moabb.datasets.BNCI2020_001#

class moabb.datasets.BNCI2020_001(subjects=None, sessions=None, *, return_all_modalities=False)[source]#

Bases: BNCIBaseDataset

[source]

Dataset Snapshot

BNCI2020_001

This study investigated whether EEG-based correlates of natural reach-and-grasp actions can be successfully identified and decoded using mobile EEG systems (water-based EEG-Versatile and dry-electrodes EEG-Hero headset) and gel-based recordings obtained in a laboratory environment (g.USBamp/g.Ladybird, gold standard). For each recording system, 15 study participants performed 80 self-initiated reach-and-grasp actions toward a glass (palmar grasp) and a spoon (lateral grasp).

Motor Imagery, 3 classes (palmar_grasp vs lateral_grasp vs rest)

AuthorsAndreas Schwarz, Carlos Escolano, Luis Montesano, Gernot R. Müller-Putz

🇦🇹 Institute of Neural Engineering, Graz University of Technology, Austria·2020·gernot.mueller@tugraz.at
Motor Imagery Code: BNCI2020-001 45 subjects 1 session 58 ch 256 Hz 3 classes 5.0 s trials CC BY 4.0

Class Labels: palmar_grasp, lateral_grasp, rest

Read Paper Compare Similar Report Issue

Overview

BNCI 2020-001 Reach-and-Grasp Electrode Comparison dataset.

Dataset from

Dataset Description

This dataset contains EEG data from 45 subjects (15 per electrode type) performing natural reach-and-grasp movements with different electrode systems. Three electrode types were compared:

  • - Gel-based electrodes (g.tec g.USBamp system): 58 EEG + 6 EOG channels
  • Water-based electrodes (BitBrain EEG-Versatile): 32 EEG + 6 EOG channels
  • Dry electrodes (BitBrain EEG-Hero): 11 EEG channels (no EOG)

The study investigates the feasibility of decoding natural reach-and-grasp movements from EEG signals recorded with different electrode technologies, including mobile systems suitable for real-world applications.

Participants

  • - 45 healthy able-bodied subjects (15 per electrode type)
  • All subjects performed the same experimental protocol
  • Each subject used only one electrode type
  • Location: Graz University of Technology, Austria (in collaboration with BitBrain, Spain)

Recording Details

  • - Sampling rate: 256 Hz (all systems)
  • Reference: Earlobe (right for gel, left for water/dry)
  • Ground: AFz (gel/water), left earlobe (dry)
  • Filters: 0.3-100 Hz bandpass (3rd-4th order Butterworth)

Experimental Procedure

  • - Self-paced reaching and grasping actions toward objects on a table
  • Two grasp types: palmar grasp (empty jar) and lateral grasp (spoon in jar)
  • Rest condition: Quiet sitting with fixation
  • 80 trials per grasp type distributed across 4 runs
  • Window of interest: [-2, 3] seconds relative to movement onset

Event Codes

  • - palmar_grasp: Movement onset for palmar grasp (reaching to empty jar)
  • lateral_grasp: Movement onset for lateral grasp (reaching to jar with spoon)
  • rest: Onset of rest period

Electrode Types

Subjects are grouped by electrode type (15 per type). The subject index maps to:

  • - 1-15: Gel-based electrode recording
  • 16-30: Water-based electrode recording
  • 31-45: Dry electrode recording

Classification Results (from original paper)

Grand average peak accuracy on unseen test data:

  • - Gel-based: 61.3% (8.6% STD)
  • Water-based: 62.3% (9.2% STD)
  • Dry electrodes: 56.4% (8.0% STD)
Open in Overview tab →

Citation & Impact

Stimulus Protocol
../_images/BNCI2020_001.svg

5s task window per trial · 3-class motor imagery paradigm · 1 runs/session across 1 sessions

HED Event Tags
HED tags3/3 events annotated

Source: MOABB BIDS HED annotation mapping.

Sensory-event
3
Agent-action
2
Experimental-stimulus
1
Rest
1
Visual-presentation
1
palmar_grasp
Sensory-eventAgent-action
lateral_grasp
Sensory-eventAgent-action
rest
Sensory-eventExperimental-stimulusVisual-presentationRest

HED tree view

Tree · palmar_grasp
├─ Sensory-event
│  ├─ Experimental-stimulus
│  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      ├─ Grasp
      └─ Hand
Tree · lateral_grasp
├─ Sensory-event
│  ├─ Experimental-stimulus
│  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      ├─ Grasp
      ├─ Hand
      └─ Label
Tree · rest
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Rest
Channel Summary
Total channels58
EEG58 (Gel-based active electrodes)
EOG6
Montage5% grid system
Sampling256 Hz
Referenceright earlobe
Filter8th order Chebyshev filter from 0.01 to 100 Hz, 50 Hz notch
Notch / line50 Hz

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

BNCI 2020-001 Reach-and-Grasp Electrode Comparison dataset.

