moabb.datasets.Beetl2021_B#

class moabb.datasets.Beetl2021_B(phase='final', subjects=None, sessions=None, **kwargs)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

Beetl2021_B

Motor Imagery dataset from BEETL Competition - Dataset B. Part of the NeurIPS 2021 BEETL competition Task 2 focusing on transfer learning for motor imagery decoding. Dataset B contains data from Weibo2014 with 32 EEG channels selected around the motor cortex, sampled at 200 Hz. 4-class motor imagery: left hand, right hand, feet, and rest.

Motor Imagery, 4 classes (left_hand vs right_hand vs feet vs rest)

AuthorsXiaoxi Wei, A. Aldo Faisal, Moritz Grosse-Wentrup, Alexandre Gramfort, Sylvain Chevallier, Vinay Jayaram, Camille Jeunet, Stylianos Bakas, Siegfried Ludwig, Konstantinos Barmpas, Mehdi Bahri, Yannis Panagakis, Nikolaos Laskaris, Dimitrios A. Adamos, Stefanos Zafeiriou, William C. Duong, Stephen M. Gordon, Vernon J. Lawhern, Maciej Śliwowski, Vincent Rouanne, Piotr Tempczyk

πŸ‡¬πŸ‡§β€‚Imperial College London, GBΒ·2022
Motor Imagery Code: Beetl2021-B 2 subjects 1 session 32 ch 200 Hz 4 classes 4.0 s trials CC BY 4.0

Class Labels: left_hand, right_hand, feet, rest

Read Paper Compare Similar Report Issue

Overview

Motor Imagery dataset from BEETL Competition - Dataset B.

Dataset description

Dataset B contains data from subjects with 200 Hz sampling rate and 32 EEG channels. In the leaderboard phase, this includes subjects 3-5, while in the final phase it includes subjects 4-5.

Note: for the BEETL competition, there was a leaderboard phase and a final phase. Both phases contained data from two datasets, A and B. However, during leaderboard phase, dataset A contained data from subjects 1-2, while dataset B contained data from subjects 3-5. During the final phase, dataset A contained data from subjects 1-3, while dataset B contained data from subjects 4-5.

Note: for the competition the data is cut into 4 second trials, here the data is concatenated into one session! In order to get the data as provided in the competition, the data has to be cut into 4 second trials.

For the leaderboard phase, the dataset contains only training data, while for the final phase it includes both training and testing data. To learn more about the datasets in detail see To learn more about the competition see

For benchmarking the BEETL competition use phase "final", train on training data benchmark on testing data.

The data was filtered using a highpass filter with a cutoff frequency of 1 Hz and a lowpass filter with a cutoff frequency of 100 Hz.

Motor imagery tasks include:

  • - Left hand (label 0)
  • Right hand (label 1)
  • Feet (label 2)
  • Rest (label 3)
Open in Overview tab β†’

Citation & Impact

Stimulus Protocol
../_images/Beetl2021_B.svg

4s task window per trial Β· 4-class motor imagery paradigm Β· 2 runs/session across 1 sessions

HED Event Tags
HED tags4/4 events annotated

Source: MOABB BIDS HED annotation mapping.

Sensory-event
4
Agent-action
3
Experimental-stimulus
1
Rest
1
Visual-presentation
1
left_hand
Sensory-eventAgent-action
right_hand
Sensory-eventAgent-action
feet
Sensory-eventAgent-action
rest
Sensory-eventExperimental-stimulusVisual-presentationRest

HED tree view

Tree Β· left_hand
β”œβ”€ Sensory-event
β”‚  β”œβ”€ Experimental-stimulus
β”‚  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      β”œβ”€ Move
      └─ Left
         └─ Hand
Tree Β· right_hand
β”œβ”€ Sensory-event
β”‚  β”œβ”€ Experimental-stimulus
β”‚  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      β”œβ”€ Move
      └─ Right
         └─ Hand
Tree Β· feet
β”œβ”€ Sensory-event
β”‚  β”œβ”€ Experimental-stimulus
β”‚  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      β”œβ”€ Move
      └─ Foot
Tree Β· rest
β”œβ”€ Sensory-event
β”œβ”€ Experimental-stimulus
β”œβ”€ Visual-presentation
└─ Rest
Channel Summary
Total channels32
EEG32 (EEG)
Montage10-05
Sampling200 Hz
FilterBandpass filter (1-100 Hz)
Notch / line50 Hz

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

Motor Imagery dataset from BEETL Competition - Dataset B.

