NM000243: eeg dataset, 15 subjects#

Name: BNCI 2016-002 Emergency Braking during Simulated Driving dataset
Published: 2011-01-01
License: CC-BY-NC-ND-4.0

BNCI 2016-002 Emergency Braking during Simulated Driving dataset

Access recordings and metadata through EEGDash.

Citation: Stefan Haufe, Matthias S Treder, Manfred F Gugler, Max Sagebaum, Gabriel Curio, Benjamin Blankertz (2011). BNCI 2016-002 Emergency Braking during Simulated Driving dataset.

Modality: eeg Subjects: 15 Recordings: 15 License: CC-BY-NC-ND-4.0 Source: nemar

Metadata: Complete (90%)

Quickstart#

Get Started

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000243

dataset = NM000243(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 = NM000243(cache_dir="./data", subject="01")

Advanced query

dataset = NM000243(
    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{nm000243,
  title = {BNCI 2016-002 Emergency Braking during Simulated Driving dataset},
  author = {Stefan Haufe and Matthias S Treder and Manfred F Gugler and Max Sagebaum and Gabriel Curio and Benjamin Blankertz},
}

About This Dataset#

BNCI 2016-002 Emergency Braking during Simulated Driving dataset

BNCI 2016-002 Emergency Braking during Simulated Driving dataset.

Dataset Overview

Code: BNCI2016-002
Paradigm: p300
DOI: 10.1088/1741-2560/8/5/056001

View full README

BNCI 2016-002 Emergency Braking during Simulated Driving dataset

BNCI 2016-002 Emergency Braking during Simulated Driving dataset.

Dataset Overview

Code: BNCI2016-002
Paradigm: p300
DOI: 10.1088/1741-2560/8/5/056001
Subjects: 15
Sessions per subject: 1
Events: Target=1, NonTarget=2
Trial interval: [-0.5, 1.0] s
File format: .mat
Data preprocessed: True
Contributing labs: Machine Learning Group, Berlin Institute of Technology, Bernstein Focus Neurotechnology, Berlin, Neurophysics Group, Charité University Medicine Berlin, Intelligent Data Analysis Group, Fraunhofer Institute FIRST

Acquisition

Sampling rate: 200.0 Hz
Number of channels: 59
Channel types: eeg=59, emg=1, eog=2, misc=7
Channel names: AF3, AF4, C1, C2, C3, C4, C5, C6, CP1, CP2, CP3, CP4, CP5, CP6, CPz, Cz, EMGf, EOGh, EOGv, F1, F2, F3, F4, F5, F6, F7, F8, FC1, FC2, FC3, FC4, FC5, FC6, FCz, FT7, FT8, Fp1, Fp2, Fz, O1, O2, Oz, P1, P10, P2, P3, P4, P5, P6, P7, P8, P9, PO3, PO4, PO7, PO8, POz, Pz, T7, T8, TP7, TP8, brake, dist_to_lead, gas, lead_brake, lead_gas, wheel_X, wheel_Y
Montage: extended 10-20
Hardware: BrainAmp
Software: TORCS
Reference: nose
Sensor type: Ag/AgCl
Line frequency: 50.0 Hz
Online filters: {‘highpass_hz’: 0.1, ‘lowpass_hz’: 250}
Impedance threshold: {‘eeg’: 20, ‘emg’: 50} kOhm
Cap manufacturer: Easycap
Cap model: Easycap
Auxiliary channels: EOG (2 ch, vertical, horizontal), EMG (1 ch), technical_markers

Participants

Number of subjects: 15
Health status: healthy
Age: mean=30.6, std=5.4
Gender distribution: male=14, female=4
Handedness: right-handed
BCI experience: naive
Species: human

Experimental Protocol

Paradigm: p300
Task type: driving_simulation
Number of classes: 2
Class labels: Target, NonTarget
Trial duration: 3.0 s
Study design: Participants drove a virtual racing car using steering wheel and gas/brake pedals, tightly following a computer-controlled lead vehicle at 100 km/h. The lead vehicle occasionally decelerated abruptly (20-40s inter-stimulus-interval) to 60-80 km/h, requiring immediate emergency braking. Three blocks of 45 min each with 10-15 min rest between blocks.
Feedback type: visual (colored circle indicating distance: green <20m, yellow otherwise; brakelight flashing)
Stimulus type: emergency_braking_scenario
Stimulus modalities: visual, multisensory
Primary modality: visual
Synchronicity: asynchronous
Mode: online
Training/test split: True
Instructions: Drive a virtual racing car using steering wheel and gas/brake pedals, tightly follow the lead vehicle within 20m at 100 km/h. Perform immediate emergency braking when the lead vehicle decelerates abruptly to avoid a crash.
Stimulus presentation: isi_range=20-40 seconds, deceleration_range=60-80 km/h, brakelight=flashing, oncoming_traffic=present, sharp_curves=present

HED Event Annotations

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

Target

     ├─ Sensory-event
     ├─ Experimental-stimulus
     ├─ Visual-presentation
     └─ Target

NonTarget

├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Non-target

Paradigm-Specific Parameters

Detected paradigm: p300

Data Structure

Trials: ~99 emergency braking events per subject (test set)
Blocks per session: 3
Block duration: 2700.0 s
Trials context: Emergency braking events with 20-40s inter-stimulus-interval, total ~225 events across 3 blocks per subject

