EEGdash›NeMAR›NM000308

Iss. 308 · 2 subjects · 8 recordings · CC-BY-4.0

Dataset Brief · NeuroTUMBCI2025

NM000308: eeg dataset, 2 subjects#

NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI

Access recordings and metadata through EEGDash.

Citation: Isabel W. Tscherniak, Niels C. Thiemann, Ana McWhinnie-Fernandez, Iustin Curcean, Leon L. J. Jokinen, Sadat Hodzic, Thomas E. Huber, Daniel Pavlov, Manuel Methasani, Pietro Marcolongo, Glenn V. Krafczyk, Oscar Osvaldo Soto Rivera, Thien Le, Flaminia Pallotti, Enrico A. Fazzi (2025). NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI. 10.82901/nemar.nm000308

Modality: eeg Subjects: 2 Recordings: 8 License: CC-BY-4.0 Source: nemar

Metadata: Complete (100%)

2-participant EEG dataset — NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI.

Data & curation Isabel W. Tscherniak · Niels C. Thiemann · Ana McWhinnie-Fernandez · Iustin Curcean · Leon L. J. Jokinen · Sadat Hodzic · …
Senior author Enrico A. Fazzi
Year 2025 · Distributed via NeMAR

EEG · 24 ch250 HzBIDS 1.9.0Task · imagery5 sessions

Layer 01Study

What was asked

Hypothesis, independent & dependent variables, paradigm, cohort, and the editorial caveats around what the recordings can and cannot answer.

Layer 02Signal · BIDS

What was recorded

Sidecars, channels & electrodes, coordinate system, event semantics, and quality stats from the NEMAR pipeline when available.

Layer 03Training · ML

What you can train on

Recommended access modes — MNE Raw, braindecode windows, PyTorch DataLoader — plus the targets the metadata makes addressable.

§ 01Access · Get started

Quickstart#

Get Started

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000308

dataset = NM000308(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 = NM000308(cache_dir="./data", subject="01")

Advanced query

dataset = NM000308(
    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{nm000308,
  title = {NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI},
  author = {Isabel W. Tscherniak and Niels C. Thiemann and Ana McWhinnie-Fernandez and Iustin Curcean and Leon L. J. Jokinen and Sadat Hodzic and Thomas E. Huber and Daniel Pavlov and Manuel Methasani and Pietro Marcolongo and Glenn V. Krafczyk and Oscar Osvaldo Soto Rivera and Thien Le and Flaminia Pallotti and Enrico A. Fazzi},
  doi = {10.82901/nemar.nm000308},
  url = {https://doi.org/10.82901/nemar.nm000308},
}

§ 02Study · The README

About This Dataset#

Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI [1]_, [2]_.

Code: NeuroTUMBCI2025

Paradigm: imagery DOI: 10.5281/zenodo.18087806 Subjects: 2 Sessions per subject: 3 Events: rest=1, left_hand=2, right_hand=3, feet=4 Trial interval: (0, 3) s File format: XDF

DOI

NeuroTUMBCI2025

Acquisition

Sampling rate: 250.0 Hz Number of channels: 24 Channel types: eeg=24 Channel names: Fp1, Fp2, Fz, F1, F2, F3, F4, FC1, FC2, FC3, FC4, Cz, C1, C2, C3, C4, CPz, CP1, CP2, Pz, P3, P4, M1, M2

View full README

DOI

NeuroTUMBCI2025

Acquisition

Sampling rate: 250.0 Hz Number of channels: 24 Channel types: eeg=24 Channel names: Fp1, Fp2, Fz, F1, F2, F3, F4, FC1, FC2, FC3, FC4, Cz, C1, C2, C3, C4, CPz, CP1, CP2, Pz, P3, P4, M1, M2 Montage: 10-20 Hardware: Smarting mobi (mBrainTrain), 24-channel, wireless (Bluetooth 2.1) Line frequency: 50.0 Hz Cap manufacturer: mBrainTrain Cap model: Smarting mobi

Participants

Number of subjects: 2 Health status: patients Clinical population: one tetraplegic pilot and one able-bodied participant

Experimental Protocol

Paradigm: imagery Number of classes: 4 Class labels: rest, left_hand, right_hand, feet Trial duration: 3.0 s Study design: Arrow-cue paradigm with a subject-specific set of three mental tasks (rest, hand and/or leg motor imagery). Each trial: 3 s reset (fixation cross), 1 s directional cue, 3 s blackscreen execution, 3 s reset. Feedback type: none Stimulus type: visual arrow/circle cues Stimulus modalities: visual Synchronicity: cue-based Mode: offline Instructions: On a black screen the pilot performs the cued mental task for 3 s following a 1 s directional cue.

