moabb.datasets.Thielen2015#

class moabb.datasets.Thielen2015(subjects=None, sessions=None, *, return_all_modalities=False)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

Thielen2015

c-VEP, 2 classes (1.0 vs 0.0)

AuthorsJordy Thielen, Philip van den Broek, Jason Farquhar, Peter Desain

🇳🇱 Radboud University Nijmegen, NL·2015·jordy.thielen@gmail.com
c-VEP Code: Thielen2015 12 subjects 1 session 64 ch 2048 Hz 2 classes 4.2 s trials CC0 1.0

Class Labels: 1.0, 0.0

Read Paper Compare Similar Report Issue

Overview

c-VEP dataset from Thielen et al. (2015)

Dataset from the study on reconvolution for c-VEP

Dataset description

EEG recordings were obtained with a sampling rate of 2048 Hz, using a setup comprising 64 Ag/AgCl electrodes, and amplified by a Biosemi ActiveTwo EEG amplifier. Electrode placement followed the international 10-10 system.

During the experimental sessions, participants actively operated a 6 x 6 visual speller brain-computer interface (BCI) with real-time feedback, encompassing 36 distinct classes. Each cell within the symbol grid underwent luminance modulation at full contrast, achieved through the application of pseudo-random noise-codes derived from a set of modulated Gold codes. These binary codes have a balanced distribution of ones and zeros while adhering to a limited run-length pattern, with a maximum run-length of 2 bits. Codes were presented at a rate of 120 Hz. Given that one cycle of these modulated Gold codes comprises 126 bits, the duration of a complete cycle spans 1.05 seconds.

Throughout the experiment, participants underwent four distinct blocks: an initial practice block consisting of two runs, followed by a training block of one run. Subsequently, they engaged in a copy-spelling block comprising six runs, and finally, a free-spelling block consisting of one run. Between the training and copy-spelling block, a classifier was calibrated using data from the training block. This calibrated classifier was then applied during both the copy-spelling and free-spelling runs. Additionally, during calibration, the stimulation codes were tailored and optimized specifically for each individual participant.

Among the six copy-spelling runs, there were three fixed-length runs. Trials in these runs started with a cueing phase, where the target symbol was highlighted in a green hue for 1 second. Participants maintained their gaze fixated on the target symbol as all symbols flashed in sync with their corresponding pseudo-random noise-codes for a duration of 4.2 seconds (equivalent to 4 code cycles). Immediately following this stimulation, the output of the classifier was shown by coloring the cell blue for 1 second. Each run consisted of 36 trials, presented in a randomized order.

Here, our focus is solely on the three copy-spelling runs characterized by fixed-length trials lasting 4.2 seconds (equivalent to four code cycles). The other three runs utilized a dynamic stopping procedure, resulting in trials of varying durations, rendering them unsuitable for benchmarking purposes. Similarly, the practice and free-spelling runs included dynamic stopping and are ignored in this dataset. The training dataset, comprising 36 trials, used a different noise-code set, and is therefore also ignored in this dataset. In total, this dataset should contain 108 trials of 4.2 seconds each, with 3 repetitions for each of the 36 codes.

Open in Overview tab →

Citation & Impact

Stimulus Protocol
../_images/Thielen2015.svg

4.2s task window per trial · 2-class c-vep paradigm · 3 runs/session across 1 sessions

HED Event Tags
HED tags2/2 events annotated

Source: MOABB BIDS HED annotation mapping.

Experimental-stimulus
2
Label
2
Sensory-event
2
Visual-presentation
2
1.0
Sensory-eventExperimental-stimulusVisual-presentationLabel
0.0
Sensory-eventExperimental-stimulusVisual-presentationLabel

HED tree view

Tree · 1.0
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 0.0
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Channel Summary
Total channels64
EEG64 (EEG)
Montagestandard_1020
Sampling2048 Hz
ReferenceCMS/DRL
Notch / line50 Hz

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

c-VEP dataset from Thielen et al. (2015)

Dataset [1] from the study on reconvolution for c-VEP [2].

