Service Incident: New DOI registrations are working again. Re-registration of failed DOI registrations (~500) are still affected by the service incident at DataCite (our DOI registration agency).
Published December 5, 2016 | Version v1
Dataset Open

EEG Data for: "Learning from Label Proportions in Brain-Computer Interfaces"

Creators

  • 1. Albert Ludwig University Freiburg

Contributors

Contact person:

Data collector:

  • 1. Albert Ludwig University Freiburg

Description

Data about two experiments is contained in this repository. An EEG experiment utilizing visual event-related potentials (ERPs) with N=13 healthy subjects was conducted in addition to a smaller study with N=5 subjects performing both an auditory and a visual ERP paradigm. 

The dataset is used and described in the following journal article:

Hübner, D., Verhoeven, T., Schmid, K., Müller, K. R., Tangermann, M., & Kindermans, P. J. (2017). Learning from label proportions in brain-computer interfaces: online unsupervised learning with guarantees. PloS one, 12(4), e0175856.

Please cite the above article when using the data.

The larger data set with N=13 is different to ordinary ERP datasets in the sense that the train of stimuli to spell one character (68) is divided into repetitions of two interleaved sequences with length 8 and 18, respectively. We added '#' symbols to the spelling matrix which should never be attended by the subject and hence, are non-targets by definition. The first, shorter sequence, now highlights only ordinary characters, while the second sequence also highlights '#' -- visual blank symbols. By construction, sequence 1 has a higher target ratio than sequence 2. These known, but different target and non-target proportions are then used to reconstruct the target and non-target class means. This approach which does not need explicit class labels is termed Learning from Label Proportions (LLP). It can be used to decode brain signals without prior calibration session. More details can be found in the article.

In another study, the above data set was used to simulate a new unsupervised mixture approach which combines the mean estimation of the unsupervised expectation-maximization algorithm by Kindermans et al. (2012, PLoS One) with the means obtained with the LLP approach. This leads to an unsupervised solution for which the performance is as good as in the supervised scenario. Please find more details in the following article:

Verhoeven, T., Hübner, D., Tangermann, M., Müller, K. R., Dambre, J., & Kindermans, P. J. (2017). Improving zero-training brain-computer interfaces by mixing model estimators. Journal of neural engineering, 14(3), 036021.

The following files are available:

description.pdf: Full description of the dataset
offline_auditory.zip: Data from the auditory offline study with N=5 subjects
offline_visual.zip: Data from the visual offline study with N=5 subjects
online_study_1-7.zip: Data from the online study for subjects 1-7
online_study_8-13.zip: Data from the online study for subjects 8-13
sequence.mat: Sequence data necessary for applying LLP to the online study. It is the same for all subjects

We will create a git repository with example code soon.

Notes

We gratefully acknowledge the support by BrainLinks-BrainTools Cluster of Excellence funded by the German Research Foundation (DFG), grant number EXC 1086.

Files

description.pdf

Files (6.3 GB)

Name Size Download all
md5:8841ef59a03f0a3000d684f316642c2f
441.4 kB Preview Download
md5:80a5371f989f435d7f916b9909db6977
1.7 GB Preview Download
md5:182e3a432a885af665fb0c3aca0d6e27
1.1 GB Preview Download
md5:4a4daa13d251dd953d8953554d8faedd
1.9 GB Preview Download
md5:c78bffee308aae8015260a8a9d4e55e8
1.7 GB Preview Download
md5:e75d8332698a338d79b8049eddefb7d1
2.2 kB Download

Additional details

Related works