EEGdash›NeMAR›NM000214

Iss. 214 · 30 subjects · 150 recordings · CC0-1.0

Dataset Brief · c-VEP dataset from Thielen et al. (2021)

NM000214: eeg dataset, 30 subjects#

c-VEP dataset from Thielen et al. (2021)

Citation: J Thielen, P Marsman, J Farquhar, P Desain (2021). c-VEP dataset from Thielen et al. (2021).

30-participant EEG dataset — c-VEP dataset from Thielen et al. (2021).

Data & curation J Thielen · P Marsman · J Farquhar · P Desain
Year 2021 · Distributed via NeMAR
Funding NWO/TTW Takeoff Grant No. 14054 · International ALS Association and Dutch ALS Foundation Grant Nos. ATC20610 and 2017-57

EEG · 8 ch512 HzBIDS 1.9.0Task · cvepHealthyVisualPerception

Layer 01Study

What was asked

Hypothesis, independent & dependent variables, paradigm, cohort, and the editorial caveats around what the recordings can and cannot answer.

Layer 02Signal · BIDS

What was recorded

Sidecars, channels & electrodes, coordinate system, event semantics, and quality stats from the NEMAR pipeline when available.

Layer 03Training · ML

What you can train on

Recommended access modes — MNE Raw, braindecode windows, PyTorch DataLoader — plus the targets the metadata makes addressable.

§ 01Access · Get started

Quickstart#

Get Started

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000214

dataset = NM000214(cache_dir="./data")
# Get the raw object of the first recording
raw = dataset.datasets[0].raw
print(raw.info)

Query & Filter

Filter by subject

dataset = NM000214(cache_dir="./data", subject="01")

Advanced query

dataset = NM000214(
    cache_dir="./data",
    query={"subject": {"$in": ["01", "02"]}},
)

Iterate recordings

for rec in dataset:
    print(rec.subject, rec.raw.info['sfreq'])

Cite This Dataset

If you use this dataset in your research, please cite the original authors.

BibTeX

@dataset{nm000214,
  title = {c-VEP dataset from Thielen et al. (2021)},
  author = {J Thielen and P Marsman and J Farquhar and P Desain},
}

§ 02Study · The README

About This Dataset#

c-VEP dataset from Thielen et al. (2021)

Schema: HED 8.4.0 | Browse: https://www.hedtags.org/hed-schema-browser

c-VEP dataset from Thielen et al. (2021)

1.0

├─ Sensory-event
├─ Experimental-stimulus

View full README

c-VEP dataset from Thielen et al. (2021)

1.0

     ├─ Sensory-event
     ├─ Experimental-stimulus
     ├─ Visual-presentation
     └─ Label/intensity_1_0

0.0

├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label/intensity_0_0

Paradigm-Specific Parameters

Detected paradigm: cvep
Code type: modulated Gold codes
Code length: 126
Number of targets: 20

Data Structure

Trials: 100
Blocks per session: 5
Trials context: per_subject (5 blocks × 20 trials each)

Preprocessing

Data state: raw
Preprocessing applied: False

Signal Processing

Classifiers: template-matching, reconvolution, CCA
Feature extraction: encoding model, event responses, spatio-temporal
Spatial filters: CCA

Cross-Validation

Method: cross-validation
Folds: 5
Evaluation type: within_session, transfer_learning, zero_training

Performance (Original Study)

High Communication Rates: achieved in online spelling task

BCI Application

Applications: speller
Environment: indoor
Online feedback: False

Tags

Pathology: Healthy
Modality: Visual
Type: Research

Documentation

DOI: 10.1088/1741-2552/abecef
Associated paper DOI: 10.1088/1741-2552/ab4057
License: CC0-1.0
Investigators: J Thielen, P Marsman, J Farquhar, P Desain
Senior author: P Desain
Contact: jordy.thielen@donders.ru.nl
Institution: Radboud University
Department: Donders Institute for Brain, Cognition and Behaviour
Country: NL
Repository: Radboud
Data URL: https://doi.org/10.34973/9txv-z787
Publication year: 2021
Funding: NWO/TTW Takeoff Grant No. 14054; International ALS Association and Dutch ALS Foundation Grant Nos. ATC20610 and 2017-57
Ethics approval: Approved by the local ethical committee of the Faculty of Social Sciences of Radboud University
Keywords: brain–computer interface (BCI), electroencephalography (EEG), code-modulated visual evoked potentials (cVEPs), reconvolution, zero training, spread spectrum communication

