moabb.datasets.BCIComp2020UpperLimb#

class moabb.datasets.BCIComp2020UpperLimb(subjects=None, sessions=None)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

BCIComp2020UpperLimb

BCI Competition 2020 Track 4: session-to-session motor imagery decoding of three grasping tasks (cylindrical, spherical, lumbrical) from a single right arm. 15 subjects, 60 channels, 250 Hz, three sessions on separate days.

Imagery, 3 classes (cylindrical vs spherical vs lumbrical)

AuthorsJi-Hoon Jeong, Jeong-Hyun Cho, Young-Eun Lee, Seo-Hyun Lee, Gi-Hwan Shin, Young-Seok Kweon, Jose del R. Millan, Klaus-Robert Muller, Seong-Whan Lee

🇰🇷 Korea University, KR·2022·bcicompetition2020@gmail.com
Imagery Code: BCIComp2020UpperLimb 15 subjects 3 sessions 60 ch 250 Hz 3 classes 4.0 s trials CC BY 4.0

Class Labels: cylindrical, spherical, lumbrical

Read Paper Compare Similar Report Issue

Overview

BCI Competition 2020 Track 4 — Upper-limb grasping MI (session-to-session).

Dataset from the 2020 International BCI Competition

Dataset Description

Fifteen right-handed subjects (S1-S15, aged 20-34) performed motor imagery of three grasping tasks on a single right arm: cylindrical grasp (holding a cup), spherical grasp (holding a ball), and lumbrical grasp (holding a card). EEG was recorded at 250 Hz using 60 channels in a 10-20 configuration with a BrainAmp amplifier (BrainProducts GmbH), FCz reference, Fpz ground, and a 60 Hz notch.

Each subject was recorded on three separate days (7 days apart) to pose a session-to-session transfer problem. Each session contains 150 trials (50 per class). A single trial lasts 10 s: 0-3 s relaxation, 3-6 s visual cue (flashing green circle around the targeted object), 6-10 s motor imagery. Only the 4-second motor imagery window is exposed by this loader, yielding consistent (150, 60, 1000) arrays per session.

Session layout

  • - Session "0": day 1, intended for training
  • Session "1": day 2, intended for validation
  • Session "2": day 3, intended as the held-out transfer test

The test-day .mat files released by the organizers have the cue section (samples 750-1500, i.e. seconds 3-6 of each trial) zeroed in-place to prevent the visual-cue response from inflating results. The array shape stays at (2501, 60, 150), so the same sample slice (1500-2500) extracts the motor imagery window consistently across train / val / test.

Test-day labels are published as a separate answer-sheet XLSX on OSF rather than inside the .mat files. They are embedded in this module as :data:`_TEST_LABELS_DAY3` so the loader can return labelled data for all three sessions without a second download.

Open in Overview tab →

Citation & Impact

Stimulus Protocol
../_images/BCIComp2020UpperLimb.svg

4s task window per trial · 3-class imagery paradigm · 1 runs/session across 3 sessions

HED Event Tags
HED tags3/3 events annotated

Source: MOABB BIDS HED annotation mapping.

Label
3
Sensory-event
3
cylindrical
Sensory-eventLabel
spherical
Sensory-eventLabel
lumbrical
Sensory-eventLabel

HED tree view

Tree · cylindrical
├─ Sensory-event
└─ Label
Tree · spherical
├─ Sensory-event
└─ Label
Tree · lumbrical
├─ Sensory-event
└─ Label
Channel Summary
Total channels60
EEG60
Montage10-05
Sampling250 Hz
ReferenceFCz
Filter{'notch_hz': 60}
Notch / line60 Hz

This diagram is automatically generated from MOABB metadata. Please consult the original publication to confirm the experimental protocol details.

BCI Competition 2020 Track 4 — Upper-limb grasping MI (session-to-session).

Dataset from the 2020 International BCI Competition [1].

