moabb.datasets.Tavakolan2017#

class moabb.datasets.Tavakolan2017(subjects=None, sessions=None, *, return_all_modalities=False)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

Tavakolan2017

Motor Imagery, 3 classes (rest vs right_hand vs right_elbow_flexion)

AuthorsMojgan Tavakolan, Zack Frehlick, Xinyi Yong, Carlo Menon

🇨🇦 Simon Fraser University, CA·2017

Motor Imagery Code: Tavakolan2017 12 subjects 4 sessions 32 ch 1000 Hz 3 classes 3.0 s trials CC0 1.0

Class Labels: rest, right_hand, right_elbow_flexion

Read Paper Compare Similar Report Issue

Overview

Motor imagery dataset for three imaginary states of the same upper extremity.

Dataset from

This dataset contains 32-channel EEG recordings from 12 healthy subjects performing motor imagery of the right upper extremity. Subjects imagined three tasks: rest, grasping (opening/closing fingers to grab an object), and elbow flexion/extension (moving the forearm up and down).

EEG was recorded at 1000 Hz using a 32-channel EGI Geodesic Sensor Net (GES 400 series amplifier) with Cz as the online reference. Each subject completed 4 sessions on separate days, with 20 trials per class per session (80 trials total per session, 4 classes).

Each trial consisted of a 3 s visual cue (during which the subject performed the imagery) followed by a 4-6 s rest interval. The imagery interval [0, 3] s after cue onset is used for analysis.

The data was originally deposited on the Dryad Digital Repository and has been re-hosted on Zenodo for direct programmatic access.

Open in Overview tab →

Citation & Impact

Paper DOI10.1371/journal.pone.0174161
CitationsLoading…
Public APICrossref | OpenAlex

Stimulus Protocol

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

rest

Sensory-eventExperimental-stimulusVisual-presentationRest

right_hand

Sensory-eventAgent-action

right_elbow_flexion

Sensory-eventAgent-action

HED tree view

Tree · rest

├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Rest

Tree · right_hand

├─ Sensory-event
│  ├─ Experimental-stimulus
│  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      ├─ Move
      └─ Right
         └─ Hand

Tree · right_elbow_flexion

├─ Sensory-event
│  ├─ Experimental-stimulus
│  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      ├─ Flex
      └─ Right
         └─ Elbow

Channel Summary

Total channels32

EEG32 (Ag/AgCl sponge)

MontageGSN-HydroCel-32

Sampling1000 Hz

ReferenceCz

Filter{'bandpass': [0.1, 100]}

Notch / line60 Hz

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

Overview

Motor imagery dataset for three imaginary states of the same upper extremity.

Dataset from [1].

This dataset contains 32-channel EEG recordings from 12 healthy subjects performing motor imagery of the right upper extremity. Subjects imagined three tasks: rest, grasping (opening/closing fingers to grab an object), and elbow flexion/extension (moving the forearm up and down).

EEG was recorded at 1000 Hz using a 32-channel EGI Geodesic Sensor Net (GES 400 series amplifier) with Cz as the online reference. Each subject completed 4 sessions on separate days, with 20 trials per class per session (80 trials total per session, 4 classes).

Each trial consisted of a 3 s visual cue (during which the subject performed the imagery) followed by a 4-6 s rest interval. The imagery interval [0, 3] s after cue onset is used for analysis.

The data was originally deposited on the Dryad Digital Repository [2] and has been re-hosted on Zenodo for direct programmatic access.

Note

Reading BCI2000 .DAT files requires the BCI2kReader package:

pip install BCI2kReader

References

[1]

M. Tavakolan, Z. Frehlick, X. Yong, and C. Menon, “Classifying three imaginary states of the same upper extremity using time-domain features,” PLoS ONE, vol. 12, no. 3, e0174161, 2017. DOI: 10.1371/journal.pone.0174161

[2]

M. Tavakolan, Z. Frehlick, X. Yong, and C. Menon, “Data from: Classifying three imaginary states of the same upper extremity using time-domain features,” Dryad, 2017. DOI: 10.5061/dryad.6qs86

Code Examples

from moabb.datasets import Tavakolan2017
dataset = Tavakolan2017()
data = dataset.get_data(subjects=[1])
print(data[1])

Metadata

Dataset summary

#Subj	12
#Chan	32
#Classes	3
#Trials / class	20
Trials length	3 s
Freq	1000 Hz
#Sessions	4
#Runs	1
Total_trials	2880

Participants

Population: healthy

Equipment

Amplifier: EGI Geodesic Net Amps 400 series
Electrodes: Ag/AgCl sponge
Montage: GSN-HydroCel-32
Reference: Cz

Preprocessing

Data state: continuous

Data Access

DOI: 10.1371/journal.pone.0174161
Data URL: https://zenodo.org/records/18967205
Repository: Zenodo

Experimental Protocol

Paradigm: imagery
Feedback: none
Stimulus: visual cue

Notes

The original channel labels follow the EGI HydroCel Geodesic Sensor Net naming convention (E1-E32 plus Cz reference). The GSN-HydroCel-32 montage from MNE is applied.

The raw BCI2000 files contain 280 source channels; only the first 32 are EEG. Channels are scaled from raw ADC units to volts using the gain from the BCI2000 header (0.0238419 µV per count).

The BCI2000 files actually contain four stimulus classes (Rest, Wrist, Elbow, Reach-Hold the Glass) with StimulusCodes 1-4. Following the paper’s analysis of three classes, only codes 1-3 are mapped to events by default.

__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

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