EEGdash›NeMAR›NM000139

Iss. 139 · 9 subjects · 108 recordings · CC-BY-ND-4.0

Dataset Brief · BNCI 2014-001 Motor Imagery dataset

NM000139: eeg dataset, 9 subjects#

Name: BNCI 2014-001 Motor Imagery dataset
Published: 2019-01-01
License: CC-BY-ND-4.0

BNCI 2014-001 Motor Imagery dataset

Citation: Michael Tangermann, Klaus-Robert Müller, Ad Aertsen, Niels Birbaumer, Christoph Braun, Clemens Brunner, Robert Leeb, Carsten Mehring, Kai J. Miller, Gernot R. Müller-Putz, Guido Nolte, Gert Pfurtscheller, Hubert Preissl, Gerwin Schalk, Alois Schlögl, Carmen Vidaurre, Stephan Waldert, Benjamin Blankertz (2019). BNCI 2014-001 Motor Imagery dataset. 10.82901/nemar.nm000139

9-participant EEG dataset — BNCI 2014-001 Motor Imagery dataset.

Data & curation Michael Tangermann · Klaus-Robert Müller · Ad Aertsen · Niels Birbaumer · Christoph Braun · Clemens Brunner · …
Year 2019 · Distributed via NeMAR

EEG · 22 ch250 HzBIDS 1.9.0Task · imagery2 sessionsHealthyMultisensoryMotor

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 NM000139

dataset = NM000139(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 = NM000139(cache_dir="./data", subject="01")

Advanced query

dataset = NM000139(
    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{nm000139,
  title = {BNCI 2014-001 Motor Imagery dataset},
  author = {Michael Tangermann and Klaus-Robert Müller and Ad Aertsen and Niels Birbaumer and Christoph Braun and Clemens Brunner and Robert Leeb and Carsten Mehring and Kai J. Miller and Gernot R. Müller-Putz and Guido Nolte and Gert Pfurtscheller and Hubert Preissl and Gerwin Schalk and Alois Schlögl and Carmen Vidaurre and Stephan Waldert and Benjamin Blankertz},
  doi = {10.82901/nemar.nm000139},
  url = {https://doi.org/10.82901/nemar.nm000139},
}

§ 02Study · The README

About This Dataset#

BNCI 2014-001 Motor Imagery dataset.

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

DOI

BNCI 2014-001 Motor Imagery dataset

left_hand

View full README

DOI

BNCI 2014-001 Motor Imagery dataset

left_hand

     ├─ Sensory-event
     │  ├─ Experimental-stimulus
     │  ├─ Visual-presentation
     │  └─ Leftward, Arrow
     └─ Agent-action
        └─ Imagine
           ├─ Move
           └─ Left, Hand

right_hand

     ├─ Sensory-event
     │  ├─ Experimental-stimulus
     │  ├─ Visual-presentation
     │  └─ Rightward, Arrow
     └─ Agent-action
        └─ Imagine
           ├─ Move
           └─ Right, Hand

feet

     ├─ Sensory-event
     │  ├─ Experimental-stimulus
     │  ├─ Visual-presentation
     │  └─ Downward, Arrow
     └─ Agent-action
        └─ Imagine, Move, Foot

tongue

├─ Sensory-event
│  ├─ Experimental-stimulus
│  ├─ Visual-presentation
│  └─ Upward, Arrow
└─ Agent-action
   └─ Imagine, Move, Tongue

Paradigm-Specific Parameters

Detected paradigm: motor_imagery
Imagery tasks: left_hand, right_hand, foot
Cue duration: 4.0 s
Imagery duration: 4.0 s

Data Structure

Trials: {‘training’: 200, ‘test’: 240}
Blocks per session: 6
Trials context: per subject (2 training runs + 4 test runs)

Preprocessing

Data state: minimally preprocessed (bandpass and notch filtered)
Preprocessing applied: True
Steps: bandpass filtering
Highpass filter: 0.05 Hz
Lowpass filter: 200 Hz
Bandpass filter: {‘low_cutoff_hz’: 0.05, ‘high_cutoff_hz’: 200.0}
Filter type: analog
Re-reference: none
Downsampled to: 100.0 Hz
Notes: Data provided in two versions: original at 1000 Hz and downsampled to 100 Hz (with Chebyshev Type II filter order 10, stop band ripple 50 dB, stop band edge 49 Hz)

Signal Processing

Classifiers: LDA, SVM, Neural Network, Naive Bayes, RBF Neural Network
Feature extraction: CSP, FBCSP, Bandpower, ERD, ERS
Frequency bands: mu=[8, 12] Hz; beta=[16, 24] Hz

Cross-Validation

Method: train-test split
Evaluation type: within_session

Performance (Original Study)

Mse: 0.382

BCI Application

Applications: cursor_control, communication
Environment: laboratory
Online feedback: False

