EEGdash›NeMAR›NM000325

Iss. 325 · 15 subjects · 60 recordings · ODC-BY

Dataset Brief · Wang2025

NM000325: eeg dataset, 15 subjects#

Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4)

Access recordings and metadata through EEGDash.

Citation: Jiaheng Wang, Lin Yao, Yueming Wang (2025). Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4). 10.82901/nemar.nm000325

Modality: eeg Subjects: 15 Recordings: 60 License: ODC-BY Source: nemar

Metadata: Complete (100%)

15-participant EEG dataset — Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4).

Data & curation Jiaheng Wang · Lin Yao · Yueming Wang
Senior author Yueming Wang
Year 2025 · Distributed via NeMAR

EEG · 62 ch256 HzBIDS 1.9.0Task · imagery2 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 NM000325

dataset = NM000325(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 = NM000325(cache_dir="./data", subject="01")

Advanced query

dataset = NM000325(
    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{nm000325,
  title = {Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4)},
  author = {Jiaheng Wang and Lin Yao and Yueming Wang},
  doi = {10.82901/nemar.nm000325},
  url = {https://doi.org/10.82901/nemar.nm000325},
}

§ 02Study · The README

About This Dataset#

Four-class motor imagery dataset (ZJU-MI-EEG / MI4) [1]_.

Code: Wang2025

Paradigm: imagery DOI: 10.1109/TNSRE.2025.3591254 Subjects: 15 Sessions per subject: 2 Events: left_hand=1, right_hand=2, tongue=3, feet=4 Trial interval: [0, 3.99609375] s Runs per session: 2 File format: MAT

DOI

Wang2025

Acquisition

Sampling rate: 256.0 Hz Number of channels: 62 Channel types: eeg=62 Channel names: Fp1, Fpz, Fp2, AF7, AF3, 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, PO7, PO3, POz, PO4, PO8, O1, Oz, O2, F9, F10

View full README

DOI

Wang2025

Acquisition

Sampling rate: 256.0 Hz Number of channels: 62 Channel types: eeg=62 Channel names: Fp1, Fpz, Fp2, AF7, AF3, 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, PO7, PO3, POz, PO4, PO8, O1, Oz, O2, F9, F10 Montage: 10-10 Hardware: g.USBamp (g.tec medical engineering, Austria), 62 channels Line frequency: 50.0 Hz Online filters: 0.1 Hz high-pass

Participants

Number of subjects: 15 Health status: healthy Age: mean=24.0, std=5.1 Gender distribution: male=12, female=3 BCI experience: 10 BCI-naive; 5 without online BCI experience

Experimental Protocol

Paradigm: imagery Number of classes: 4 Class labels: left_hand, right_hand, tongue, feet Trial duration: 4.0 s Trials per class: left_hand=200, right_hand=200, tongue=200, feet=200 Study design: Cued four-class motor imagery (left hand, right hand, tongue, both feet) over two days, each with a 240-trial calibration run and a 160-trial online feedback run. Feedback type: visual Stimulus type: visual Synchronicity: cue-based Mode: online Training/test split: True

HED Event Annotations

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

tongue

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

feet

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

Paradigm-Specific Parameters

Detected paradigm: motor_imagery Imagery tasks: left_hand, right_hand, tongue, feet Imagery duration: 4.0 s

Tags

Pathology: healthy Modality: Motor Type: Motor Imagery

Documentation

Description: Four-class motor imagery EEG from 15 healthy subjects (left hand, right hand, tongue, both feet) recorded with 62 channels at 256 Hz over two days of calibration and online feedback sessions. DOI: 10.1109/TNSRE.2025.3591254 License: ODC-BY Investigators: Jiaheng Wang, Lin Yao, Yueming Wang Institution: Zhejiang University Country: CN Repository: Hugging Face Data URL: https://huggingface.co/datasets/Jiaheng-Wang/ZJU-MI-EEG Publication year: 2025 Keywords: motor imagery, BCI, brain-computer interface, EEG, four-class

References

Wang, J., Yao, L., and Wang, Y. (2025). Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 33, 2834-2846. DOI: 10.1109/TNSRE.2025.3591254 Notes .. 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.

