NM000171: eeg dataset, 14 subjects#

Name: BNCI 2014-002 Motor Imagery dataset
Published: 2015-01-01
License: CC-BY-ND-4.0

BNCI 2014-002 Motor Imagery dataset

Access recordings and metadata through EEGDash.

Citation: David Steyrl, Reinhold Scherer, Oswin Förstner, Gernot R. Müller-Putz (2015). BNCI 2014-002 Motor Imagery dataset.

Modality: eeg Subjects: 14 Recordings: 112 License: CC-BY-ND-4.0 Source: nemar

Metadata: Complete (90%)

Quickstart#

Get Started

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000171

dataset = NM000171(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 = NM000171(cache_dir="./data", subject="01")

Advanced query

dataset = NM000171(
    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{nm000171,
  title = {BNCI 2014-002 Motor Imagery dataset},
  author = {David Steyrl and Reinhold Scherer and Oswin Förstner and Gernot R. Müller-Putz},
}

About This Dataset#

BNCI 2014-002 Motor Imagery dataset

BNCI 2014-002 Motor Imagery dataset.

Dataset Overview

Code: BNCI2014-002
Paradigm: imagery
DOI: 10.1007/s00500-012-0895-4

View full README

BNCI 2014-002 Motor Imagery dataset

BNCI 2014-002 Motor Imagery dataset.

Dataset Overview

Code: BNCI2014-002
Paradigm: imagery
DOI: 10.1007/s00500-012-0895-4
Subjects: 14
Sessions per subject: 1
Events: right_hand=1, feet=2
Trial interval: [3, 8] s
Runs per session: 8
File format: MAT
Data preprocessed: True

Acquisition

Sampling rate: 512.0 Hz
Number of channels: 15
Channel types: eeg=15
Channel names: EEG1, EEG2, EEG3, EEG4, EEG5, EEG6, EEG7, EEG8, EEG9, EEG10, EEG11, EEG12, EEG13, EEG14, EEG15
Montage: Laplacian
Hardware: g.USBamp
Software: BCI2000
Reference: left mastoid
Ground: right mastoid
Sensor type: Ag/AgCl
Line frequency: 50.0 Hz
Online filters: 8th order Butterworth band-pass filters
Cap manufacturer: Guger Technologies OG
Cap model: g.LADYbird
Electrode type: active
Electrode material: Ag/AgCl

Participants

Number of subjects: 14
Health status: healthy
Age: min=20.0, max=30.0
BCI experience: mixed
Species: human

Experimental Protocol

Paradigm: imagery
Number of classes: 2
Class labels: right_hand, feet
Trial duration: 5.0 s
Study design: Two-class motor imagery: right hand and feet. Cue-guided Graz-BCI training paradigm with recording, training, and feedback within a single session.
Feedback type: continuous
Stimulus type: bar_graph
Stimulus modalities: visual
Primary modality: visual
Synchronicity: synchronous
Mode: online

HED Event Annotations

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

right_hand

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

feet

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

Paradigm-Specific Parameters

Detected paradigm: motor_imagery
Imagery tasks: right_hand, feet
Imagery duration: 5.0 s

Data Structure

Trials: 160
Trials per class: right_hand=80, feet=80
Blocks per session: 8
Trials context: total per subject

Preprocessing

Data state: minimally preprocessed (online filtered)
Preprocessing applied: True
Steps: bandpass filtering
Filter type: Butterworth
Filter order: 8

Signal Processing

Classifiers: Random Forest, Shrinkage LDA
Feature extraction: CSP, DFT, Bandpower
Frequency bands: alpha=[6, 14] Hz; beta=[14, 40] Hz
Spatial filters: CSP, Laplacian

Cross-Validation

Method: train-test split
Evaluation type: within_subject

Performance (Original Study)

Accuracy: 79.3%
Peak Accuracy: 89.67
Median Accuracy: 80.42

BCI Application

Applications: communication, control
Environment: laboratory
Online feedback: True

Tags

Pathology: Healthy
Modality: Motor
Type: Motor Imagery

Documentation

DOI: 10.1515/bmt-2014-0117
Associated paper DOI: 10.3217/978-3-85125-378-8-61
License: CC-BY-ND-4.0
Investigators: David Steyrl, Reinhold Scherer, Oswin Förstner, Gernot R. Müller-Putz
Contact: david.steyrl@tugraz.at; reinhold.scherer@tugraz.at; oswin.foerstner@student.tugraz.at; gernot.mueller@tugraz.at
Institution: Graz University of Technology
Department: Institute for Knowledge Discovery, Laboratory of Brain-Computer Interfaces
Country: Austria
Repository: BNCI Horizon
Publication year: 2014
Funding: FP7 BackHome (No. 288566); FP7 ABC (No. 287774)
Keywords: brain-computer interfaces, machine learning, random forests, regularized linear discriminant analysis, sensorimotor rhythms

References

Scherer, R., Faller, J., Balderas, D., Friedrich, E. V., & Müller-Putz, G. (2015). Brain-computer interfacing: more than the sum of its parts. Soft Computing, 19(11), 3173-3186. https://doi.org/10.1007/s00500-012-0895-4 Notes .. note:: BNCI2014_002 was previously named BNCI2014002. BNCI2014002 will be removed in version 1.1. .. versionadded:: 0.4.0 See Also BNCI2014_001 : 4-class motor imagery (BCI Competition IV Dataset 2a) BNCI2014_004 : 2-class motor imagery (Dataset B) 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) NeuroTechX/moabb

Dataset Information#

Dataset ID	`NM000171`
Title	BNCI 2014-002 Motor Imagery dataset
Author (year)	`Steyrl2014`
Canonical	—
Importable as	`NM000171`, `Steyrl2014`
Year	2015
Authors	David Steyrl, Reinhold Scherer, Oswin Förstner, Gernot R. Müller-Putz
License	CC-BY-ND-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: 14
Recordings: 112
Tasks: 1

Channels & sampling rate

Channels: 15
Sampling rate (Hz): 512.0
Duration (hours): 13.730989583333333

Electrode Layout#

No scalp electrode layout is currently indexed for this dataset. Once the eegdash montage registry ingests it, the interactive viewer will appear here automatically.

Dataset Statistics#

Channel counts: 15 ch (n=224 recordings)

Sampling frequencies: 512.0 Hz (n=224 recordings)

Total recording duration: 13 h 43 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 NM000171 class to access this dataset programmatically.

class eegdash.dataset.NM000171(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Bases: EEGDashDataset

BNCI 2014-002 Motor Imagery dataset

Study:: nm000171 (NeMAR)
Author (year):: Steyrl2014
Canonical:: —

Also importable as: NM000171, Steyrl2014.

Modality: eeg; Experiment type: Motor; Subject type: Healthy. Subjects: 14; recordings: 112; 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/nm000171 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000171

Examples

>>> from eegdash.dataset import NM000171
>>> dataset = NM000171(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)