moabb.datasets.Zhang2017#

class moabb.datasets.Zhang2017(subjects=None, sessions=None, *, return_all_modalities=False)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

Zhang2017

Motor Imagery, 10 classes

AuthorsXin Zhang, Xinyi Yong, Carlo Menon

🇨🇦 Simon Fraser University, CA·2017
Motor Imagery Code: Zhang2017 12 subjects 1 session 17 ch 1000 Hz 10 classes 5.0 s trials CC BY 4.0

Class Labels: rest, elbow_flexion, drawer, soup, weight_lifting, door, plate_cleaning, combing, ...

Read Paper Compare Similar Report Issue

Overview

Upper-limb elbow-centered motor imagery dataset (10 classes).

Dataset from

This dataset contains 32-channel EEG recordings from 12 healthy subjects (10 male, 2 female, ages 20-33, 11 right-handed) performing 10 motor imagery tasks involving the dominant upper limb. Data was recorded using a 32-channel EGI Geodesic Sensor Net (N400 series) at 1000 Hz with Cz reference, using BCI2000 in Stimulus Presentation mode.

The 10 tasks are:

  • - rest: stay alert, look at center cross
  • elbow_flexion: simple elbow flexion/extension
  • drawer: opening/closing a drawer
  • soup: spoon-feeding (drinking soup with a spoon)
  • weight_lifting: lifting/lowering a dumbbell
  • door: opening/closing a door
  • plate_cleaning: plate-cleaning movements
  • combing: hair-combing
  • pizza_cutting: pizza-cutting motions
  • pick_and_place: picking a ball into a basket

Each subject completed 15 runs (~3 minutes each). Each run contained 24 trials: 4 rest + 4 elbow + 2 each of the 8 goal-directed tasks. Trial timing: 4-6 s cue display (randomized) with MI, then 4-6 s rest. Total: 60 rest trials + 30 trials per MI task = 330 trials per subject.

The dataset is distributed as a single RAR archive on Figshare. Extraction requires unrar, unar, or 7z to be installed on the system. The BCI2000 .dat files are read using the BCI2kReader package (pip install BCI2kReader).

Open in Overview tab →

Citation & Impact

Stimulus Protocol
../_images/Zhang2017.svg

5s task window per trial · 10-class motor imagery paradigm · 15 runs/session across 1 sessions

HED Event Tags
HED tags10/10 events annotated

Source: MOABB BIDS HED annotation mapping.

Sensory-event
10
Label
9
Experimental-stimulus
1
Rest
1
Visual-presentation
1
rest
Sensory-eventExperimental-stimulusVisual-presentationRest
elbow_flexion
Sensory-eventLabel
drawer
Sensory-eventLabel
soup
Sensory-eventLabel
weight_lifting
Sensory-eventLabel
door
Sensory-eventLabel
plate_cleaning
Sensory-eventLabel
combing
Sensory-eventLabel
pizza_cutting
Sensory-eventLabel
pick_and_place
Sensory-eventLabel

HED tree view

Tree · rest
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Rest
Tree · elbow_flexion
├─ Sensory-event
└─ Label
Tree · drawer
├─ Sensory-event
└─ Label
Tree · soup
├─ Sensory-event
└─ Label
Tree · weight_lifting
├─ Sensory-event
└─ Label
Tree · door
├─ Sensory-event
└─ Label
Tree · plate_cleaning
├─ Sensory-event
└─ Label
Tree · combing
├─ Sensory-event
└─ Label
Tree · pizza_cutting
├─ Sensory-event
└─ Label
Tree · pick_and_place
├─ Sensory-event
└─ Label
Channel Summary
Total channels17
EEG17 (Ag/AgCl sponge)
Sampling1000 Hz
ReferenceCz
Filter{'bandpass': [0.1, 40]}
Notch / line60 Hz

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

Upper-limb elbow-centered motor imagery dataset (10 classes).

Dataset from [1].

This dataset contains 32-channel EEG recordings from 12 healthy subjects (10 male, 2 female, ages 20-33, 11 right-handed) performing 10 motor imagery tasks involving the dominant upper limb. Data was recorded using a 32-channel EGI Geodesic Sensor Net (N400 series) at 1000 Hz with Cz reference, using BCI2000 in Stimulus Presentation mode.

The 10 tasks are:

  • rest: stay alert, look at center cross

  • elbow_flexion: simple elbow flexion/extension

  • drawer: opening/closing a drawer

  • soup: spoon-feeding (drinking soup with a spoon)

  • weight_lifting: lifting/lowering a dumbbell

  • door: opening/closing a door

  • plate_cleaning: plate-cleaning movements

  • combing: hair-combing

  • pizza_cutting: pizza-cutting motions

  • pick_and_place: picking a ball into a basket

Each subject completed 15 runs (~3 minutes each). Each run contained 24 trials: 4 rest + 4 elbow + 2 each of the 8 goal-directed tasks. Trial timing: 4-6 s cue display (randomized) with MI, then 4-6 s rest. Total: 60 rest trials + 30 trials per MI task = 330 trials per subject.

The dataset is distributed as a single RAR archive on Figshare. Extraction requires unrar, unar, or 7z to be installed on the system. The BCI2000 .dat files are read using the BCI2kReader package (pip install BCI2kReader).

References

[1]

X. Zhang, X. Yong, and C. Menon, “Evaluating the versatility of EEG models generated from motor imagery tasks: An exploratory investigation on upper-limb elbow-centered motor imagery tasks,” PLoS ONE, vol. 12, no. 11, e0188293, 2017. DOI: 10.1371/journal.pone.0188293

from moabb.datasets import Zhang2017
dataset = Zhang2017()
data = dataset.get_data(subjects=[1])
print(data[1])

Dataset summary

#Subj

12

#Chan

17

#Classes

10

#Trials / class

30

Trials length

4 s

Freq

1000 Hz

#Sessions

1

#Runs

15

Total_trials

4321

Participants

  • Population: healthy

  • Handedness: {‘right’: 11, ‘left’: 1}

  • BCI experience: naive

Equipment

  • Amplifier: EGI Geodesic Net Amps 400 series (N400)

  • Electrodes: Ag/AgCl sponge

  • Reference: Cz

Preprocessing

  • Data state: raw

Data Access

Experimental Protocol

  • Paradigm: imagery

  • Feedback: none

  • Stimulus: picture cues

Notes

Subject H5 is left-handed; all other subjects are right-handed. In the paper’s analysis, H5’s channels were flipped between hemispheres. This adapter does NOT apply any hemisphere flipping.

Only 17 of the 32 channels were used in the paper’s analysis (facial channels excluded). The raw data contains all 32 channels.

__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)[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 list of BCI2000 .dat file paths for a subject.

Downloads and extracts the KI.rar archive from Figshare if needed.

Parameters:

  • subject (int) – Subject number (1-12).

  • path (str or None) – Download destination. Defaults to MNE_DATA.

  • force_update (bool) – Re-download even if local files exist.

  • update_path (ignored) – Kept for API compatibility.

  • verbose (ignored) – Kept for API compatibility.

Returns:

Paths to BCI2000 .dat files for this subject, sorted.

Return type:

list of str

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) → 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 “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: 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