EEGdash›NeMAR›NM000203

Iss. 203 · 13 subjects · 800 recordings · CC-BY-SA-4.0

Dataset Brief · P300 dataset from initial spot study

NM000203: eeg dataset, 13 subjects#

P300 dataset from initial spot study

Citation: Jan Sosulski, David Hübner, Aaron Klein, Michael Tangermann (2019). P300 dataset from initial spot study.

13-participant EEG dataset — P300 dataset from initial spot study.

Data & curation Jan Sosulski · David Hübner · Aaron Klein · Michael Tangermann
Year 2019 · Distributed via NeMAR
Funding Cluster of Excellence BrainLinks-BrainTools funded by the German Research Foundation (DFG) [grant number EXC 1086] · DFG project SuitAble [grant number TA 1258/1-1] · + 1 more

EEG · 31 ch1000 HzBIDS 1.9.0Task · p300777 sessions

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 NM000203

dataset = NM000203(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 = NM000203(cache_dir="./data", subject="01")

Advanced query

dataset = NM000203(
    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{nm000203,
  title = {P300 dataset from initial spot study},
  author = {Jan Sosulski and David Hübner and Aaron Klein and Michael Tangermann},
}

§ 02Study · The README

About This Dataset#

P300 dataset from initial spot study.

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

P300 dataset from initial spot study

Target

├─ Sensory-event
├─ Experimental-stimulus

View full README

P300 dataset from initial spot study

Target

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

NonTarget

├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Non-target

Paradigm-Specific Parameters

Detected paradigm: p300
Number of targets: 1

Data Structure

Trials: Variable: optimization part used time-limited trials (20 minutes per strategy), validation part used 20 trials per SOA
Trials per class: target=13 per trial (after preprocessing, originally 15), non_target=65 per trial (after preprocessing, originally 75)
Trials context: Each trial consisted of 90 stimuli (15 target, 75 non-target). After preprocessing (removing first and last 6 epochs), 78 data points available per trial: 13 target and 65 non-target epochs.

Signal Processing

Classifiers: rLDA, Shrinkage LDA
Feature extraction: Mean amplitude in time intervals
Frequency bands: analyzed=[1.5, 40.0] Hz

Cross-Validation

Method: 13-fold
Folds: 13
Evaluation type: within_session

Performance (Original Study)

Auc: 0.701
Mean Auc Ucb: 0.701
Mean Auc Rand: 0.704
Mean Auc P300 Ucb: 0.67
Mean Auc P300 Rand: 0.681
Mean Auc Fixed60: 0.517

BCI Application

Applications: communication
Online feedback: False

Tags

Pathology: Healthy
Modality: Auditory
Type: Research

Documentation

Description: Auditory oddball ERP dataset from 13 healthy subjects. Two sinusoidal tones (target 1000 Hz, non-target 500 Hz) presented at various stimulus onset asynchronies (SOAs, 60-600 ms). 31-channel EEG recorded at 1000 Hz with BrainProducts BrainAmp DC. Raw BrainVision format data.
DOI: 10.48550/arXiv.2109.06011
License: CC-BY-SA-4.0
Investigators: Jan Sosulski, David Hübner, Aaron Klein, Michael Tangermann
Senior author: Michael Tangermann
Contact: jan.sosulski@blbt.uni-freiburg.de; davhuebn@gmail.com; kleinaa@cs.uni-freiburg.de; michael.tangermann@donders.ru.nl
Institution: University of Freiburg
Country: DE
Repository: FreiDok
Data URL: https://freidok.uni-freiburg.de/data/154576
Publication year: 2021
Funding: Cluster of Excellence BrainLinks-BrainTools funded by the German Research Foundation (DFG) [grant number EXC 1086]; DFG project SuitAble [grant number TA 1258/1-1]; state of Baden-Württemberg, Germany, through bwHPC and the German Research Foundation (DFG) [grant number INST 39/963-1 FUGG]
Ethics approval: Approved by the ethics committee of the university medical center of Freiburg
Acknowledgements: Experiments were performed according to the Declaration of Helsinki.
Keywords: Bayesian optimization, individual experimental parameters, brain-computer interfaces, learning from small data, auditory event-related potentials, closed-loop parameter optimization

