moabb.datasets.BI2012#

class moabb.datasets.BI2012(training=True, online=False, subjects=None, sessions=None, **kwargs)[source]#

P300 dataset BI2012 from a “Brain Invaders” experiment.

PapersWithCode leaderboard: https://paperswithcode.com/dataset/braininvaders2012-moabb

Dataset summary

#Subj

25

#Chan

16

#Trials / class

640 NT / 128 T

Trials length

1 s

Freq

128 Hz

#Sessions

2

Participants

  • Population: healthy

  • Age: 24.4 (range: 21-31) years

  • BCI experience: half played games occasionally (around 4.5 hours a week)

Equipment

  • Amplifier: NeXus-32 (MindMedia/TMSi)

  • Electrodes: wet electrodes

  • Montage: 10-20

  • Reference: hardware common average reference

Preprocessing

  • Data state: raw EEG with software tagging (note: tagging introduces jitter and latency)

  • Re-reference: hardware common average reference

  • Notes: Software tagging introduces a jitter and a latency which artificially modify the ERPs onset. Strong drift over time resulting in higher jitter. Only possible to compare ERP acquired within the same experimental conditions when latency is not corrected.

Data Access

Experimental Protocol

  • Paradigm: p300

  • Feedback: visual (game interface)

  • Stimulus: visual flashes of alien groups

Found an issue with this dataset?

If you encounter any problems with this dataset (missing files, incorrect metadata, loading errors, etc.), please let us know!

Report an Issue on GitHub

Dataset following the setup from [1] carried-out at University of Grenoble Alpes.

This dataset contains electroencephalographic (EEG) recordings of 25 subjects testing the Brain Invaders, a visual P300 Brain-Computer Interface inspired by the famous vintage video game Space Invaders (Taito, Tokyo, Japan). The visual P300 is an event-related potential elicited by a visual stimulation, peaking 240-600 ms after stimulus onset. EEG data were recorded by 16 electrodes in an experiment that took place in the GIPSA-lab, Grenoble, France, in 2012). A full description of the experiment is available in [1].

Principal Investigator:

B.Sc. Gijsbrecht Franciscus Petrus Van Veen

Technical Supervisors:

Ph.D. Alexandre Barachant, Eng. Anton Andreev, Eng. Grégoire Cattan, Eng. Pedro. L. C. Rodrigues

Scientific Supervisor:

Ph.D. Marco Congedo

ID of the dataset:

BI.EEG.2012-GIPSA

Notes

Note

BI2012 was previously named bi2012. bi2012 will be removed in version 1.1.

Added in version 0.4.6.

References

[1] (1,2)

Van Veen, G., Barachant, A., Andreev, A., Cattan, G., Rodrigues, P. C., & Congedo, M. (2019). Building Brain Invaders: EEG data of an experimental validation. arXiv preprint arXiv:1905.05182.

data_path(subject, path=None, force_update=False, update_path=None, verbose=None)[source]#

Get path to local copy of a subject data.

Parameters:

  • subject (int) – Number of subject to use

  • path (None | str) – Location of where to look for the data storing location. If None, the environment variable or config parameter MNE_DATASETS_(dataset)_PATH is used. If it doesn’t exist, the “~/mne_data” directory is used. If the dataset is not found under the given path, the data will be automatically downloaded to the specified folder.

  • force_update (bool) – Force update of the dataset even if a local copy exists.

  • update_path (bool | None Deprecated) – If True, set the MNE_DATASETS_(dataset)_PATH in mne-python config to the given path. If None, the user is prompted.

  • verbose (bool, str, int, or None) – If not None, override default verbose level (see mne.verbose()).

Returns:

path – Local path to the given data file. This path is contained inside a list of length one, for compatibility.

Return type:

list of str

On this page