Dataset Description

Fifteen right-handed subjects (S1-S15, aged 20-34) performed motor imagery of three grasping tasks on a single right arm: cylindrical grasp (holding a cup), spherical grasp (holding a ball), and lumbrical grasp (holding a card). EEG was recorded at 250 Hz using 60 channels in a 10-20 configuration with a BrainAmp amplifier (BrainProducts GmbH), FCz reference, Fpz ground, and a 60 Hz notch.

Each subject was recorded on three separate days (7 days apart) to pose a session-to-session transfer problem. Each session contains 150 trials (50 per class). A single trial lasts 10 s: 0-3 s relaxation, 3-6 s visual cue (flashing green circle around the targeted object), 6-10 s motor imagery. Only the 4-second motor imagery window is exposed by this loader, yielding consistent (150, 60, 1000) arrays per session.

Session layout

  • Session “0”: day 1, intended for training

  • Session “1”: day 2, intended for validation

  • Session “2”: day 3, intended as the held-out transfer test

The test-day .mat files released by the organizers have the cue section (samples 750-1500, i.e. seconds 3-6 of each trial) zeroed in-place to prevent the visual-cue response from inflating results. The array shape stays at (2501, 60, 150), so the same sample slice (1500-2500) extracts the motor imagery window consistently across train / val / test.

Test-day labels are published as a separate answer-sheet XLSX on OSF rather than inside the .mat files. They are embedded in this module as _TEST_LABELS_DAY3 so the loader can return labelled data for all three sessions without a second download.

References

[1]

Jeong, J.-H. et al. (2022). 2020 International brain-computer interface competition: A review. Frontiers in Human Neuroscience, 16, 898300. https://doi.org/10.3389/fnhum.2022.898300

from moabb.datasets import BCIComp2020UpperLimb
dataset = BCIComp2020UpperLimb()
data = dataset.get_data(subjects=[1])
print(data[1])

Dataset summary

#Subj

15

#Chan

60

#Classes

3

#Trials / class

50

Trials length

4 s

Freq

250 Hz

#Sessions

3

#Runs

1

Total_trials

6750

Participants

  • Population: healthy

Equipment

  • Amplifier: BrainAmp (BrainProducts GmbH)

  • Montage: standard_1005

  • Reference: FCz

Preprocessing

  • Data state: preprocessed

  • Steps: 60 Hz notch filter, cue-aligned epoching, motor imagery window (6-10 s of each trial) extracted by loader

Data Access

Experimental Protocol

  • Paradigm: imagery

  • Stimulus: visual cue

__init__(subjects=None, sessions=None)[source]#

Initialize function for the BaseDataset.

property all_subjects#

Full list of subjects available in this dataset (unfiltered).

convert_to_bids(path=None, subjects=None, overwrite=False, format='EDF', verbose=None, generate_figures=False)[source]#

Convert the dataset to BIDS format.

Saves the raw EEG data in a BIDS-compliant directory structure. Unlike the caching mechanism (see CacheConfig), the files produced here do not contain a processing-pipeline hash (desc-<hash>) in their names, making the output a clean, shareable BIDS dataset.

Parameters:

  • path (str | Path | None) – Directory under which the BIDS dataset will be written. If None the default MNE data directory is used (same default as the rest of MOABB).

  • subjects (list of int | None) – Subject numbers to convert. If None, all subjects in subject_list are converted.

  • overwrite (bool) – If True, existing BIDS files for a subject are removed before saving. Default is False.

  • format (str) – The file format for the raw EEG data. Supported values are "EDF" (default), "BrainVision", and "EEGLAB".

  • verbose (str | None) – Verbosity level forwarded to MNE/MNE-BIDS.

  • generate_figures (bool) – If True, generate interactive neural signature HTML figures in {bids_root}/derivatives/neural_signatures/. Requires plotly (pip install moabb[interactive]). Default is False.

Returns:

bids_root – Path to the root of the written BIDS dataset.