HED Event Annotations

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

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

left_hand

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

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

Preprocessing

Data state: raw Preprocessing applied: False

Tags

Modality: Motor Type: Motor Imagery

Documentation

Description: Mobile EEG motor imagery dataset from two pilots recorded during the development of the neuroTUM BCI system for the 2024 Cybathlon BCI race. DOI: 10.5281/zenodo.18087806 License: CC-BY-4.0 Investigators: Isabel W. Tscherniak, Niels C. Thiemann, Ana McWhinnie-Fernandez, Iustin Curcean, Leon L. J. Jokinen, Sadat Hodzic, Thomas E. Huber, Daniel Pavlov, Manuel Methasani, Pietro Marcolongo, Glenn V. Krafczyk, Oscar Osvaldo Soto Rivera, Thien Le, Flaminia Pallotti, Enrico A. Fazzi Contact: team@neurotum.com Institution: Technical University of Munich / neuroTUM e.V. Address: Munich, Germany Country: DE Repository: Zenodo Data URL: https://doi.org/10.5281/zenodo.18087806 Publication year: 2025

Abstract

Two-pilot mobile EEG motor imagery dataset (24-channel Smarting mobi, 250 Hz) collected for the neuroTUM 2024 Cybathlon BCI race, using an arrow-cue paradigm with a subject-specific set of three classes (rest plus hand and/or leg motor imagery).

References

neuroTUM e.V. (2025). neuroTUM-BCI: Cybathlon Dataset. Zenodo. DOI: https://doi.org/10.5281/zenodo.18087806 Tscherniak, I. W., Thiemann, N. C., McWhinnie-Fernandez, A., et al. (2025). Improving motor imagery decoding methods for an EEG-based mobile brain-computer interface in the context of the 2024 Cybathlon. arXiv (v1 November 2025; v4 March 2026). DOI: https://doi.org/10.48550/arXiv.2511.23384 Notes XDF files are read with MOABB’s built-in reader; no optional XDF dependency is required. Four labels describe the union of subject-specific three-class tasks, not a four-class task available for every participant. Subject 1 supplies five sessions and subject 2 supplies three; the catalog reports the minimum session count. .. versionadded:: 1.8 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 1.8.0dev0 (Mother of All BCI Benchmarks) NeuroTechX/moabb

Ethics

Ethics approval: the data analysed in this deposit were collected under the ethics approval obtained by the original investigators and reported in the primary publication cited above (see References/Documentation sections of this README). Participants gave informed consent in the source study. No new human-subject data were collected during this BIDS re-release; this NEMAR record only reformats the published source data into BIDS via MOABB.

Please consult the primary publication for the exact IRB/ethics committee reference.

Ethics

Informed consent was obtained prior to data collection, usage, and publication (neuroTUM e.V. 2025, Zenodo DOI 10.5281/zenodo.18087806). The source does not name the approving ethics committee.

Verbatim from the source:

Informed consent was obtained prior to data collection, usage, and publication.

Source: Zenodo record 18087806 description (https://zenodo.org/records/18087806).

Note: The source statement is incomplete (no committee named); defers to the primary publication for the full ethics record.

NEMAR Metadata#

[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000308-blue)](https://doi.org/10.82901/nemar.nm000308) NeuroTUMBCI2025 =============== Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI [1]_, [2]_. Dataset Overview —————-

Code: NeuroTUMBCI2025 Paradigm: imagery DOI: 10.5281/zenodo.18087806 Subjects: 2 Sessions per subject: 3 Events: rest=1, left_hand=2, right_hand=3, feet=4 Trial interval: (0, 3) s File format: XDF

Acquisition#

Sampling rate: 250.0 Hz Number of channels: 24 Channel types: eeg=24 Channel names: Fp1, Fp2, Fz, F1, F2, F3, F4, FC1, FC2, FC3, FC4, Cz, C1, C2, C3, C4, CPz, CP1, CP2, Pz, P3, P4, M1, M2 Montage: 10-20 Hardware: Smarting mobi (mBrainTrain), 24-channel, wireless (Bluetooth 2.1) Line frequency: 50.0 Hz Cap manufacturer: mBrainTrain Cap model: Smarting mobi

Participants#

Number of subjects: 2 Health status: patients Clinical population: one tetraplegic pilot and one able-bodied participant

Experimental Protocol#

Paradigm: imagery Number of classes: 4 Class labels: rest, left_hand, right_hand, feet Trial duration: 3.0 s Study design: Arrow-cue paradigm with a subject-specific set of three mental tasks (rest, hand and/or leg motor imagery). Each trial: 3 s reset (fixation cross), 1 s directional cue, 3 s blackscreen execution, 3 s reset. Feedback type: none Stimulus type: visual arrow/circle cues Stimulus modalities: visual Synchronicity: cue-based Mode: offline Instructions: On a black screen the pilot performs the cued mental task for 3 s following a 1 s directional cue.

