EEGdash›NeMAR›NM000272

Iss. 272 · 45 subjects · 181 recordings · CC-BY-4.0

Dataset Brief · Romani et al. 2025 — BrainForm

NM000272: eeg dataset, 45 subjects#

Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento)

Access recordings and metadata through EEGDash.

Citation: Michele Romani, Devis Zanoni, Elisabetta Farella, Luca Turchet (2025). Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento). 10.82901/nemar.nm000272

Modality: eeg Subjects: 45 Recordings: 181 License: CC-BY-4.0 Source: nemar

Metadata: Complete (100%)

45-participant EEG dataset — Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento).

Data & curation Michele Romani · Devis Zanoni · Elisabetta Farella · Luca Turchet
Senior author Luca Turchet
Year 2025 · Distributed via NeMAR

EEG · 8 (240), 9 (61) ch250 HzBIDS 1.9.02 tasks6 sessionsVisualAttention

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 NM000272

dataset = NM000272(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 = NM000272(cache_dir="./data", subject="01")

Advanced query

dataset = NM000272(
    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{nm000272,
  title = {Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento)},
  author = {Michele Romani and Devis Zanoni and Elisabetta Farella and Luca Turchet},
  doi = {10.82901/nemar.nm000272},
  url = {https://doi.org/10.82901/nemar.nm000272},
}

§ 02Study · The README

About This Dataset#

This dataset contains scalp electroencephalography (EEG) recordings collected with

BrainForm, a gamified (serious-game) P300 event-related potential (ERP) brain–computer interface (BCI) designed for scalable data collection using consumer hardware and a minimal setup. Participants completed repeated runs of a P300 spelling / selection task, enabling study of BCI skill acquisition across sessions and of the perceptual/performance effects of different visual stimulation textures.

The BIDS conversion in this NEMAR record contains EEG data for 22 participants

(sub-* folders), organised under the eeg/ modality with a P300 task (task-p300).

DOI

BrainForm: a P300 ERP EEG dataset from a serious game for BCI training and data collection

Summary

Modality and paradigm

Modality: EEG (scalp electroencephalography)

NEMAR Metadata#

[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000272-blue)](https://doi.org/10.82901/nemar.nm000272) # BrainForm: a P300 ERP EEG dataset from a serious game for BCI training and data collection ## Summary This dataset contains scalp electroencephalography (EEG) recordings collected with BrainForm, a gamified (serious-game) P300 event-related potential (ERP) brain–computer interface (BCI) designed for scalable data collection using consumer hardware and a minimal setup. Participants completed repeated runs of a P300 spelling / selection task, enabling study of BCI skill acquisition across sessions and of the perceptual/performance effects of different visual stimulation textures. The BIDS conversion in this NEMAR record contains EEG data for 22 participants (sub-* folders), organised under the eeg/ modality with a P300 task (task-p300). ## Modality and paradigm - Modality: EEG (scalp electroencephalography) - Task / paradigm: P300 ERP oddball / speller within a serious game (task-p300) - Focus: BCI training, human factors, machine learning on ERP data ## Participants This BIDS dataset includes 22 subjects. The original study used a within-subject design with multiple runs and two task complexities. Refer to participants.tsv and the paper for details. ## Original dataset / data paper Please cite the original paper when using this dataset: > Romani, M., Zanoni, D., Farella, E., & Turchet, L. (2025). BrainForm: a Serious Game > for BCI Training and Data Collection. arXiv:2510.10169. > https://doi.org/10.48550/arXiv.2510.10169 - DOI / preprint: [arXiv:2510.10169](https://doi.org/10.48550/arXiv.2510.10169) - Source / project: University of Trento and Fondazione Bruno Kessler (FBK) - Related record: https://zenodo.org/records/17225966 ## Attribution All data were collected by the original authors (Michele Romani and colleagues, University of Trento / FBK). Please credit the original creators and cite the paper above. This NEMAR record redistributes the dataset in BIDS format; EEG-BIDS and related BIDS tools were used only for standardisation, not as the source of the data. ## License CC-BY-4.0 (see dataset_description.json).

License: CC-BY-4.0

Authors:

Michele Romani
Devis Zanoni
Elisabetta Farella
Luca Turchet

Versions:

Version	DOI	Released
`current`	10.82901/nemar.nm000272

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Channel counts (ch)

89

Sampling frequencies: 250.0 Hz (n=301 recordings)

Total recording duration: 18 h 57 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 8 (240), 9 (61) ch · EEG · 250 Hz · 45 subjects, 181 recordings

Live trace viewer — sub-P01 · ses-0grain · task-ERP

Showing one representative recording out of 45 subjects and 181 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.NM000272(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)Romani2025_BF_ERP

Canonical—

Importable asNM000272 · Romani2025_BF_ERP

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

class eegdash.dataset.NM000272(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento)

Study:: nm000272 (NeMAR)
Author (year):: Romani2025_BF_ERP
Canonical:: —

Also importable as: NM000272, Romani2025_BF_ERP.

Modality: eeg; Experiment type: Attention; Subject type: Unknown. Subjects: 45; recordings: 181; tasks: 2.

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/nm000272 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000272 DOI: https://doi.org/10.82901/nemar.nm000272

Examples

>>> from eegdash.dataset import NM000272
>>> dataset = NM000272(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 FacePre-bundled mirror at EEGDash/nm000272 · pull with datasets.load_dataset("EEGDash/nm000272").huggingface

Croissant 1.0Machine-readable JSON-LD descriptor — NM000272.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 nm000272 to reproduce the tutorial on this dataset.

Citation

Michele Romani, Devis Zanoni, Elisabetta Farella, Luca Turchet (2025). Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento). 10.82901/nemar.nm000272

Provenance

¹Contributed to nemar in BIDS format.

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

³Persistent identifier: 10.82901/nemar.nm000272.

Related & sibling datasets

NM000217EEG · 44 subj NM000201EEG · 33 subj NM000351EEG · 19 subj NM000215EEG · 38 subj NM000277EEG · 20 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC-BY-4.0 · 10.82901/nemar.nm000272

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HuggingFace

Dataset ID	`NM000272`
Title	Romani et al. 2025 — BrainForm: a Serious Game for BCI Training and Data Collection (P300 ERP, University of Trento)
Author (year)	`Romani2025_BF_ERP`
Canonical	—
Importable as	`NM000272`, `Romani2025_BF_ERP`
Year	2025
Authors	Michele Romani, Devis Zanoni, Elisabetta Farella, Luca Turchet
License	CC-BY-4.0
Citation / DOI	10.82901/nemar.nm000272
Source links	OpenNeuro \| NeMAR \| Source URL

NM000272: eeg dataset, 45 subjects#

Quickstart#

About This Dataset#

NEMAR Metadata#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#