moabb.datasets.BNCI2025_002#

class moabb.datasets.BNCI2025_002(subjects=None, sessions=None, *, return_all_modalities=False)[source]#

Bases: BNCIBaseDataset

[source]

Dataset Snapshot

BNCI2025_002

Continuous 2D trajectory decoding from attempted movement: across-session performance in able-bodied and feasibility in a spinal cord injured participant

Motor Imagery, 3 classes (snakerun vs freerun vs eyerun)

AuthorsHannah S Pulferer, Brynja Ásgeirsdóttir, Valeria Mondini, Andreea I Sburlea, Gernot R Müller-Putz

🇦🇹 Institute of Neural Engineering, Graz University of Technology, Austria·2022·gernot.mueller@tugraz.at
Motor Imagery Code: BNCI2025-002 10 subjects 3 sessions 60 ch 200 Hz 3 classes 23.0 s trials CC BY 4.0

Class Labels: snakerun, freerun, eyerun

Read Paper Compare Similar Report Issue

Overview

BNCI 2025-002 Continuous 2D Trajectory Decoding dataset.

Dataset from

Dataset Description

This dataset contains EEG recordings from participants performing a continuous 2D trajectory decoding task using attempted movement. The study investigates continuous decoding of hand movement trajectories from EEG signals, with participants tracking a moving target on screen while their dominant arm is strapped to restrict actual motor output (simulating attempted movement conditions similar to paralyzed individuals).

The experimental paradigm includes both calibration and online decoding phases, with varying levels of EEG feedback (0%, 50%, 100%) to evaluate the impact of feedback on decoding performance.

Note: Only 2 of the original 20 participants' data is currently available on the BNCI server.

Participants

  • - 10 able-bodied subjects (5 male, 5 female)
  • Mean age 24 +/- 5 years, all right-handed
  • 4 had prior EEG experience
  • Location: Institute of Neural Engineering, Graz University of Technology, Austria

Recording Details

  • - Equipment: 64-channel actiCAP system (Brain Products GmbH)
  • Channels: 60 EEG + 4 EOG electrodes
  • Original sampling rate: 200 Hz
  • Electrode positions: 10-10 system with modifications (Fp1, Fp2, FT9, FT10 used as EOG; TP9, TP10 relocated to PPO1h, PPO2h)
  • Reference: Common average
  • Data synchronized using Lab Streaming Layer (LSL)

Experimental Procedure

Each session consists of:

  • - Calibration phase: 2 eye runs (38 trials, 8s each) + 4 snake runs (48 trials, 23s each)
  • Online phase with 3 perception conditions:
  • perc0: No EEG feedback (baseline)
  • perc50: 50% EEG feedback
  • perc100: 100% EEG feedback

Trial types:

  • - Snake runs: Tracking a moving white target with decorrelated x/y coordinates
  • Free runs: Tracing static shapes (diagonal/circle) at self-paced speed

Data Organization

  • - 3 sessions per subject (recorded over 5 days)
  • 3 perception levels per session (perc0, perc50, perc100)
  • Files named: {subject_id}_ses{session}_perc{level}.mat
Open in Overview tab →

Citation & Impact

Stimulus Protocol
../_images/BNCI2025_002.svg

23s task window per trial · 3-class motor imagery paradigm · 3 runs/session across 3 sessions

HED Event Tags
HED tags3/3 events annotated

Source: MOABB BIDS HED annotation mapping.

