EEGdash›NeMAR›NM000261

Iss. 261 · 8 subjects · 8 recordings · other-open

Dataset Brief · Imagined speech EEG dataset — vowels condition (Nguyen et al…

NM000261: eeg dataset, 8 subjects#

Name: Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017)
License: other-open

Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017)

Access recordings and metadata through EEGDash.

Citation: Chuong H. Nguyen, George K. Karavas, Panagiotis Artemiadis (20). Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017). 10.82901/nemar.nm000261

Modality: eeg Subjects: 8 Recordings: 8 License: other-open Source: nemar

Metadata: Complete (100%)

8-participant EEG dataset — Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017).

Data & curation Chuong H. Nguyen · George K. Karavas · Panagiotis Artemiadis
Senior author Panagiotis Artemiadis
Year 20 · Distributed via NeMAR

EEG · 60 ch256 HzBIDS 1.9.0Task · imagery

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 NM000261

dataset = NM000261(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 = NM000261(cache_dir="./data", subject="01")

Advanced query

dataset = NM000261(
    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{nm000261,
  title = {Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017)},
  author = {Chuong H. Nguyen and George K. Karavas and Panagiotis Artemiadis},
  doi = {10.82901/nemar.nm000261},
  url = {https://doi.org/10.82901/nemar.nm000261},
}

§ 02Study · The README

About This Dataset#

This dataset comprises preprocessed EEG recordings from 8 healthy subjects performing imagined speech tasks involving three vowel phonemes (a, i, u). Participants received auditory and visual cues to imagine speaking each vowel, with 64-channel EEG data acquired at 256 Hz. The dataset includes 7,200 trials (8 subjects × 300 trials × 3 overlapping 2-second epochs per trial) analyzed using Riemannian manifold-based feature extraction and relevance vector machine classification, achieving approximately 49% mean accuracy across a 10-fold cross-validation scheme.

EEG data were acquired using a BrainProducts ActiCHamp system with 64 channels (60 EEG, 4 EOG) at 256 Hz sampling rate using a standard 10-20 montage. The experimental paradigm consisted of auditory beeps at 1.0 s intervals with visual cues, during which subjects imagined speaking designated vowels. Preprocessing included bandpass filtering (8-70 Hz, 5th order Butterworth), 60 Hz notch filtering, and adaptive EOG artifact removal. Feature extraction employed Riemannian tangent space mapping with common spatial pattern spatial filtering across mu (8-13 Hz), beta (13-30 Hz), and gamma (30-70 Hz) frequency bands.

DOI

Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017)

Overview

How to Access via MOABB

Install MOABB and load this dataset directly:

NEMAR Metadata#

[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000261-blue)](https://doi.org/10.82901/nemar.nm000261) # Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017) ## Overview This dataset comprises preprocessed EEG recordings from 8 healthy subjects performing imagined speech tasks involving three vowel phonemes (a, i, u). Participants received auditory and visual cues to imagine speaking each vowel, with 64-channel EEG data acquired at 256 Hz. The dataset includes 7,200 trials (8 subjects × 300 trials × 3 overlapping 2-second epochs per trial) analyzed using Riemannian manifold-based feature extraction and relevance vector machine classification, achieving approximately 49% mean accuracy across a 10-fold cross-validation scheme. ## Dataset Summary | Property | Value | |---|—| | Subjects | 8 | | Channels | 64 | | Classes | 3 | | Trial length | 5 s | | Sampling frequency | 256 Hz | | Sessions | 1 | | Total trials | 2400 | | Paradigm | MotorImagery | ## Data Collection Methods EEG data were acquired using a BrainProducts ActiCHamp system with 64 channels (60 EEG, 4 EOG) at 256 Hz sampling rate using a standard 10-20 montage. The experimental paradigm consisted of auditory beeps at 1.0 s intervals with visual cues, during which subjects imagined speaking designated vowels. Preprocessing included bandpass filtering (8-70 Hz, 5th order Butterworth), 60 Hz notch filtering, and adaptive EOG artifact removal. Feature extraction employed Riemannian tangent space mapping with common spatial pattern spatial filtering across mu (8-13 Hz), beta (13-30 Hz), and gamma (30-70 Hz) frequency bands. ## How to Access via MOABB Install MOABB and load this dataset directly: `python from moabb.datasets import Nguyen2017_V from moabb.paradigms import MotorImagery paradigm = MotorImagery() dataset = Nguyen2017_V() X, y, metadata = paradigm.get_data(dataset) ` For more details see the [MOABB documentation](https://moabb.neurotechx.com/) and the [MOABB dataset page](https://moabb.neurotechx.com/docs/generated/moabb.datasets.Nguyen2017_V.html). ## Citation If you use this dataset please cite the primary publication: > DOI: [10.1088/1741-2552/aa8235](https://doi.org/10.1088/1741-2552/aa8235) ## NEMAR / MOABB Benchmark Collection This BIDS-formatted dataset was converted from the original data using the [MOABB](https://moabb.neurotechx.com/) pipeline and re-hosted on [NEMAR](https://nemar.org/) as part of the MOABB benchmark collection. The original data and license terms apply — see dataset_description.json for details.

License: other-open

Authors:

Chuong H. Nguyen
George K. Karavas
Panagiotis Artemiadis

Versions:

Version	DOI	Released
`current`	10.82901/nemar.nm000261

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Channel counts: 60 ch (n=8 recordings)

Sampling frequencies: 256.0 Hz (n=8 recordings)

Total recording duration: 4 h 46 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 60 ch · EEG · 256 Hz · 8 subjects, 8 recordings

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

Showing one representative recording out of 8 subjects and 8 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 · 60 sensors — 60 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.NM000261(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)—

Canonical—

Importable asNM000261

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

class eegdash.dataset.NM000261(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017)

Study:: nm000261 (NeMAR)
Author (year):: —
Canonical:: —

Also importable as: NM000261.

Modality: eeg; Subject type: Unknown. Subjects: 8; recordings: 8; 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/nm000261 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000261 DOI: https://doi.org/10.82901/nemar.nm000261

Examples

>>> from eegdash.dataset import NM000261
>>> dataset = NM000261(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 — NM000261.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 nm000261 to reproduce the tutorial on this dataset.

Citation

Chuong H. Nguyen, George K. Karavas, Panagiotis Artemiadis (20). Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017). 10.82901/nemar.nm000261

Provenance

¹Contributed to nemar in BIDS format.

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

³Persistent identifier: 10.82901/nemar.nm000261.

Related & sibling datasets

NM000257EEG · 6 subj NM000252EEG · 6 subj NM000224EEG · 6 subj ON007406EEG · 10 subj ON003626EEG · 10 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

other-open · 10.82901/nemar.nm000261

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000261`
Title	Imagined speech EEG dataset — vowels condition (Nguyen et al. 2017)
Author (year)	—
Canonical	—
Importable as	`NM000261`
Year	20
Authors	Chuong H. Nguyen, George K. Karavas, Panagiotis Artemiadis
License	other-open
Citation / DOI	10.82901/nemar.nm000261
Source links	OpenNeuro \| NeMAR \| Source URL

NM000261: eeg dataset, 8 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#