Return type:

pathlib.Path

Examples

>>> from moabb.datasets import AlexMI
>>> dataset = AlexMI()
>>> bids_root = dataset.convert_to_bids(path="/tmp/bids", subjects=[1])

Notes

Use CacheConfig to configure caching for get_data(). Use moabb.datasets.bids_interface.get_bids_root to get the BIDS root path.

Added in version 1.5.

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

Return local paths for a subject’s split files.

Downloads training + validation + test files for subject via moabb.datasets.download.data_dl(). Returns the path for the requested split (defaults to "training").

download(subject_list=None, path=None, force_update=False, update_path=None, accept=False, verbose=None)[source]#

Download all data from the dataset.

This function is only useful to download all the dataset at once.

Parameters:

  • subject_list (list of int | None) – List of subjects id to download, if None all subjects are downloaded.

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

  • accept (bool) – Accept licence term to download the data, if any. Default: False

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

get_additional_metadata(subject: str, session: str, run: str)[source]#

Load additional metadata for a specific subject, session, and run.

This method is intended to be overridden by subclasses to provide additional metadata specific to the dataset. The metadata is typically loaded from an events.tsv file or similar data source.

Parameters:

  • subject (str) – The identifier for the subject.

  • session (str) – The identifier for the session.

  • run (str) – The identifier for the run.

Returns:

A DataFrame containing the additional metadata if available, otherwise None.

Return type:

None | pandas.DataFrame

get_block_repetition(paradigm, subjects, block_list, repetition_list)[source]#

Select data for all provided subjects, blocks and repetitions.

subject -> session -> run -> block -> repetition

See also

get_data

Parameters:

  • subjects (List of int) – List of subject number

  • block_list (List of int) – List of block number

  • repetition_list (List of int) – List of repetition number inside a block

Returns:

data – dict containing the raw data

Return type:

Dict

get_data(subjects=None, cache_config=None, process_pipeline=None)[source]#

Return the data corresponding to a list of subjects.

The returned data is a dictionary with the following structure:

data = {"subject_id": {"session_id": {"run_id": run}}}

subjects are on top, then we have sessions, then runs. A sessions is a recording done in a single day, without removing the EEG cap. A session is constitued of at least one run. A run is a single contiguous recording. Some dataset break session in multiple runs.

Processing steps can optionally be applied to the data using the *_pipeline arguments. These pipelines are applied in the following order: raw_pipeline -> epochs_pipeline -> array_pipeline. If a *_pipeline argument is None, the step will be skipped. Therefore, the array_pipeline may either receive a mne.io.Raw or a mne.Epochs object as input depending on whether epochs_pipeline is None or not.

Parameters:

  • subjects (List of int) – List of subject number

  • cache_config (dict | CacheConfig) – Configuration for caching of datasets. See CacheConfig for details.

  • process_pipeline (sklearn.pipeline.Pipeline | None) – Optional processing pipeline to apply to the data. To generate an adequate pipeline, we recommend using moabb.make_process_pipelines(). This pipeline will receive mne.io.BaseRaw objects. The steps names of this pipeline should be elements of StepType. According to their name, the steps should either return a mne.io.BaseRaw, a mne.Epochs, or a numpy.ndarray. This pipeline must be “fixed” because it will not be trained, i.e. no call to fit will be made.

Returns:

data – dict containing the raw data

Return type:

Dict

property metadata[source]#

Return structured metadata for this dataset.

Returns the DatasetMetadata object from the centralized catalog, or None if metadata is not available for this dataset.

Returns:

The metadata object containing acquisition parameters, participant demographics, experiment details, and documentation. Returns None if no metadata is registered for this dataset.

Return type:

DatasetMetadata | None

Examples

>>> from moabb.datasets import BNCI2014_001
>>> dataset = BNCI2014_001()
>>> dataset.metadata.participants.n_subjects
9
>>> dataset.metadata.acquisition.sampling_rate
250.0