HED Event Annotations#

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

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

left_hand
├─ Sensory-event, Experimental-stimulus, Visual-presentation └─ Agent-action

└─ Imagine
├─ Move └─ Left, Hand

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

Preprocessing#

Data state: raw Preprocessing applied: False

Tags#

Modality: Motor Type: Motor Imagery

Documentation#

Description: Mobile EEG motor imagery dataset from two pilots recorded during the development of the neuroTUM BCI system for the 2024 Cybathlon BCI race. DOI: 10.5281/zenodo.18087806 License: CC-BY-4.0 Investigators: Isabel W. Tscherniak, Niels C. Thiemann, Ana McWhinnie-Fernandez, Iustin Curcean, Leon L. J. Jokinen, Sadat Hodzic, Thomas E. Huber, Daniel Pavlov, Manuel Methasani, Pietro Marcolongo, Glenn V. Krafczyk, Oscar Osvaldo Soto Rivera, Thien Le, Flaminia Pallotti, Enrico A. Fazzi Contact: team@neurotum.com Institution: Technical University of Munich / neuroTUM e.V. Address: Munich, Germany Country: DE Repository: Zenodo Data URL: https://doi.org/10.5281/zenodo.18087806 Publication year: 2025

Abstract#

Two-pilot mobile EEG motor imagery dataset (24-channel Smarting mobi, 250 Hz) collected for the neuroTUM 2024 Cybathlon BCI race, using an arrow-cue paradigm with a subject-specific set of three classes (rest plus hand and/or leg motor imagery). References ———- neuroTUM e.V. (2025). neuroTUM-BCI: Cybathlon Dataset. Zenodo. DOI: https://doi.org/10.5281/zenodo.18087806 Tscherniak, I. W., Thiemann, N. C., McWhinnie-Fernandez, A., et al. (2025). Improving motor imagery decoding methods for an EEG-based mobile brain-computer interface in the context of the 2024 Cybathlon. arXiv (v1 November 2025; v4 March 2026). DOI: https://doi.org/10.48550/arXiv.2511.23384 Notes XDF files are read with MOABB’s built-in reader; no optional XDF dependency is required. Four labels describe the union of subject-specific three-class tasks, not a four-class task available for every participant. Subject 1 supplies five sessions and subject 2 supplies three; the catalog reports the minimum session count. .. versionadded:: 1.8 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 1.8.0dev0 (Mother of All BCI Benchmarks) NeuroTechX/moabb Ethics —— Ethics approval: the data analysed in this deposit were collected under the ethics approval obtained by the original investigators and reported in the primary publication cited above (see References/Documentation sections of this README). Participants gave informed consent in the source study. No new human-subject data were collected during this BIDS re-release; this NEMAR record only reformats the published source data into BIDS via MOABB. Please consult the primary publication for the exact IRB/ethics committee reference. ## Ethics Informed consent was obtained prior to data collection, usage, and publication (neuroTUM e.V. 2025, Zenodo DOI 10.5281/zenodo.18087806). The source does not name the approving ethics committee. Verbatim from the source: > Informed consent was obtained prior to data collection, usage, and publication. Source: Zenodo record 18087806 description (https://zenodo.org/records/18087806). Note: The source statement is incomplete (no committee named); defers to the primary publication for the full ethics record.

License: CC-BY-4.0

Authors:

Isabel W. Tscherniak
Niels C. Thiemann
Ana McWhinnie-Fernandez
Iustin Curcean
Leon L. J. Jokinen
… and 10 more

Versions:

Version	DOI	Released
`current`	10.82901/nemar.nm000308

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Channel counts: 24 ch (n=8 recordings)

Sampling frequencies: 250.0 Hz (n=8 recordings)

Total recording duration: 3 h 6 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 24 ch · EEG · 250 Hz · 2 subjects, 8 recordings

Live trace viewer — sub-1 · ses-0 · task-imagery · run-0

Showing one representative recording out of 2 subjects and 8 recordings in this dataset. Browse the full set on OpenNeuro; drop any other _eeg.{set,edf,bdf,vhdr} file onto the viewer (or pass ?eeg=<url>) to inspect it.