Preprocessing

Data state: preprocessed
Preprocessing applied: True
Steps: lowpass filtering, bandpass filtering, notch filtering, rectification, downsampling/upsampling, baseline correction, synchronization
Highpass filter: 0.1 Hz
Lowpass filter: 45.0 Hz
Bandpass filter: [15.0, 90.0]
Notch filter: 50.0 Hz
Filter type: Chebychev type II (EEG lowpass), Elliptic (EMG bandpass), digital (notch)
Filter order: tenth-order (EEG), sixth-order (EMG), second-order (notch)
Re-reference: nose
Downsampled to: 200.0 Hz
Epoch window: [-0.3, 1.2]
Notes: EEG lowpass filtered at 45 Hz (causal). EMG bandpass filtered 15-90 Hz with 50 Hz notch and rectified. All signals synchronized and resampled to 200 Hz. Baseline correction using first 100 ms.

Signal Processing

Classifiers: RLDA, Regularized Linear Discriminant Analysis, Shrinkage LDA
Feature extraction: Event-Related Potentials, Spatio-temporal features, Bi-serial correlation, Area Under Curve
Spatial filters: Artifact rejection based on spectral power

Cross-Validation

Method: sequential temporal split
Evaluation type: temporal_validation

Performance (Original Study)

Auc: 0.5
Braking Time Reduction Ms: 130
Braking Distance Reduction M: 3.66

BCI Application

Applications: driving_assistance, emergency_braking_detection, neuroergonomics
Environment: laboratory
Online feedback: True

Tags

Pathology: Healthy
Modality: Visual, Multisensory
Type: Driving, Neuroergonomics

Documentation

Description: Emergency braking detection during simulated driving using EEG and EMG to predict driver’s braking intention before behavioral response.
DOI: 10.1088/1741-2560/8/5/056001
Associated paper DOI: 10.1088/1741-2560/8/5/056001
License: CC-BY-NC-ND-4.0
Investigators: Stefan Haufe, Matthias S Treder, Manfred F Gugler, Max Sagebaum, Gabriel Curio, Benjamin Blankertz
Senior author: Benjamin Blankertz
Contact: stefan.haufe@tu-berlin.de
Institution: Berlin Institute of Technology
Department: Machine Learning Group, Department of Computer Science
Address: Franklinstraße 28/29, D-10587 Berlin, Germany
Country: Germany
Repository: BNCI Horizon
Publication year: 2011
Funding: DFG grant; BMBF grant; Bernstein Focus Neurotechnology, Berlin
Ethics approval: IRB of Charité University Medicine, Berlin; Declaration of Helsinki; Written informed consent from all participants
Keywords: emergency braking, driving simulation, EEG, EMG, brain-computer interface, neuroergonomics, event-related potentials, machine learning, driver assistance

References

Haufe, S., Treder, M. S., Gugler, M. F., Sagebaum, M., Curio, G., & Blankertz, B. (2011). EEG potentials predict upcoming emergency brakings during simulated driving. Journal of Neural Engineering, 8(5), 056001. https://doi.org/10.1088/1741-2560/8/5/056001 Notes .. versionadded:: 1.3.0 This dataset is valuable for research on: - Predictive braking assistance systems - Neuroergonomics and driving safety - Real-time detection of emergency intentions - Multimodal biosignal integration (EEG + EMG + vehicle dynamics)

The paradigm represents a unique blend of ERP (event-related potential) analysis with ecological validity in a naturalistic driving context. Data Availability: Currently 15 of 18 subjects are available. Files are hosted at the BBCI (Berlin Brain-Computer Interface) archive. License: Creative Commons Attribution Non-Commercial No Derivatives (CC BY-NC-ND 4.0) 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	`NM000243`
Title	BNCI 2016-002 Emergency Braking during Simulated Driving dataset
Author (year)	`Haufe2016`
Canonical	—
Importable as	`NM000243`, `Haufe2016`
Year	2011
Authors	Stefan Haufe, Matthias S Treder, Manfred F Gugler, Max Sagebaum, Gabriel Curio, Benjamin Blankertz
License	CC-BY-NC-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: 15
Recordings: 15
Tasks: 1

Channels & sampling rate

Channels: 59
Sampling rate (Hz): 200.0
Duration (hours): 33.74497916666667

Electrode Layout#

Electrode layout — EEG · 59 sensors — 59 channels

Dataset Statistics#

Age distribution (n=15, range 30–30 yr)

30

Channel counts: 59 ch (n=15 recordings)

Sampling frequencies: 200.0 Hz (n=15 recordings)

Total recording duration: 33 h

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 NM000243 class to access this dataset programmatically.

class eegdash.dataset.NM000243(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Bases: EEGDashDataset

BNCI 2016-002 Emergency Braking during Simulated Driving dataset

Study:: nm000243 (NeMAR)
Author (year):: Haufe2016
Canonical:: —

Also importable as: NM000243, Haufe2016.

Modality: eeg; Experiment type: Motor; Subject type: Healthy. Subjects: 15; recordings: 15; 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/nm000243 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000243

Examples

>>> from eegdash.dataset import NM000243
>>> dataset = NM000243(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)