NM000210: eeg dataset, 15 subjects#

BCIAUT-P300 dataset for autism from Simoes et al 2020

Access recordings and metadata through EEGDash.

Citation: Marco Simoes, Davide Borra, Eduardo Santamaria-Vazquez, Mayra Bittencourt-Villalpando, Dominik Krzeminski, Aleksandar Miladinovic, Carlos Amaral, Bruno Direito, Miguel Castelo-Branco (2020). BCIAUT-P300 dataset for autism from Simoes et al 2020.

Modality: eeg Subjects: 15 Recordings: 210 License: CC-BY-4.0 Source: nemar

Metadata: Complete (90%)

Quickstart#

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000210

dataset = NM000210(cache_dir="./data")
# Get the raw object of the first recording
raw = dataset.datasets[0].raw
print(raw.info)

Filter by subject

dataset = NM000210(cache_dir="./data", subject="01")

Advanced query

dataset = NM000210(
    cache_dir="./data",
    query={"subject": {"$in": ["01", "02"]}},
)

Iterate recordings

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

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

BibTeX

@dataset{nm000210,
  title = {BCIAUT-P300 dataset for autism from Simoes et al 2020},
  author = {Marco Simoes and Davide Borra and Eduardo Santamaria-Vazquez and Mayra Bittencourt-Villalpando and Dominik Krzeminski and Aleksandar Miladinovic and Carlos Amaral and Bruno Direito and Miguel Castelo-Branco},
}

About This Dataset#

BCIAUT-P300 dataset for autism from Simoes et al 2020

BCIAUT-P300 dataset for autism from Simoes et al 2020.

Dataset Overview

  • Code: Simoes2020

  • Paradigm: p300

  • DOI: 10.3389/fnins.2020.568104

View full README

BCIAUT-P300 dataset for autism from Simoes et al 2020

BCIAUT-P300 dataset for autism from Simoes et al 2020.

Dataset Overview

  • Code: Simoes2020

  • Paradigm: p300

  • DOI: 10.3389/fnins.2020.568104

  • Subjects: 15

  • Sessions per subject: 7

  • Events: Target=2, NonTarget=1

  • Trial interval: [0, 1.2] s

  • Runs per session: 2

  • File format: MATLAB (epoched)

  • Data preprocessed: True

Acquisition

  • Sampling rate: 250.0 Hz

  • Number of channels: 8

  • Channel types: eeg=8

  • Channel names: C3, Cz, C4, CPz, P3, Pz, P4, POz

  • Montage: standard_1020

  • Hardware: g.Nautilus (g.tec, wireless)

  • Reference: right ear

  • Ground: AFz

  • Line frequency: 50.0 Hz

Participants

  • Number of subjects: 15

  • Health status: patients

  • Clinical population: autism spectrum disorder (ASD)

  • Age: mean=22.17, std=5.5, min=16, max=38

  • Gender distribution: male=15

  • Species: human

Experimental Protocol

  • Paradigm: p300

  • Number of classes: 2

  • Class labels: Target, NonTarget

  • Trial duration: 1.2 s

  • Study design: P300 BCI joint-attention training in virtual environment; 8 flashing objects; 15 ASD subjects across 7 sessions (clinical trial NCT02445625)

  • Feedback type: visual

  • Stimulus type: object flash

  • Stimulus modalities: visual

  • Primary modality: visual

  • Mode: online

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**: 1600 train + 400*K test per session (K=3-10)

  • Trials context: per_session

Signal Processing

  • Classifiers: EEGNet, LDA, SVM, MLP

  • Feature extraction: temporal_features, deep_learning

  • Frequency bands: bandpass=[2.0, 30.0] Hz

Cross-Validation

  • Method: calibration_vs_online

  • Evaluation type: within_subject, cross_session, cross_subject

BCI Application

  • Applications: joint_attention_training

  • Environment: clinical

  • Online feedback: True

Tags

  • Pathology: Autism

  • Modality: ERP

  • Type: P300

Documentation

  • DOI: 10.3389/fnins.2020.568104

  • License: CC-BY-4.0

  • Investigators: Marco Simoes, Davide Borra, Eduardo Santamaria-Vazquez, Mayra Bittencourt-Villalpando, Dominik Krzeminski, Aleksandar Miladinovic, Carlos Amaral, Bruno Direito, Miguel Castelo-Branco

  • Institution: University of Coimbra

  • Country: PT

  • Data URL: https://zenodo.org/records/19005186

  • Publication year: 2020

References

Simoes, M., Borra, D., Santamaria-Vazquez, E., et al. (2020). BCIAUT-P300: A Multi-Session and Multi-Subject Benchmark Dataset on Autism for P300-Based Brain-Computer- Interfaces. Frontiers in Neuroscience, 14, 568104. https://doi.org/10.3389/fnins.2020.568104 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) https://github.com/NeuroTechX/moabb

Dataset Information#

Dataset ID

NM000210

Title

BCIAUT-P300 dataset for autism from Simoes et al 2020

Author (year)

Simoes2020

Canonical

BCIAUTP300, BCIAUT_P300, BCIAUT

Importable as

NM000210, Simoes2020, BCIAUTP300, BCIAUT_P300, BCIAUT

Year

2020

Authors

Marco Simoes, Davide Borra, Eduardo Santamaria-Vazquez, Mayra Bittencourt-Villalpando, Dominik Krzeminski, Aleksandar Miladinovic, Carlos Amaral, Bruno Direito, Miguel Castelo-Branco

License

CC-BY-4.0

Citation / DOI

Unknown

Source links

OpenNeuro | NeMAR | Source URL

Found an issue with this dataset?

If you encounter any problems with this dataset (missing files, incorrect metadata, loading errors, etc.), please let us know!

Report an Issue on GitHub

Technical Details#

Subjects & recordings

  • Subjects: 15

  • Recordings: 210

  • Tasks: 1

Channels & sampling rate

  • Channels: 8

  • Sampling rate (Hz): 250.0

  • Duration (hours): 187.43532222222225

Tags

  • Pathology: Development

  • Modality: Visual

  • Type: Clinical/Intervention

Files & format

  • Size on disk: 3.8 GB

  • File count: 210

  • Format: BIDS

License & citation

  • License: CC-BY-4.0

  • DOI: —

Provenance

API Reference#

Use the NM000210 class to access this dataset programmatically.

class eegdash.dataset.NM000210(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Bases: EEGDashDataset

BCIAUT-P300 dataset for autism from Simoes et al 2020

Study:

nm000210 (NeMAR)

Author (year):

Simoes2020

Canonical:

BCIAUTP300, BCIAUT_P300, BCIAUT

Also importable as: NM000210, Simoes2020, BCIAUTP300, BCIAUT_P300, BCIAUT.

Modality: eeg; Experiment type: Clinical/Intervention; Subject type: Development. Subjects: 15; recordings: 210; 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/nm000210 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000210

Examples

>>> from eegdash.dataset import NM000210
>>> dataset = NM000210(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, overwrite=False)[source]#

Save the dataset to disk.

Parameters:

  • path (str or Path) – Destination file path.

  • overwrite (bool, default False) – If True, overwrite existing file.

Return type:

None

See Also#