Dataset from [1].

Dataset Description

This dataset contains EEG data from 45 subjects (15 per electrode type) performing natural reach-and-grasp movements with different electrode systems. Three electrode types were compared:

  • Gel-based electrodes (g.tec g.USBamp system): 58 EEG + 6 EOG channels

  • Water-based electrodes (BitBrain EEG-Versatile): 32 EEG + 6 EOG channels

  • Dry electrodes (BitBrain EEG-Hero): 11 EEG channels (no EOG)

The study investigates the feasibility of decoding natural reach-and-grasp movements from EEG signals recorded with different electrode technologies, including mobile systems suitable for real-world applications.

Participants

  • 45 healthy able-bodied subjects (15 per electrode type)

  • All subjects performed the same experimental protocol

  • Each subject used only one electrode type

  • Location: Graz University of Technology, Austria (in collaboration with BitBrain, Spain)

Recording Details

  • Sampling rate: 256 Hz (all systems)

  • Reference: Earlobe (right for gel, left for water/dry)

  • Ground: AFz (gel/water), left earlobe (dry)

  • Filters: 0.3-100 Hz bandpass (3rd-4th order Butterworth)

Experimental Procedure

  • Self-paced reaching and grasping actions toward objects on a table

  • Two grasp types: palmar grasp (empty jar) and lateral grasp (spoon in jar)

  • Rest condition: Quiet sitting with fixation

  • 80 trials per grasp type distributed across 4 runs

  • Window of interest: [-2, 3] seconds relative to movement onset

Event Codes

  • palmar_grasp: Movement onset for palmar grasp (reaching to empty jar)

  • lateral_grasp: Movement onset for lateral grasp (reaching to jar with spoon)

  • rest: Onset of rest period

Electrode Types

Subjects are grouped by electrode type (15 per type). The subject index maps to:

  • 1-15: Gel-based electrode recording

  • 16-30: Water-based electrode recording

  • 31-45: Dry electrode recording

Classification Results (from original paper)

Grand average peak accuracy on unseen test data:

  • Gel-based: 61.3% (8.6% STD)

  • Water-based: 62.3% (9.2% STD)

  • Dry electrodes: 56.4% (8.0% STD)

References

[1]

Schwarz, A., Escolano, C., Montesano, L., & Muller-Putz, G. R. (2020). Analyzing and Decoding Natural Reach-and-Grasp Actions Using Gel, Water and Dry EEG Systems. Frontiers in Neuroscience, 14, 849. https://doi.org/10.3389/fnins.2020.00849

from moabb.datasets import BNCI2020_001
dataset = BNCI2020_001()
data = dataset.get_data(subjects=[1])
print(data[1])

Dataset summary

#Subj

15

#Chan

varies (11-64)

#Classes

3

#Trials / class

80

Trials length

5 s

Freq

256 Hz

#Sessions

3

#Runs

4

Total_trials

7200

Participants

  • Population: healthy

  • Handedness: right-handed

Equipment

  • Amplifier: g.tec USBamp/g.tec Ladybird

  • Electrodes: Gel-based active electrodes

  • Montage: 5% grid system

  • Reference: right earlobe

Preprocessing

  • Data state: raw

  • Bandpass filter: 0.3-60 Hz

  • Steps: zero-phase 4th order Butterworth bandpass filter (0.3-60 Hz), extended infomax ICA for eye artifact removal, artifact rejection by amplitude threshold (>125 µV), artifact rejection by abnormal joint probability (4 SD threshold), artifact rejection by abnormal kurtosis (4 SD threshold)

  • Re-reference: CAR

  • Notes: Preprocessing applied during analysis, not to raw data. For gel-based and water-based recordings, extended infomax ICA algorithm was applied on all available EEG and EOG channels. ICA was not applied to dry-electrode recordings due to unfavorable number of channels (n=11).

Data Access

Experimental Protocol

  • Paradigm: imagery

  • Task type: reach-and-grasp

  • Tasks: reach-and-grasp toward jar (palmar grasp), reach-and-grasp toward spoon (lateral grasp)

  • Feedback: visual (screen showing number of completed grasps)

  • Stimulus: physical objects (jar, spoon)

Notes

Added in version 1.3.0.

This dataset is valuable for comparing electrode technologies in naturalistic movement paradigms. Data is available under CC BY 4.0 license.

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

Return paths to data files for a single subject.

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