Electrode layout — EEG · 24 sensors — 24 channels

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

§ 05Manifest · BIDS tree

Manifest#

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.

Recordings—

Files—

Subjects—

Modalities—

Click to load file structure…

§ 06API · Programmatic access

API Reference#

Signature

eegdash.dataset

class

eegdash.dataset.NM000308(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)—

Canonical—

Importable asNM000308

Sourceeegdash/dataset/registry.py · [source ↗]

class eegdash.dataset.NM000308(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI

Study:: nm000308 (NeMAR)
Author (year):: —
Canonical:: —

Also importable as: NM000308.

Modality: eeg; Subject type: Unknown. Subjects: 2; recordings: 8; 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/nm000308 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000308 DOI: https://doi.org/10.82901/nemar.nm000308

Examples

>>> from eegdash.dataset import NM000308
>>> dataset = NM000308(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)

Parameters:

path (str) –

Directory in which subdirectories are created to store
-raw.fif | -epo.fif and .json files to.
overwrite (bool) – Whether to delete old subdirectories that will be saved to in this call.
offset (int) – If provided, the integer is added to the id of the dataset in the concat. This is useful in the setting of very large datasets, where one dataset has to be processed and saved at a time to account for its original position.

Access modesMNE → braindecode → PyTorch → ML

.rawMNE Raw object — standard tools (filter, epoch, ICA, plot_psd).mne

BaseConcatDatasetEach record is a lazy BaseDataset from braindecode — windowed via create_windows_from_events.braindecode

DataLoaderWraps the windowed dataset into a PyTorch DataLoader; supports parallel workers and on-the-fly augmentations.pytorch

Zarr cacheOptional braindecode Zarr mirror for fast resume; persisted to cache_dir.zarr

Hugging FaceNo per-dataset mirror published yet — browse the EEGDash org listing for sibling datasets. See the datasets loader API.huggingface

Croissant 1.0Machine-readable JSON-LD descriptor — NM000308.croissant.json (MLCommons schema, ingestible by PyTorch / TensorFlow / JAX).mlcommons

Examples using EEGDashcurated · start here

Find datasets with the EEGDash APIQuery the catalogue, filter by task or modality, list candidates.

Load one EEG recordingResolve a single record to an MNE Raw with channels and events.

EEG recording to PyTorch DataLoaderWrap braindecode windows in a DataLoader for model training.

Preprocess EEG and create windowsFilter, resample, epoch — and persist the windowed dataset.

Save and reload prepared dataCache a windowed dataset to disk and reattach it without recompute.

Download a dataset locallyPrefetch BIDS files to a local cache and validate the layout.

Swap any load_dataset(...) call for nm000308 to reproduce the tutorial on this dataset.

Citation

Isabel W. Tscherniak, Niels C. Thiemann, Ana McWhinnie-Fernandez, Iustin Curcean, Leon L. J. Jokinen, … (2025). NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI. 10.82901/nemar.nm000308

Provenance

¹Contributed to nemar in BIDS format.

²Curated & ingested by the EEGDash catalog; see CITATION.cff for canonical reference.

³Persistent identifier: 10.82901/nemar.nm000308.

Related & sibling datasets

NM000150EEG NM000300EEG · 10 subj NM000302EEG · 6 subj NM000291EEG · 14 subj NM000315EEG · 10 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

CC-BY-4.0 · 10.82901/nemar.nm000308

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000308`
Title	NeuroTUMBCI2025: Motor imagery dataset from the neuroTUM 2024 Cybathlon BCI
Author (year)	—
Canonical	—
Importable as	`NM000308`
Year	2025
Authors	Isabel W. Tscherniak, Niels C. Thiemann, Ana McWhinnie-Fernandez, Iustin Curcean, Leon L. J. Jokinen, Sadat Hodzic, Thomas E. Huber, Daniel Pavlov, Manuel Methasani, Pietro Marcolongo, Glenn V. Krafczyk, Oscar Osvaldo Soto Rivera, Thien Le, Flaminia Pallotti, Enrico A. Fazzi
License	CC-BY-4.0
Citation / DOI	10.82901/nemar.nm000308
Source links	OpenNeuro \| NeMAR \| Source URL

NM000308: eeg dataset, 2 subjects#

Quickstart#

About This Dataset#

NEMAR Metadata#

Acquisition#

Participants#

Experimental Protocol#

HED Event Annotations#

Preprocessing#

Tags#

Documentation#

Abstract#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#