Abstract

The decoding of brain signals recorded via, e.g., an electroencephalogram, using machine learning is key to brain-computer interfaces (BCIs). Stimulation parameters or other experimental settings of the BCI protocol typically are chosen according to the literature. The decoding performance directly depends on the choice of parameters, as they influence the elicited brain signals and optimal parameters are subject-dependent. Thus a fast and automated selection procedure for experimental parameters could greatly improve the usability of BCIs. We evaluate a standalone random search and a combined Bayesian optimization with random search into a closed-loop auditory event-related potential protocol. We aimed at finding the individually best stimulation speed—also known as stimulus onset asynchrony (SOA)—that maximizes the classification performance of a regularized linear discriminant analysis.

Methodology

The experiment was divided into two parts: (1) Optimization part: four strategies (AUC-ucb, AUC-rand, P300-ucb, P300-rand) each allocated 20 minutes to find optimal SOA. Strategies alternated to minimize non-stationarity effects. (2) Validation part: evaluated SOAs from each optimization strategy plus fixed 60ms SOA using 20 trials each (in blocks of 5 trials). Features were mean amplitudes in 5 time intervals ([100, 170], [171, 230], [231, 300], [301, 410], [411, 500] ms) across 31 channels (155 dimensions total). Classification used rLDA with automatic shrinkage regularization and 13-fold cross-validation on single trials.

References

Sosulski, J., Tangermann, M.: Electroencephalogram signals recorded from 13 healthy subjects during an auditory oddball paradigm under different stimulus onset asynchrony conditions. Dataset. DOI: 10.6094/UNIFR/154576 Sosulski, J., Tangermann, M.: Spatial filters for auditory evoked potentials transfer between different experimental conditions. Graz BCI Conference. 2019.

Sosulski, J., Hübner, D., Klein, A., Tangermann, M.: Online Optimization of Stimulation Speed in an Auditory Brain-Computer Interface under Time Constraints. arXiv preprint. 2021. Notes .. versionadded:: 0.4.5 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=13, range 23–23 yr, mean 22.0 yr)

20

Other · 13

Channel counts: 31 ch (n=800 recordings)

Sampling frequencies: 1000.0 Hz (n=800 recordings)

Total recording duration: 8 h 54 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 31 ch · EEG · 1000 Hz · 13 subjects, 800 recordings

Live trace viewer — sub-13 · ses-38soa256 · task-p300 · run-0

Showing one representative recording out of 13 subjects and 800 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 · 31 sensors — 31 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.NM000203(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)—

Canonical—

Importable asNM000203

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

class eegdash.dataset.NM000203(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

P300 dataset from initial spot study

Study:: nm000203 (NeMAR)
Author (year):: nan
Canonical:: —

Also importable as: NM000203, nan.

Modality: eeg. Subjects: 13; recordings: 800; 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/nm000203 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000203

Examples

>>> from eegdash.dataset import NM000203
>>> dataset = NM000203(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 — NM000203.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 nm000203 to reproduce the tutorial on this dataset.

Citation

Jan Sosulski, David Hübner, Aaron Klein, Michael Tangermann (2019). P300 dataset from initial spot study.

Provenance

¹Contributed to nemar in BIDS format.

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

Related & sibling datasets

NM000232EEG · 10 subj NM000157EEG · 19 subj NM000132EEG · 40 subj ON007176EEG · 45 subj ON004745EEG · 6 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC-BY-SA-4.0 · DOI not on file

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000203`
Title	P300 dataset from initial spot study
Author (year)	—
Canonical	—
Importable as	`NM000203`
Year	2019
Authors	Jan Sosulski, David Hübner, Aaron Klein, Michael Tangermann
License	CC-BY-SA-4.0
Citation / DOI	Unknown
Source links	OpenNeuro \| NeMAR \| Source URL

NM000203: eeg dataset, 13 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#