Tags

Pathology: Healthy
Modality: Motor
Type: Motor

Documentation

Description: Review of the BCI competition IV - Data set 1: Asynchronous Motor Imagery
DOI: 10.3389/fnins.2012.00055
License: CC-BY-ND-4.0
Investigators: Michael Tangermann, Klaus-Robert Müller, Ad Aertsen, Niels Birbaumer, Christoph Braun, Clemens Brunner, Robert Leeb, Carsten Mehring, Kai J. Miller, Gernot R. Müller-Putz, Guido Nolte, Gert Pfurtscheller, Hubert Preissl, Gerwin Schalk, Alois Schlögl, Carmen Vidaurre, Stephan Waldert, Benjamin Blankertz
Senior author: Michael Tangermann
Contact: michael.tangermann@tu-berlin.de
Institution: Berlin Institute of Technology
Department: Machine Learning Laboratory
Address: FR 6-9, Franklinstr. 28/29, 10587 Berlin, Germany
Country: AT
Repository: BNCI Horizon
Data URL: http://www.bbci.de/competition/iv/
Publication year: 2012
Keywords: brain-computer interface, BCI, competition

References

Tangermann, M., Muller, K.R., Aertsen, A., Birbaumer, N., Braun, C., Brunner, C., Leeb, R., Mehring, C., Miller, K.J., Mueller-Putz, G. and Nolte, G., 2012. Review of the BCI competition IV. Frontiers in neuroscience, 6, p.55.

Notes .. note:: BNCI2014_001 was previously named BNCI2014001. BNCI2014001 will be removed in version 1.1. .. versionadded:: 0.4.0 This is one of the most widely used motor imagery datasets in BCI research, commonly referred to as “BCI Competition IV Dataset 2a”. It serves as a standard benchmark for 4-class motor imagery classification algorithms.

The dataset is particularly useful for: - Multi-class motor imagery classification (4 classes) - Transfer learning studies (9 subjects, 2 sessions each) - Cross-session variability analysis

See Also BNCI2014_004 : BCI Competition 2008 2-class motor imagery (Dataset B) BNCI2003_004 : BCI Competition III 2-class motor imagery Examples

>> from moabb.datasets import BNCI2014_001 >>> dataset = BNCI2014_001() >>> dataset.subject_list [1, 2, 3, 4, 5, 6, 7, 8, 9]

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 1.4.3 (Mother of All BCI Benchmarks) NeuroTechX/moabb

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Age distribution by gender (n=9, range 17–26 yr, mean 23.1 yr)

152025

Female · 4Male · 5

Sex composition

Female
4
Male
5
F : M ratio
0.80 : 1

44% female · n = 9 subjects with reported sex.

HandednessRight · 9

Channel counts: 22 ch (n=108 recordings)

Sampling frequencies: 250.0 Hz (n=108 recordings)

Total recording duration: 11 h 36 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 22 ch · EEG · 250 Hz · 9 subjects, 108 recordings

Live trace viewer — sub-6 · ses-0train · task-imagery · run-4

Showing one representative recording out of 9 subjects and 108 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 · 22 sensors — 22 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.NM000139(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)Tangermann2014

Canonical—

Importable asNM000139 · Tangermann2014

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

class eegdash.dataset.NM000139(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

BNCI 2014-001 Motor Imagery dataset

Study:: nm000139 (NeMAR)
Author (year):: Tangermann2014
Canonical:: —

Also importable as: NM000139, Tangermann2014.

Modality: eeg; Experiment type: Motor; Subject type: Healthy. Subjects: 9; recordings: 108; 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/nm000139 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000139 DOI: https://doi.org/10.82901/nemar.nm000139

Examples

>>> from eegdash.dataset import NM000139
>>> dataset = NM000139(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 — NM000139.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 nm000139 to reproduce the tutorial on this dataset.

Citation

Michael Tangermann, Klaus-Robert Müller, Ad Aertsen, Niels Birbaumer, Christoph Braun, … (2019). BNCI 2014-001 Motor Imagery dataset. 10.82901/nemar.nm000139

Provenance

¹Contributed to nemar in BIDS format.

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

³Persistent identifier: 10.82901/nemar.nm000139.

Related & sibling datasets

NM000347EEG · 37 subj NM000158EEG · 50 subj DS007406EEG · 10 subj DS007006EEG · 10 subj NM000137EEG · 7 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC-BY-ND-4.0 · 10.82901/nemar.nm000139

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000139`
Title	BNCI 2014-001 Motor Imagery dataset
Author (year)	`Tangermann2014`
Canonical	—
Importable as	`NM000139`, `Tangermann2014`
Year	2019
Authors	Michael Tangermann, Klaus-Robert Müller, Ad Aertsen, Niels Birbaumer, Christoph Braun, Clemens Brunner, Robert Leeb, Carsten Mehring, Kai J. Miller, Gernot R. Müller-Putz, Guido Nolte, Gert Pfurtscheller, Hubert Preissl, Gerwin Schalk, Alois Schlögl, Carmen Vidaurre, Stephan Waldert, Benjamin Blankertz
License	CC-BY-ND-4.0
Citation / DOI	10.82901/nemar.nm000139
Source links	OpenNeuro \| NeMAR \| Source URL

NM000139: eeg dataset, 9 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#