moabb.datasets.Kalunga2016#

class moabb.datasets.Kalunga2016[source]#

SSVEP Exo dataset.

PapersWithCode leaderboard: https://paperswithcode.com/dataset/kalunga2016-moabb

Dataset summary

#Subj

#Chan

#Classes

#Trials / class

Trials length

Sampling rate

#Sessions

12

8

4

16

2s

256Hz

1

SSVEP dataset from E. Kalunga PhD in University of Versailles [1].

The datasets contains recording from 12 male and female subjects aged between 20 and 28 years. Informed consent was obtained from all subjects, each one has signed a form attesting her or his consent. The subject sits in an electric wheelchair, his right upper limb is resting on the exoskeleton. The exoskeleton is functional but is not used during the recording of this experiment.

A panel of size 20x30 cm is attached on the left side of the chair, with 3 groups of 4 LEDs blinking at different frequencies. Even if the panel is on the left side, the user could see it without moving its head. The subjects were asked to sit comfortably in the wheelchair and to follow the auditory instructions, they could move and blink freely.

A sequence of trials is proposed to the user. A trial begin by an audio cue indicating which LED to focus on, or to focus on a fixation point set at an equal distance from all LEDs for the reject class. A trial lasts 5 seconds and there is a 3 second pause between each trial. The evaluation is conducted during a session consisting of 32 trials, with 8 trials for each frequency (13Hz, 17Hz and 21Hz) and 8 trials for the reject class, i.e. when the subject is not focusing on any specific blinking LED.

There is between 2 and 5 sessions for each user, recorded on different days, by the same operators, on the same hardware and in the same conditions.

References

1

Emmanuel K. Kalunga, Sylvain Chevallier, Quentin Barthelemy. “Online SSVEP-based BCI using Riemannian Geometry”. Neurocomputing, 2016. arXiv report: https://arxiv.org/abs/1501.03227

Notes

Note

Kalunga2016 was previously named SSVEPExo. SSVEPExo will be removed in version 1.1.

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

Examples using moabb.datasets.Kalunga2016#

Cross-Subject SSVEP

Cross-Subject SSVEP

Cross-Subject SSVEP