BCI Competition II

[ goals | data sets | schedule | submission | download | news | organizers ]

Goals of the organizers

The goal of the "BCI Competition II" is to validate signal processing and classification methods for Brain Computer Interfaces (BCIs). The organizers are aware of the fact that by such a competition it is impossible to validate BCI systems as a whole. But nevertheless we envision interesting contributions to ultimately improve the full BCI.

Goals for the participants

For each data set specific goals are given in the respective description. Technically speaking, each data set consists of single-trials of spontaneous EEG activity, one part labeled (training data) and another part unlabeled (test data), and a performance measure. The goal is to infer labels for the test set from training data that maximize the performance measure for the true (but to the participant unknown) test labels. Results will be announced on this web site and in a note to IEEE Transactions on Biomedical Engineering. There will also be a full article on the competition in IEEE TBME where each winning team may describe their algorithm.

[ top ]


BCI Competition III started

Go for it!

Competition results

are available here!

Competition deadline

The deadline for submissions was at midnight CET in the night from May 1st to May 2nd.

Specification of submission rules

[ top ]

Data sets

Data sets Ia / Ib: ‹self-regulation of SCPs› (description Ia, description Ib)
provided by University of Tübingen, Institute of Medical Psychology and Behavioral Neurobiology (Niels Birbaumer)
the goal is to decide whether the subject tried to produce cortical negativity or cortical positivity
[2 classes, 7 resp. 6 channels, 1152 resp. 896 samples per trial]

Data set IIa: ‹self-regulation of mu- and/or central beta-rhythm› (description IIa)
provided by Wadsworth Center, NYS Department of Health, (Jonathan R. Wolpaw)
the goal is to provide the intended target of the feedback test trials
[4 classes, 64 channels, 896 samples per trial]

Data set IIb: ‹P300 speller paradigm› (description IIb, also as pdf)
provided by Wadsworth Center, NYS Department of Health (Jonathan R. Wolpaw)
the goal is to estimate to which letter of a 6-by-6 matrix with successively intensified rows resp. columns the subject was paying attention to
[36 classes, 64 channels, 240Hz sampling rate]

Data set III: ‹motor imagery› (description III [doc])
provided by Department of Medical Informatics, Institute for Biomedical Engineering, Graz University of Technology, (Gert Pfurtscheller, Alois Schlögl)
the goal is to provide a continuous output that could be used for a BCI- feedback (between t=3s and 9s after cue onset
[2 classes, 140 training and 140 test trials, 3 channels, 128Hz sampling rate, 0.5-30Hz filter, each trial is 9s long]

Data set IV: ‹self-paced 1s› (description IV)
provided by Berlin: Fraunhofer-FIRST, Intelligent Data Analysis Group (Klaus-Robert Müller, Benjamin Blankertz), and Freie Universität Berlin, Department of Neurology, Neurophysics Group (Gabriel Curio)
the goal is to predict the laterality of upcoming finger movements (left vs. right hand) 130 ms before keypress
[2 classes, 316 training and 100 test trials of 28 EEG channels and 500 samples]

[ top ]


December 6th 2002: Launching of the competition
May 1st II, midnight CET to May 2nd: Deadline for submission
May 15st II: announcement of the results on this web site

[ top ]


Submissions to a data set are to be send to the responsible contact person as stated in the data set description. The submission has to comprise the estimated labels, names and affiliations of all involved researchers and a short note on the involved processing techniques.
Submissions are evaluated for each data set separately. There is no need to submit for all 6 data sets in order to participate.
Each participant agrees to deliver an extended description (one page in IEEE style) of the used algorithm for the publication in IEEE TBME until May 31th II in case she/he is the winner for one of the data sets.

[ top ]

Download of data sets

Each participant has to agree to give reference to the group(s) which recorded the data and to cite (one of) the paper listed in the respective description in each of her/his publications where one of those data sets is analyzed. Furthermore, we request each author to report any publication involving BCI Competiton data sets to us for including it in our list.

[ top ]


Albany: Theresa M. Vaughan, Gerwin Schalk, Jonathan R. Wolpaw

Berlin: Benjamin Blankertz, Gabriel Curio, Klaus-Robert Müller

Graz: Alois Schlögl, Christa Neuper, Gernot Müller, Bernhard Graimann, Gert Pfurtscheller

Tübingen: Thilo Hinterberger, Michael Schröder, Niels Birbaumer

[ top ]

Contact:   Benjamin Blankertz <benjamin.blankertz@tu-berlin.de>
Technische Universität Berlin
Chair for Neurotechnology, MAR 4-3
Marchstr. 23, 10587 Berlin, Germany