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

Access recordings and metadata through EEGDash.

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

Modality: eeg Subjects: 9 Recordings: 108 License: CC-BY-ND-4.0 Source: nemar

Metadata: Complete (100%)

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},
}

About This Dataset#

DOI

BNCI 2014-001 Motor Imagery dataset

BNCI 2014-001 Motor Imagery dataset.

Dataset Overview

Code: BNCI2014-001
Paradigm: imagery

View full README

DOI

BNCI 2014-001 Motor Imagery dataset

BNCI 2014-001 Motor Imagery dataset.

Dataset Overview

Code: BNCI2014-001
Paradigm: imagery
DOI: 10.3389/fnins.2012.00055
Subjects: 9
Sessions per subject: 2
Events: left_hand=1, right_hand=2, feet=3, tongue=4
Trial interval: [2, 6] s
Runs per session: 6
File format: GDF
Data preprocessed: True

Acquisition

Sampling rate: 250.0 Hz
Number of channels: 25
Channel types: eeg=22, eog=3
Channel names: C1, C2, C3, C4, C5, C6, CP1, CP2, CP3, CP4, CPz, Cz, EOG1, EOG2, EOG3, FC1, FC2, FC3, FC4, FCz, Fz, P1, P2, POz, Pz
Montage: custom
Hardware: BrainAmp MR plus
Software: BCI2000
Reference: left mastoid
Ground: unknown
Sensor type: Ag/AgCl
Line frequency: 50.0 Hz
Online filters: bandpass 0.05-200 Hz
Cap manufacturer: EASYCAP GmbH

Participants

Number of subjects: 9
Health status: healthy
Species: human

Experimental Protocol

Paradigm: imagery
Number of classes: 4
Class labels: left_hand, right_hand, feet, tongue
Trial duration: 4.0 s
Study design: Two-class motor imagery (selected from left hand, right hand, and foot) with asynchronous/continuous control periods
Feedback type: none
Stimulus type: arrow_cue
Stimulus modalities: visual, auditory
Primary modality: multisensory
Synchronicity: asynchronous
Mode: offline
Instructions: Subjects instructed to perform motor imagery during cued periods

HED Event Annotations

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

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

Dataset Information#

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

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: 9
Recordings: 108
Tasks: 1

Channels & sampling rate

Channels: 22
Sampling rate (Hz): 250.0
Duration (hours): 11.60808

Electrode Layout#

Electrode layout — EEG · 22 sensors — 22 channels

Dataset Statistics#

Age distribution (n=9, range 17–26 yr)

152025

Sex distribution

4

5

Female Male Total: 9

Channel counts: 22 ch (n=108 recordings)

Sampling frequencies: 250.0 Hz (n=108 recordings)

Total recording duration: 11 h 36 min

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

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.

Files: —

Size: —

Subjects: —

Click to load file structure…

API Reference#

Use the NM000139 class to access this dataset programmatically.

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

Bases: EEGDashDataset

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)