Dataset description

EEG recordings were obtained with a sampling rate of 2048 Hz, using a setup comprising 64 Ag/AgCl electrodes, and amplified by a Biosemi ActiveTwo EEG amplifier. Electrode placement followed the international 10-10 system.

During the experimental sessions, participants actively operated a 6 x 6 visual speller brain-computer interface (BCI) with real-time feedback, encompassing 36 distinct classes. Each cell within the symbol grid underwent luminance modulation at full contrast, achieved through the application of pseudo-random noise-codes derived from a set of modulated Gold codes. These binary codes have a balanced distribution of ones and zeros while adhering to a limited run-length pattern, with a maximum run-length of 2 bits. Codes were presented at a rate of 120 Hz. Given that one cycle of these modulated Gold codes comprises 126 bits, the duration of a complete cycle spans 1.05 seconds.

Throughout the experiment, participants underwent four distinct blocks: an initial practice block consisting of two runs, followed by a training block of one run. Subsequently, they engaged in a copy-spelling block comprising six runs, and finally, a free-spelling block consisting of one run. Between the training and copy-spelling block, a classifier was calibrated using data from the training block. This calibrated classifier was then applied during both the copy-spelling and free-spelling runs. Additionally, during calibration, the stimulation codes were tailored and optimized specifically for each individual participant.

Among the six copy-spelling runs, there were three fixed-length runs. Trials in these runs started with a cueing phase, where the target symbol was highlighted in a green hue for 1 second. Participants maintained their gaze fixated on the target symbol as all symbols flashed in sync with their corresponding pseudo-random noise-codes for a duration of 4.2 seconds (equivalent to 4 code cycles). Immediately following this stimulation, the output of the classifier was shown by coloring the cell blue for 1 second. Each run consisted of 36 trials, presented in a randomized order.

Here, our focus is solely on the three copy-spelling runs characterized by fixed-length trials lasting 4.2 seconds (equivalent to four code cycles). The other three runs utilized a dynamic stopping procedure, resulting in trials of varying durations, rendering them unsuitable for benchmarking purposes. Similarly, the practice and free-spelling runs included dynamic stopping and are ignored in this dataset. The training dataset, comprising 36 trials, used a different noise-code set, and is therefore also ignored in this dataset. In total, this dataset should contain 108 trials of 4.2 seconds each, with 3 repetitions for each of the 36 codes.

References

[1]

Thielen, J. (Jordy), Jason Farquhar, Desain, P.W.M. (Peter) (2023): Broad-Band Visually Evoked Potentials: Re(con)volution in Brain-Computer Interfacing. Version 2. Radboud University. (dataset). DOI: https://doi.org/10.34973/1ecz-1232

[2]

Thielen, J., Van Den Broek, P., Farquhar, J., & Desain, P. (2015). Broad-Band visually evoked potentials: re(con)volution in brain-computer interfacing. PLOS ONE, 10(7), e0133797. DOI: https://doi.org/10.1371/journal.pone.0133797

from moabb.datasets import Thielen2015
dataset = Thielen2015()
data = dataset.get_data(subjects=[1])
print(data[1])

Dataset summary

#Subj

12

#Chan

64

#Trials / class

3

Trials length

4.2 s

Freq

2048 Hz

#Sessions

1

#Trial classes

36

#Epochs classes

2

#Epochs / class

27216 NT / 27216 T

Codes

Gold codes

Presentation rate

120 Hz

Participants

  • Population: Healthy

  • Age: 24 years

  • BCI experience: naive

Equipment

  • Amplifier: Biosemi ActiveTwo

  • Electrodes: EEG

  • Montage: standard_1020

  • Reference: CMS/DRL

Preprocessing

  • Data state: preprocessed

  • Bandpass filter: 5-100 Hz

  • Steps: downsampling from 2048 Hz to 360 Hz, linear de-trending, common average referencing, spectral filtering

  • Re-reference: car

Data Access

Experimental Protocol

  • Paradigm: cvep

  • Feedback: visual

  • Stimulus: pseudo-random noise-code

Notes

Added in version 1.0.0.

__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 the data paths of 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) → 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