EEGdash›NeMAR›NM000264

Iss. 264 · 24 subjects · 292 recordings · CC-BY-1.0

Dataset Brief · Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive v…

NM000264: eeg dataset, 24 subjects#

Name: Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a)
Published: 2019-01-01
License: CC-BY-1.0

Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a)

Citation: E. Vaineau, A. Barachant, A. Andreev, P. Rodrigues, G. Cattan, M. Congedo (2019). Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a). 10.5281/zenodo.1494163

24-participant EEG dataset — Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a).

Data & curation E. Vaineau · A. Barachant · A. Andreev · P. Rodrigues · G. Cattan · M. Congedo
Year 2019 · Distributed via NeMAR

EEG · 16 ch512 HzBIDS 1.9.0Task · p3008 sessionsHealthyVisualAttention

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 NM000264

dataset = NM000264(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 = NM000264(cache_dir="./data", subject="01")

Advanced query

dataset = NM000264(
    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{nm000264,
  title = {Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a)},
  author = {E. Vaineau and A. Barachant and A. Andreev and P. Rodrigues and G. Cattan and M. Congedo},
  doi = {10.5281/zenodo.1494163},
  url = {https://doi.org/10.5281/zenodo.1494163},
}

§ 02Study · The README

About This Dataset#

P300 dataset BI2013a from a “Brain Invaders” experiment.

Code: BrainInvaders2013a

Paradigm: p300 DOI: https://doi.org/10.5281/zenodo.2669187 Subjects: 24 Sessions per subject: 8 Events: Target=33285, NonTarget=33286 Trial interval: [0, 1] s Runs per session: 2 File format: mat, csv, gdf Contributing labs: GIPSA-lab

BrainInvaders2013a

Acquisition

Sampling rate: 512.0 Hz Number of channels: 16 Channel types: eeg=16 Channel names: Fp1, Fp2, F5, AFz, F6, T7, Cz, T8, P7, P3, Pz, P4, P8, O1, Oz, O2 Montage: standard_1020 Hardware: g.USBamp (g.tec, Schiedlberg, Austria)
View full README
BrainInvaders2013a

Acquisition

Sampling rate: 512.0 Hz Number of channels: 16 Channel types: eeg=16 Channel names: Fp1, Fp2, F5, AFz, F6, T7, Cz, T8, P7, P3, Pz, P4, P8, O1, Oz, O2 Montage: standard_1020 Hardware: g.USBamp (g.tec, Schiedlberg, Austria) Software: OpenVibe Reference: left earlobe Ground: FZ Sensor type: wet Silver/Silver Chloride electrodes Line frequency: 50.0 Hz Online filters: no digital filter applied Cap manufacturer: g.tec Cap model: g.GAMMAcap Electrode type: wet Electrode material: Silver/Silver Chloride

Participants

Number of subjects: 24 Health status: healthy Age: mean=25.96, std=4.46, min=20.0, max=30.0 Gender distribution: male=12, female=12 BCI experience: volunteers recruited via flyers and university mailing list Species: human

Experimental Protocol

Paradigm: p300 Task type: visual P300 BCI Number of classes: 2 Class labels: Target, NonTarget Study design: compare P300-based BCI with and without adaptive calibration using Riemannian geometry; randomised order of runs (adaptive vs non-adaptive) Feedback type: visual (Brain Invaders video game interface) Stimulus type: visual flashes Stimulus modalities: visual Primary modality: visual Mode: both Training/test split: True Instructions: destroy targets in Brain Invaders BCI video game Stimulus presentation: distance_from_screen=75 to 115 cm, screen=ViewSonic 22 inch, flash_groups=36 symbols distributed in 12 groups

HED Event Annotations

Schema: HED 8.4.0 | Browse: https://www.hedtags.org/hed-schema-browser Target
     ├─ Sensory-event
     ├─ Experimental-stimulus
     ├─ Visual-presentation
     └─ Target

NonTarget
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Non-target
Paradigm-Specific Parameters

Detected paradigm: p300

Data Structure

Trials: {‘Training_Target’: 80, ‘Training_non-Target’: 400, ‘Online’: ‘variable (depends on user performance)’} Trials context: per_phase

Preprocessing

Data state: raw EEG with software tagging via USB (note: tagging introduces jitter and latency) Preprocessing applied: False Notes: Tags sent by application to amplifier through USB port and recorded as supplementary channel; tagging process identical in all experimental conditions

Signal Processing

Classifiers: xDAWN, Riemannian, RMDM (Riemannian Minimum Distance to Mean) Feature extraction: Covariance/Riemannian, xDAWN, common spatiotemporal pattern

Cross-Validation

Evaluation type: cross_session

Performance (Original Study)

Balanced Accuracy: used due to unbalanced classes (1:5 ratio Target to non-Target)

BCI Application

Applications: gaming Environment: small room (4 square meters) with one-way glass window for experimenter observation Online feedback: True