External Links

Source: https://doi.org/10.34973/9txv-z787

Abstract

Objective. Typically, a brain–computer interface (BCI) is calibrated using user- and session-specific data because of the individual idiosyncrasies and the non-stationary signal properties of the electroencephalogram (EEG). Therefore, it is normal for BCIs to undergo a time-consuming passive training stage that prevents users from directly operating them. In this study, we systematically reduce the training data set in a stepwise fashion, to ultimately arrive at a calibration-free method for a code-modulated visually evoked potential (cVEP)-based BCI to fully eliminate the tedious training stage. Approach. In an extensive offline analysis, we compare our sophisticated encoding model with a traditional event-related potential (ERP) technique. We calibrate the encoding model in a standard way, with data limited to a single class while generalizing to all others and without any data. In addition, we investigate the feasibility of the zero-training cVEP BCI in an online setting. Main results. By adopting the encoding model, the training data can be reduced substantially, while maintaining both the classification performance as well as the explained variance of the ERP method. Moreover, with data from only one class or even no data at all, it still shows excellent performance. In addition, the zero-training cVEP BCI achieved high communication rates in an online spelling task, proving its feasibility for practical use. Significance. To date, this is the fastest zero-training cVEP BCI in the field, allowing high communication speeds without calibration while using only a few non-invasive water-based EEG electrodes. This allows us to skip the training stage altogether and spend all the valuable time on direct operation. This minimizes the session time and opens up new exciting directions for practical plug-and-play BCI. Fundamentally, these results validate that the adopted neural encoding model compresses data into event responses without the loss of explanatory power compared to using full ERPs as a template.

Methodology

The study compared four training regimes: (1) e-train: traditional ERP template-matching with data from all classes, (2) n-train: encoding model (reconvolution) with data from all n classes, (3) 1-train: encoding model with data from only one class while generating templates for all sequences, (4) 0-train: zero-training encoding model requiring no calibration data. Offline experiment: 30 participants completed 5 blocks of 20 trials each (100 trials total), with 31.5 s trials using a 4×5 calculator grid (n=20 symbols). Stimuli were luminance-modulated pseudo-random Gold codes (126-bit sequences, 2.1 s duration) presented on an iPad Pro at 60 Hz. Online experiment: 11 participants (9 analyzed) used a keyboard layout (n=29 symbols) with dynamic stopping rule for spelling tasks. EEG recorded at 512 Hz from 8 electrodes, preprocessed with 2-30 Hz Butterworth filtering and downsampled to 120 Hz. Classification used template-matching with reconvolution encoding model that decomposes responses to sequences into linear sums of individual event responses.

References

Thielen, J. (Jordy), Pieter Marsman, Jason Farquhar, Desain, P.W.M. (Peter) (2023): From full calibration to zero training for a code-modulated visual evoked potentials brain computer interface. Version 3. Radboud University. (dataset). DOI: https://doi.org/10.34973/9txv-z787 Thielen, J., Marsman, P., Farquhar, J., & Desain, P. (2021). From full calibration to zero training for a code-modulated visual evoked potentials for brain–computer interface. Journal of Neural Engineering, 18(5), 056007. DOI: https://doi.org/10.1088/1741-2552/abecef Ahmadi, S., Borhanazad, M., Tump, D., Farquhar, J., & Desain, P. (2019). Low channel count montages using sensor tying for VEP-based BCI. Journal of Neural Engineering, 16(6), 066038. DOI: https://doi.org/10.1088/1741-2552/ab4057 Notes .. versionadded:: 0.6.0 Appelhoff, S., Sanderson, M., Brooks, T., Vliet, M., Quentin, R., Holdgraf, C., Chaumon, M., Mikulan, E., Tavabi, K., Hochenberger, R., Welke, D., Brunner, C., Rockhill, A., Larson, E., Gramfort, A. and Jas, M. (2019). MNE-BIDS: Organizing electrophysiological data into the BIDS format and facilitating their analysis. Journal of Open Source Software 4: (1896). https://doi.org/10.21105/joss.01896 Pernet, C. R., Appelhoff, S., Gorgolewski, K. J., Flandin, G., Phillips, C., Delorme, A., Oostenveld, R. (2019). EEG-BIDS, an extension to the brain imaging data structure for electroencephalography. Scientific Data, 6, 103. https://doi.org/10.1038/s41597-019-0104-8 Generated by MOABB 1.5.0 (Mother of All BCI Benchmarks) NeuroTechX/moabb

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Age distribution by gender (n=30, range 25–25 yr, mean 25.0 yr)

25

Other · 30

Channel counts: 8 ch (n=150 recordings)

Sampling frequencies: 512.0 Hz (n=150 recordings)

Total recording duration: 27 h

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 8 ch · EEG · 512 Hz · 30 subjects, 150 recordings

Live trace viewer — sub-13 · ses-0 · task-cvep · run-4

Showing one representative recording out of 30 subjects and 150 recordings in this dataset. Browse the full set on OpenNeuro; drop any other _eeg.{set,edf,bdf,vhdr} file onto the viewer (or pass ?eeg=<url>) to inspect it.

Electrode layout — EEG · 8 sensors — 8 channels

NEMAR Processing Statistics#

The plots below are generated by NEMAR’s automated EEG pipeline. The histogram shows pipeline success for data cleaning and ICA decomposition, the percentage of data frames and EEG channels retained after artefact removal, line noise per channel (RMS, dB), and the age/gender distribution of participants.

