Causal Analysis of simulated EEG data

Description of task

Motivation: Noninvasive electrophysiological measurements like EEG/MEG measure to large extent unknown superpositions of very many sources. Any relation observed between channels is dominated by meaningless mixtures of mainly independent sources. The question is how to observe and properly interpret true interactions in the presence of such strong confounders.

Download data here.

To read the data into MATLAB, type
fid=fopen('simuldata.bin');
data=reshape(fread(fid,'float'),6000,2,1000);

The data consists of 1000 examples of bivariate data for 6000 time points. Each example is a superposition of a signal (of interest) and noise. The signal is constructed from a unidirectional bivariate AR-model of order 10 with (otherwise) random AR-parameters and uniformly distributed input. The noise is constructed of three independent sources, generated with 3 univariate AR-models with random parameters and uniformly distributed input, which were instantaneously mixed into the two sensors with a random mixing matrix. The relative strength of noise and signal was set randomly. The data were generated with this Matlab code. Note, that the phrase 'simulated EEG data' is meant loosely. The simulation addresses the conceptual problems of EEG data, but e.g. the actual spectra can be quite different from real EEG data.

The task is to estimate the direction of the interaction of the signal. A submitted result is a vector with 1000 numbers having the values 1, -1, or 0. Here, 1 means direction is from first to second sensor, -1 means direction is from second to first sensor, and 0 means "I don't know".

For all examples either 1 or -1 is correct. The most important point here is the way it is counted: you get +1 point for each correct answer; you get -10 points for each wrong answer; and you get 0 points for each 0 in the result vector. With this counting confidence about the result is added into the evaluation. It is strongly recommended that for each example the evidence for a specific finding is assessed.

Submission

Please send submissions by October 10, 2011 to

Guido Nolte
email: guido.nolte(at)first.fraunhofer.de

Causal Analysis of simulated EEG data

Description of task

Motivation: Noninvasive electrophysiological measurements like EEG/MEG measure to large extent unknown superpositions of very many sources. Any relation observed between channels is dominated by meaningless mixtures of mainly independent sources. The question is how to observe and properly interpret true interactions in the presence of such strong confounders.

Download data here.

To read the data into MATLAB, type
fid=fopen('simuldata.bin');
data=reshape(fread(fid,'float'),6000,2,1000);

The data consists of 1000 examples of bivariate data for 6000 time points. Each example is a superposition of a signal (of interest) and noise. The signal is constructed from a unidirectional bivariate AR-model of order 10 with (otherwise) random AR-parameters and uniformly distributed input. The noise is constructed of three independent sources, generated with 3 univariate AR-models with random parameters and uniformly distributed input, which were instantaneously mixed into the two sensors with a random mixing matrix. The relative strength of noise and signal was set randomly. The data were generated with this Matlab code. Note, that the phrase 'simulated EEG data' is meant loosely. The simulation addresses the conceptual problems of EEG data, but e.g. the actual spectra can be quite different from real EEG data.

The task is to estimate the direction of the interaction of the signal. A submitted result is a vector with 1000 numbers having the values 1, -1, or 0. Here, 1 means direction is from first to second sensor, -1 means direction is from second to first sensor, and 0 means "I don't know".

For all examples either 1 or -1 is correct. The most important point here is the way it is counted: you get +1 point for each correct answer; you get -10 points for each wrong answer; and you get 0 points for each 0 in the result vector. With this counting confidence about the result is added into the evaluation. It is strongly recommended that for each example the evidence for a specific finding is assessed.

Submission

The deadline for submission of results was October 31, 2011 to be sent to

Guido Nolte
email: guido.nolte(at)first.fraunhofer.de


In addition, each participant was asked to provide basic information about his/her algorithm (e.g. a bibliographical reference) .

Results

To see the algorithm details, click the submitter's name.

Name	City	Total points	Correct detections	False detections	Details
A.M. Bianchi	Milano/Italy	-2289	701	299
S. Hu	Hangzhou/China	252	352	10	Click name
L. Leistritz	Jena/Germany	-357	773	113	Click name
V. Vakorin	Toronto/Canada	218	278	6	Click name
M. Wibral	Frankfurt/Germany	-247	163	41	(pdf)

Remark: The total points can be calculated as the number of correct detections minus ten times
the number of false detections.