Experiment-structure
3
Label
3
snakerun
Experiment-structureLabel
freerun
Experiment-structureLabel
eyerun
Experiment-structureLabel

HED tree view

Tree · snakerun
├─ Experiment-structure
└─ Label
Tree · freerun
├─ Experiment-structure
└─ Label
Tree · eyerun
├─ Experiment-structure
└─ Label
Channel Summary
Total channels60
EEG60 (EEG)
EOG4
Montageaf7 af3 afz af4 af8 f7 f5 f3 f1 fz f2 f4 f6 f8 ft7 fc5 fc3 fc1 fcz fc2 fc4 fc6 ft8 t7 c5 c3 c1 cz c2 c4 c6 t8 tp7 cp5 cp3 cp1 cpz cp2 cp4 cp6 tp8 p7 p5 p3 p1 pz p2 p4 p6 p8 ppo1h ppo2h po7 po3 poz po4 po8 o1 oz o2
Sampling200 Hz
Referenceright mastoid
Filteranti-aliasing 25 Hz, notch 50 Hz
Notch / line50 Hz

This diagram is automatically generated from MOABB metadata. Please consult the original publication to confirm the experimental protocol details.

BNCI 2025-002 Continuous 2D Trajectory Decoding dataset.

Dataset from [1].

Dataset Description

This dataset contains EEG recordings from participants performing a continuous 2D trajectory decoding task using attempted movement. The study investigates continuous decoding of hand movement trajectories from EEG signals, with participants tracking a moving target on screen while their dominant arm is strapped to restrict actual motor output (simulating attempted movement conditions similar to paralyzed individuals).

The experimental paradigm includes both calibration and online decoding phases, with varying levels of EEG feedback (0%, 50%, 100%) to evaluate the impact of feedback on decoding performance.

Note: Only 2 of the original 20 participants’ data is currently available on the BNCI server.

Participants

  • 10 able-bodied subjects (5 male, 5 female)

  • Mean age 24 +/- 5 years, all right-handed

  • 4 had prior EEG experience

  • Location: Institute of Neural Engineering, Graz University of Technology, Austria

Recording Details

  • Equipment: 64-channel actiCAP system (Brain Products GmbH)

  • Channels: 60 EEG + 4 EOG electrodes

  • Original sampling rate: 200 Hz

  • Electrode positions: 10-10 system with modifications (Fp1, Fp2, FT9, FT10 used as EOG; TP9, TP10 relocated to PPO1h, PPO2h)

  • Reference: Common average

  • Data synchronized using Lab Streaming Layer (LSL)

Experimental Procedure

Each session consists of:

  • Calibration phase: 2 eye runs (38 trials, 8s each) + 4 snake runs (48 trials, 23s each)

  • Online phase with 3 perception conditions: - perc0: No EEG feedback (baseline) - perc50: 50% EEG feedback - perc100: 100% EEG feedback

Trial types:

  • Snake runs: Tracking a moving white target with decorrelated x/y coordinates

  • Free runs: Tracing static shapes (diagonal/circle) at self-paced speed

Data Organization

  • 3 sessions per subject (recorded over 5 days)

  • 3 perception levels per session (perc0, perc50, perc100)

  • Files named: {subject_id}_ses{session}_perc{level}.mat

References

[1]

Kobler, R. J., Almeida, I., Sburlea, A. I., & Muller-Putz, G. R. (2022). Continuous 2D trajectory decoding from attempted movement: across-session performance in able-bodied and feasibility in a spinal cord injured participant. Journal of Neural Engineering, 19(3), 036005. https://doi.org/10.1088/1741-2552/ac689f

from moabb.datasets import BNCI2025_002
dataset = BNCI2025_002()
data = dataset.get_data(subjects=[1])
print(data[1])

Dataset summary

#Subj

20

#Chan

64

#Classes

3

#Trials / class

varies

Trials length

8 s

Freq

200 Hz

#Sessions

3

#Runs

1

Total_trials

varies

Participants

  • Population: Healthy (able-bodied participants) + 1 SCI participant

  • Age: 24 years

  • Handedness: {‘right’: 10}

  • BCI experience: naive BCI users in terms of motor decoding; 4 had previous EEG experience