Dataset description

Dataset B contains data from subjects with 200 Hz sampling rate and 32 EEG channels. In the leaderboard phase, this includes subjects 3-5, while in the final phase it includes subjects 4-5.

Note: for the BEETL competition, there was a leaderboard phase and a final phase. Both phases contained data from two datasets, A and B. However, during leaderboard phase, dataset A contained data from subjects 1-2, while dataset B contained data from subjects 3-5. During the final phase, dataset A contained data from subjects 1-3, while dataset B contained data from subjects 4-5.

Note: for the competition the data is cut into 4 second trials, here the data is concatenated into one session! In order to get the data as provided in the competition, the data has to be cut into 4 second trials.

For the leaderboard phase, the dataset contains only training data, while for the final phase it includes both training and testing data. To learn more about the datasets in detail see [1]. To learn more about the competition see [2].

For benchmarking the BEETL competition use phase β€œfinal”, train on training data benchmark on testing data.

The data was filtered using a highpass filter with a cutoff frequency of 1 Hz and a lowpass filter with a cutoff frequency of 100 Hz.

Motor imagery tasks include: - Left hand (label 0) - Right hand (label 1) - Feet (label 2) - Rest (label 3)

phase#

Either β€œleaderboard” or β€œfinal”

Type:

str

References

[1]

Wei, X., Faisal, A. A., Grosse-Wentrup, M., Gramfort, A., Chevallier, S., Jayaram, V., … & Tempczyk, P. (2022, July). 2021 BEETL competition: Advancing transfer learning for subject independence and heterogeneous EEG data sets. In NeurIPS 2021 Competitions and Demonstrations Track (pp. 205-219). PMLR.

from moabb.datasets import Beetl2021_B
dataset = Beetl2021_B()
data = dataset.get_data(subjects=[4])
print(data[4])

Dataset summary

#Subj

2

#Chan

32

#Classes

4

#Trials / class

160

Trials length

4 s

Freq

200 Hz

#Sessions

1

#Runs

1

Total_trials

1590

Participants

  • Population: healthy

Equipment

  • Electrodes: EEG

  • Montage: standard_1005

Preprocessing

  • Data state: preprocessed

  • Bandpass filter: 1-100 Hz

  • Steps: Bandpass filtering (1-100 Hz), Channel selection (32 channels from Weibo2014)

  • Notes: Data from Weibo2014 dataset with 32 channels selected around motor cortex. Filtered with bandpass 1-100 Hz. Cut into 4-second trials for the competition.

Data Access

Experimental Protocol

  • Paradigm: imagery

  • Task type: motor imagery

__init__(phase='final', subjects=None, sessions=None, **kwargs)[source]#

Initialize BEETL Dataset B.

Parameters:

phase (str) – Either β€œleaderboard” (subjects 3-5) or β€œfinal” (subjects 4-5)

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)[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.

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])

See also

CacheConfig

Cache configuration for get_data().

moabb.datasets.bids_interface.get_bids_root

Return the BIDS root path.

Notes

Added in version 1.5.

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

Return path to the data files.

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 β€œ~/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) → None | DataFrame[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 | pd.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

BaseDataset.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 (Pipeline | None) – Optional processing pipeline to apply to the data. To generate an adequate pipeline, we recommend using moabb.utils.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 β€œfixed” 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: DatasetMetadata | None[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