Tags

Pathology: Healthy Modality: Visual Type: Perception

Documentation

Description: EEG recordings of 24 subjects doing a visual P300 Brain-Computer Interface experiment comparing adaptive vs non-adaptive calibration using Riemannian geometry DOI: 10.5281/zenodo.1494163 Associated paper DOI: 10.5281/zenodo.2649006 License: CC-BY-1.0 Investigators: E. Vaineau, A. Barachant, A. Andreev, P. Rodrigues, G. Cattan, M. Congedo Senior author: M. Congedo Institution: GIPSA-lab, CNRS, University Grenoble-Alpes, Grenoble INP Address: GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402, France Country: FR Repository: Zenodo Data URL: https://doi.org/10.5281/zenodo.1494163 Publication year: 2019 Ethics approval: Approved by the Ethical Committee of the University of Grenoble Alpes (Comité d’Ethique pour la Recherche Non-Interventionnelle) Keywords: Electroencephalography (EEG), P300, Brain-Computer Interface, Experiment, Adaptive, Calibration

Abstract

This dataset contains electroencephalographic (EEG) recordings of 24 subjects doing a visual P300 Brain-Computer Interface experiment on PC. The visual P300 is an event-related potential elicited by visual stimulation, peaking 240-600 ms after stimulus onset. The experiment was designed to compare the use of a P300-based brain-computer interface with and without adaptive calibration using Riemannian geometry. EEG data were recorded using 16 electrodes during an experiment at GIPSA-lab, Grenoble, France, in 2013.

Methodology

Subjects participated in sessions with two runs (Non-Adaptive and Adaptive, randomised order). Each run had Training (calibration) and Online phases. In Non-Adaptive mode, Training data calibrated the MDM classifier for Online phase. In Adaptive mode, classifier initialized with generic class geometric means from previous experiment and continuously adapted using Riemannian method. Brain Invaders interface: 36 symbols in 12 groups, one repetition = 12 flashes (2 Target, 10 non-Target). Training phase: 80 Target and 400 non-Target flashes (fixed). Online phase: variable repetitions based on performance to destroy targets. Subjects blind to mode of operation.

References

Vaineau, E., Barachant, A., Andreev, A., Rodrigues, P. C., Cattan, G. & Congedo, M. (2019). Brain invaders adaptive versus non-adaptive P300 brain-computer interface dataset. arXiv preprint arXiv:1904.09111.

Barachant A, Congedo M (2014) A Plug & Play P300 BCI using Information Geometry. arXiv:1409.0107. Congedo M, Goyat M, Tarrin N, Ionescu G, Rivet B,Varnet L, Rivet B, Phlypo R, Jrad N, Acquadro M, Jutten C (2011) “Brain Invaders”: a prototype of an open-source P300-based video game working with the OpenViBE platform. Proc. IBCI Conf., Graz, Austria, 280-283.

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=24, range 26–26 yr, mean 25.0 yr)

25

Other · 24

Channel counts: 16 ch (n=292 recordings)

Sampling frequencies: 512.0 Hz (n=292 recordings)

Total recording duration: 20 h 37 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 16 ch · EEG · 512 Hz · 24 subjects, 292 recordings

Live trace viewer — sub-1 · ses-0 · task-p300 · run-0

Showing one representative recording out of 24 subjects and 292 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 · 16 sensors — 16 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.NM000264(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)BrainInvaders2013

Canonical—

Importable asNM000264 · BrainInvaders2013

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

class eegdash.dataset.NM000264(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a)

Study:: nm000264 (NeMAR)
Author (year):: BrainInvaders2013
Canonical:: —

Also importable as: NM000264, BrainInvaders2013.

Modality: eeg; Experiment type: Attention; Subject type: Healthy. Subjects: 24; recordings: 292; 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/nm000264 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000264 DOI: https://doi.org/10.5281/zenodo.1494163

Examples

>>> from eegdash.dataset import NM000264
>>> dataset = NM000264(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 — NM000264.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 nm000264 to reproduce the tutorial on this dataset.

Citation

E. Vaineau, A. Barachant, A. Andreev, P. Rodrigues, G. Cattan, … (2019). Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a). 10.5281/zenodo.1494163

Provenance

¹Contributed to nemar in BIDS format.

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

³Persistent identifier: 10.5281/zenodo.1494163.

Related & sibling datasets

NM000222EEG · 10 subj NM000277EEG · 20 subj NM000201EEG · 24 subj NM000301EEG · 17 subj NM000326EEG · 19 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC-BY-1.0 · 10.5281/zenodo.1494163

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000264`
Title	Vaineau, Barachant & Andreev 2013 — Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset (BI2013a)
Author (year)	`BrainInvaders2013`
Canonical	—
Importable as	`NM000264`, `BrainInvaders2013`
Year	2019
Authors	Vaineau, A. Barachant, A. Andreev, P. Rodrigues, G. Cattan, M. Congedo
License	CC-BY-1.0
Citation / DOI	doi:10.5281/zenodo.1494163
Source links	OpenNeuro \| NeMAR \| Source URL

NM000264: eeg dataset, 24 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#