Equipment

  • Amplifier: actiCAP, Brain Products GmbH

  • Electrodes: EEG

  • Montage: af7 af3 afz af4 af8 f7 f5 f3 f1 fz f2 f4 f6 f8 ft7 fc5 fc3 fc1 fcz fc2 fc4 fc6 ft8 t7 c5 c3 c1 cz c2 c4 c6 t8 tp7 cp5 cp3 cp1 cpz cp2 cp4 cp6 tp8 p7 p5 p3 p1 pz p2 p4 p6 p8 ppo1h ppo2h po7 po3 poz po4 po8 o1 oz o2

  • Reference: right mastoid

Preprocessing

  • Data state: preprocessed

  • Bandpass filter: 0.18-3 Hz

  • Steps: anti-aliasing filter (25 Hz), notch filter (50 Hz), downsampling to 100 Hz, bad channel interpolation, eye artifact subtraction (SGEYESUB algorithm), removal of frontal (AF) row channels, high-pass filter (0.18 Hz), common average re-reference, pops and drifts attenuation (HEAR algorithm), low-pass filter (3 Hz), downsampling to 20 Hz

  • Re-reference: common average reference

Data Access

Experimental Protocol

  • Paradigm: motor imagery

  • Task type: continuous 2D trajectory decoding

  • Feedback: visual (green dot showing EEG-decoded trajectory position)

  • Stimulus: visual targets (white snake/shapes on black screen)

Notes

Added in version 1.3.0.

This dataset is designed for continuous decoding research, specifically for predicting 2D hand movement trajectories from EEG. Unlike classification-based motor imagery datasets, this dataset contains continuous trajectory labels suitable for regression-based decoders.

The paradigm “imagery” is used for compatibility with MOABB’s motor imagery processing pipelines, though the actual task involves attempted (rather than imagined) movements.

See also

BNCI2014_001

4-class motor imagery dataset

BNCI2014_004

2-class motor imagery dataset

__init__(subjects=None, sessions=None, *, return_all_modalities=False)[source]#

Initialize function for the BaseDataset.

property all_subjects#

Full list of subjects available in this dataset (unfiltered).

convert_to_bids(path=None, subjects=None, overwrite=False, format='EDF', verbose=None, generate_figures=False)[source]#

Convert the dataset to BIDS format.

Saves the raw EEG data in a BIDS-compliant directory structure. Unlike the caching mechanism (see CacheConfig), the files produced here do not contain a processing-pipeline hash (desc-<hash>) in their names, making the output a clean, shareable BIDS dataset.

Parameters:

  • path (str | Path | None) – Directory under which the BIDS dataset will be written. If None the default MNE data directory is used (same default as the rest of MOABB).

  • subjects (list of int | None) – Subject numbers to convert. If None, all subjects in subject_list are converted.

  • overwrite (bool) – If True, existing BIDS files for a subject are removed before saving. Default is False.

  • format (str) – The file format for the raw EEG data. Supported values are "EDF" (default), "BrainVision", and "EEGLAB".

  • verbose (str | None) – Verbosity level forwarded to MNE/MNE-BIDS.

  • generate_figures (bool) – If True, generate interactive neural signature HTML figures in {bids_root}/derivatives/neural_signatures/. Requires plotly (pip install moabb[interactive]). Default is False.

Returns:

bids_root – Path to the root of the written BIDS dataset.

Return type:

pathlib.Path

Examples

>>> from moabb.datasets import AlexMI
>>> dataset = AlexMI()
>>> bids_root = dataset.convert_to_bids(path='/tmp/bids', subjects=[1])

See also

CacheConfig

Cache configuration for get_data().

moabb.datasets.bids_interface.get_bids_root

Return the BIDS root path.

Notes

Added in version 1.5.

data_path(subject, path=None, force_update=False, update_path=None, verbose=None)[source]#

Return paths to data files for a single subject.

download(subject_list=None, path=None, force_update=False, update_path=None, accept=False, verbose=None)[source]#

Download all data from the dataset.