HED event descriptors word cloud

§ 05Manifest · BIDS tree

Manifest#

File Explorer#

Browse the BIDS file structure of this dataset. Records are fetched on demand from the EEGDash catalog the first time you open the explorer.

Recordings—

Files—

Subjects—

Modalities—

Click to load file structure…

§ 06API · Programmatic access

API Reference#

Signature

eegdash.dataset

class

eegdash.dataset.NM000214(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)Thielen2021

Canonical—

Importable asNM000214 · Thielen2021

Sourceeegdash/dataset/registry.py · [source ↗]

class eegdash.dataset.NM000214(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

c-VEP dataset from Thielen et al. (2021)

Study:: nm000214 (NeMAR)
Author (year):: Thielen2021
Canonical:: —

Also importable as: NM000214, Thielen2021.

Modality: eeg; Experiment type: Perception; Subject type: Healthy. Subjects: 30; recordings: 150; tasks: 1.

Parameters:

cache_dir (str | Path) – Directory where data are cached locally.
query (dict | None) – Additional MongoDB-style filters to AND with the dataset selection. Must not contain the key dataset.
s3_bucket (str | None) – Base S3 bucket used to locate the data.
**kwargs (dict) – Additional keyword arguments forwarded to EEGDashDataset.

data_dir#

Local dataset cache directory (cache_dir / dataset_id).

Type:: Path

query#

Merged query with the dataset filter applied.

Type:: dict

records#

Metadata records used to build the dataset, if pre-fetched.

Type:: list[dict] | None

Notes

Each item is a recording; recording-level metadata are available via dataset.description. query supports MongoDB-style filters on fields in ALLOWED_QUERY_FIELDS and is combined with the dataset filter. Dataset-specific caveats are not provided in the summary metadata.

References

OpenNeuro dataset: https://openneuro.org/datasets/nm000214 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000214

Examples

>>> from eegdash.dataset import NM000214
>>> dataset = NM000214(cache_dir="./data")
>>> recording = dataset[0]
>>> raw = recording.load()

__init__(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

save(path: str, overwrite: bool = False, offset: int = 0)[source]#

Save datasets to files by creating one subdirectory for each dataset:

path/
    0/
        0-raw.fif | 0-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)
    1/
        1-raw.fif | 1-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)

Parameters:

path (str) –

Directory in which subdirectories are created to store
-raw.fif | -epo.fif and .json files to.
overwrite (bool) – Whether to delete old subdirectories that will be saved to in this call.
offset (int) – If provided, the integer is added to the id of the dataset in the concat. This is useful in the setting of very large datasets, where one dataset has to be processed and saved at a time to account for its original position.

Access modesMNE → braindecode → PyTorch → ML

.rawMNE Raw object — standard tools (filter, epoch, ICA, plot_psd).mne

BaseConcatDatasetEach record is a lazy BaseDataset from braindecode — windowed via create_windows_from_events.braindecode

DataLoaderWraps the windowed dataset into a PyTorch DataLoader; supports parallel workers and on-the-fly augmentations.pytorch

Zarr cacheOptional braindecode Zarr mirror for fast resume; persisted to cache_dir.zarr

Hugging FaceNo per-dataset mirror published yet — browse the EEGDash org listing for sibling datasets. See the datasets loader API.huggingface

Croissant 1.0Machine-readable JSON-LD descriptor — NM000214.croissant.json (MLCommons schema, ingestible by PyTorch / TensorFlow / JAX).mlcommons

Examples using EEGDashcurated · start here

Find datasets with the EEGDash APIQuery the catalogue, filter by task or modality, list candidates.

Load one EEG recordingResolve a single record to an MNE Raw with channels and events.

EEG recording to PyTorch DataLoaderWrap braindecode windows in a DataLoader for model training.

Preprocess EEG and create windowsFilter, resample, epoch — and persist the windowed dataset.

Save and reload prepared dataCache a windowed dataset to disk and reattach it without recompute.

Download a dataset locallyPrefetch BIDS files to a local cache and validate the layout.

Swap any load_dataset(...) call for nm000214 to reproduce the tutorial on this dataset.

Citation

J Thielen, P Marsman, J Farquhar, P Desain (2021). c-VEP dataset from Thielen et al. (2021).

Provenance

¹Contributed to nemar in BIDS format.

²Curated & ingested by the EEGDash catalog; see CITATION.cff for canonical reference.

Related & sibling datasets

NM000216EEG · 43 subj NM000122EEG · 12 subj NM000313EEG · 24 subj NM000126EEG · 34 subj NM000176EEG · 5 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC0-1.0 · DOI not on file

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000214`
Title	c-VEP dataset from Thielen et al. (2021)
Author (year)	`Thielen2021`
Canonical	—
Importable as	`NM000214`, `Thielen2021`
Year	2021
Authors	J Thielen, P Marsman, J Farquhar, P Desain
License	CC0-1.0
Citation / DOI	Unknown
Source links	OpenNeuro \| NeMAR \| Source URL

NM000214: eeg dataset, 30 subjects#

Quickstart#

About This Dataset#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#