-Computer Interfaces),Graz University of Technology,(Clemens Brunner, Robert Leeb, Gernot Müller-Putz,Alois Schlögl,Gert Pfurtscheller)
EEG, cued motor imagery (left hand, right hand, feet, tongue)
[22 EEG channels (0.5-100Hz; notch filtered), 3 EOG channels, 250Hz sampling rate, 4 classes, 9 subjects]
Data sets 2b:‹motor imagery› (description)
provided by theInstitute for Knowledge Discovery(Laboratory of Brain-Computer Interfaces),Graz University of Technology,(Robert Leeb, Clemens Brunner, Gernot -Müller-Putz,Alois Schlögl,Gert Pfurtscheller)
EEG, cued motor imagery (left hand, right hand)
[3 bipolar EEG channels (0.5-100Hz; notch filtered), 3 EOG channels, 250Hz sampling rate, 2 classes, 9 subjects]
Data sets 3:‹hand movement direction in MEG›(description)
provided by theBrain Machine Interfacing Initiative, Albert-Ludwigs-UniversityFreiburg, theBernstein Center for Computational Neuroscience Freiburgand theInstitute of Medical Psychology and Behavioral Neurobiology,University of Tübingen (Stephan Waldert,Carsten Mehring,HubertPreissl,Christoph Braun)
The data set contains directionally modulated low-frequency MEGactivity that was recorded while subjects performed wrist movements infour different directions.
[10 MEG channels (filtered to 0.5-100Hz), 400Hz sampling rate, 4 classes, 2 subjects]
Data sets 4:‹finger movements in ECoG›(description)
provided byDepartments of Physics and Medicine of theUniversity of Washington, Seattle(Kai J. Miller) andWadsworth Center, NYS Department of Health(Gerwin Schalk)
ECoG data during individual flexions of the five fingers; movements acquired with a data glove.
[48 - 64 ECoG channels (0.15-200Hz), 1000Hz sampling rate, 5 classes, 3 subjects]
July 3rd 2008: launching of the competition
November 21st 2008, midnight CET to Nov 22nd: deadline forsubmissions
December 12th 2008: announcement of the results at aworkshop ofNIPS 2008and on this web site
Submissions to a data set are to be sent to the responsible contactperson as stated in the data set description. The submission has tocomprise the estimated labels, names and affiliations of all involvedresearchers and a short note on the involved processing techniques. Wesend confirmations for each submission we get. If you do not receivea confirmation within 2 days please resend your email with CC to the otherorganizing committee members, ‹benjamin.blankertz@tu-berlin.de›, ‹alois.schloegl@tugraz.at›, ‹waldert@bccn.uni-freiburg.de›, ‹kjmiller@u.washington.edu›.
One researcher may NOT submit multiple results to one data set. She/hehas to decide for her/his favorite one. However: From one researchgroup multiple submissions to one data set are possible. The sets ofinvolved researchers do not have to be disjoint, but (1) the 'firstauthor' (contributor) should be distinct, and (2) approaches should besubstantially different.
For details on how to submit your results please refer to thedescription of the respective data set. If questions remain unansweredsend an email to the responsable contact person for the specific dataset which is indicated in the description.
Submissions are evaluated for each group of data sets separately. There is no need to submit for all data sets of the competition in order to participate, however each submission must provide resultsfor all data sets of one group (e.g., for all subjects providedin Data sets 2a).
Each participant agrees to deliver an extended description (4-6 pages)of the used algorithm for publication until Februar 1st 2009 in caseshe/he is the winner for one of the data sets.
[top ]Each participant has to agree to give reference to the group(s) whichrecorded the data and to cite (one of) the paper listed in therespective description in each of her/his publications where one ofthose data sets is analyzed. Furthermore, we request each author to reportany publication involving BCI Competiton data sets to us forincluding it in ourlist.
[top ]Berlin:Benjamin Blankertz, Carmen Vidaurre, Michael Tangermann, Klaus-Robert Müller
Graz:Clemens Brunner, Robert Leeb, Gernot Müller-Putz, Alois Schlögl, Gert Pfurtscheller
Freiburg/Tübingen:Stephan Waldert, Carsten Mehring, Ad Aertsen, Niels Birbaumer
Washington/Albany:Kai J. Miller, Gerwin Schalk
[top ]The first BCI Competition was announced at NIPS 2001, and the second at NIPS 2002. The firstcompetition was a first try to see how such a thing wouldwork and it was only announced in a smaller community. Accordinglythere were not such much submissions, but nevertheless manyresearchers showed great interest when the results were published(first in the internet and then inIEEE Trans Neural Sys Rehab Eng,2003, vol 11(2), pp. 184-185 [draft ]). For the second competition data setswere provided by four of the leading groups in EEG-based BCIs. Here wereceived 59 submissions. A review of the 2nd competition appeared inIEEE Trans Biomed Eng, 51(6):1044-1051, 2004 [draft ] and articles of allwinning teams of the competition were published in the same issuewhich provides a good overview of the state of art in classificationtechniques for BCI. The 3rd BCI Competition involved data sets fromfive BCI labs and we received 99 submissions. It was reviewed inIEEETrans Neural Sys Rehab Eng, 14(2):153-159, 2006 [draft ] and individualarticles of the competition winners appeared in differentjournals.