This function is only useful to download all the dataset at once.

Parameters:

  • subject_list (list of int | None) – List of subjects id to download, if None all subjects are downloaded.

  • path (None | str) – Location of where to look for the data storing location. If None, the environment variable or config parameter MNE_DATASETS_(dataset)_PATH is used. If it doesn’t exist, the “~/mne_data” directory is used. If the dataset is not found under the given path, the data will be automatically downloaded to the specified folder.

  • force_update (bool) – Force update of the dataset even if a local copy exists.

  • update_path (bool | None) – If True, set the MNE_DATASETS_(dataset)_PATH in mne-python config to the given path. If None, the user is prompted.

  • accept (bool) – Accept licence term to download the data, if any. Default: False

  • verbose (bool, str, int, or None) – If not None, override default verbose level (see mne.verbose()).

get_additional_metadata(subject: str, session: str, run: str) → None | DataFrame[source]#

Load additional metadata for a specific subject, session, and run.

This method is intended to be overridden by subclasses to provide additional metadata specific to the dataset. The metadata is typically loaded from an events.tsv file or similar data source.

Parameters:

  • subject (str) – The identifier for the subject.

  • session (str) – The identifier for the session.

  • run (str) – The identifier for the run.

Returns:

A DataFrame containing the additional metadata if available, otherwise None.

Return type:

None | pd.DataFrame

get_block_repetition(paradigm, subjects, block_list, repetition_list)[source]#

Select data for all provided subjects, blocks and repetitions.

subject -> session -> run -> block -> repetition

See also

BaseDataset.get_data

Parameters:

  • subjects (List of int) – List of subject number

  • block_list (List of int) – List of block number

  • repetition_list (List of int) – List of repetition number inside a block

Returns:

data – dict containing the raw data

Return type:

Dict

get_data(subjects=None, cache_config=None, process_pipeline=None)[source]#

Return the data corresponding to a list of subjects.

The returned data is a dictionary with the following structure:

data = {'subject_id' :
            {'session_id':
                {'run_id': run}
            }
        }

subjects are on top, then we have sessions, then runs. A sessions is a recording done in a single day, without removing the EEG cap. A session is constitued of at least one run. A run is a single contiguous recording. Some dataset break session in multiple runs.

Processing steps can optionally be applied to the data using the *_pipeline arguments. These pipelines are applied in the following order: raw_pipeline -> epochs_pipeline -> array_pipeline. If a *_pipeline argument is None, the step will be skipped. Therefore, the array_pipeline may either receive a mne.io.Raw or a mne.Epochs object as input depending on whether epochs_pipeline is None or not.

Parameters:

  • subjects (List of int) – List of subject number

  • cache_config (dict | CacheConfig) – Configuration for caching of datasets. See CacheConfig for details.

  • process_pipeline (Pipeline | None) – Optional processing pipeline to apply to the data. To generate an adequate pipeline, we recommend using moabb.utils.make_process_pipelines(). This pipeline will receive mne.io.BaseRaw objects. The steps names of this pipeline should be elements of StepType. According to their name, the steps should either return a mne.io.BaseRaw, a mne.Epochs, or a numpy.ndarray(). This pipeline must be “fixed” because it will not be trained, i.e. no call to fit will be made.

Returns:

data – dict containing the raw data

Return type:

Dict

property metadata: DatasetMetadata | None[source]#

Return structured metadata for this dataset.

Returns the DatasetMetadata object from the centralized catalog, or None if metadata is not available for this dataset.

Returns:

The metadata object containing acquisition parameters, participant demographics, experiment details, and documentation. Returns None if no metadata is registered for this dataset.

Return type:

DatasetMetadata | None

Examples

>>> from moabb.datasets import BNCI2014_001
>>> dataset = BNCI2014_001()
>>> dataset.metadata.participants.n_subjects
9
>>> dataset.metadata.acquisition.sampling_rate
250.0