NM000171: eeg dataset, 14 subjects#

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#

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)

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'])

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) https://github.com/NeuroTechX/moabb

Dataset Information#

Dataset ID

NM000171

Title

BNCI 2014-002 Motor Imagery dataset

Author (year)

Steyrl2014

Canonical

BNCI2014002

Importable as

NM000171, Steyrl2014, BNCI2014002

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): 6.865494791666666

Tags

  • Pathology: Healthy

  • Modality: Visual

  • Type: Motor

Files & format

  • Size on disk: 554.3 MB

  • File count: 112

  • Format: BIDS

License & citation

  • License: CC-BY-ND-4.0

  • DOI: —

Provenance

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:

BNCI2014002

Also importable as: NM000171, Steyrl2014, BNCI2014002.

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, overwrite=False)[source]#

Save the dataset to disk.

Parameters:

  • path (str or Path) – Destination file path.

  • overwrite (bool, default False) – If True, overwrite existing file.

Return type:

None

See Also#