NEMAR Metadata#

[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000325-blue)](https://doi.org/10.82901/nemar.nm000325) Wang2025 ======== Four-class motor imagery dataset (ZJU-MI-EEG / MI4) [1]_. Dataset Overview —————-

Code: Wang2025 Paradigm: imagery DOI: 10.1109/TNSRE.2025.3591254 Subjects: 15 Sessions per subject: 2 Events: left_hand=1, right_hand=2, tongue=3, feet=4 Trial interval: [0, 3.99609375] s Runs per session: 2 File format: MAT

Acquisition#

Sampling rate: 256.0 Hz Number of channels: 62 Channel types: eeg=62 Channel names: Fp1, Fpz, Fp2, AF7, AF3, 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, PO7, PO3, POz, PO4, PO8, O1, Oz, O2, F9, F10 Montage: 10-10 Hardware: g.USBamp (g.tec medical engineering, Austria), 62 channels Line frequency: 50.0 Hz Online filters: 0.1 Hz high-pass

Participants#

Number of subjects: 15 Health status: healthy Age: mean=24.0, std=5.1 Gender distribution: male=12, female=3 BCI experience: 10 BCI-naive; 5 without online BCI experience

Experimental Protocol#

Paradigm: imagery Number of classes: 4 Class labels: left_hand, right_hand, tongue, feet Trial duration: 4.0 s Trials per class: left_hand=200, right_hand=200, tongue=200, feet=200 Study design: Cued four-class motor imagery (left hand, right hand, tongue, both feet) over two days, each with a 240-trial calibration run and a 160-trial online feedback run. Feedback type: visual Stimulus type: visual Synchronicity: cue-based Mode: online Training/test split: True

HED Event Annotations#

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

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

└─ Imagine, Move, Tongue

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

└─ Imagine, Move, Foot

Paradigm-Specific Parameters#

Detected paradigm: motor_imagery Imagery tasks: left_hand, right_hand, tongue, feet Imagery duration: 4.0 s

Tags#

Pathology: healthy Modality: Motor Type: Motor Imagery

Documentation#

Description: Four-class motor imagery EEG from 15 healthy subjects (left hand, right hand, tongue, both feet) recorded with 62 channels at 256 Hz over two days of calibration and online feedback sessions. DOI: 10.1109/TNSRE.2025.3591254 License: ODC-BY Investigators: Jiaheng Wang, Lin Yao, Yueming Wang Institution: Zhejiang University Country: CN Repository: Hugging Face Data URL: https://huggingface.co/datasets/Jiaheng-Wang/ZJU-MI-EEG Publication year: 2025 Keywords: motor imagery, BCI, brain-computer interface, EEG, four-class

References#

Wang, J., Yao, L., and Wang, Y. (2025). Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 33, 2834-2846. DOI: 10.1109/TNSRE.2025.3591254 Notes .. 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.

License: ODC-BY

Authors:

Jiaheng Wang
Lin Yao
Yueming Wang

Versions:

Version	DOI	Released
`current`	10.82901/nemar.nm000325

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Age distribution by gender (n=15, range 24–24 yr, mean 24.0 yr)

20

Other · 15

Channel counts: 62 ch (n=60 recordings)

Sampling frequencies: 256.0 Hz (n=60 recordings)

Total recording duration: 16 h 39 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 62 ch · EEG · 256 Hz · 15 subjects, 60 recordings

Live trace viewer — sub-7 · ses-0 · task-imagery · run-1

Showing one representative recording out of 15 subjects and 60 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 · 62 sensors — 62 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.NM000325(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)—

Canonical—

Importable asNM000325

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

class eegdash.dataset.NM000325(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4)

Study:: nm000325 (NeMAR)
Author (year):: —
Canonical:: —

Also importable as: NM000325.

Modality: eeg; Subject type: Unknown. Subjects: 15; recordings: 60; 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/nm000325 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000325 DOI: https://doi.org/10.82901/nemar.nm000325

Examples

>>> from eegdash.dataset import NM000325
>>> dataset = NM000325(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 — NM000325.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 nm000325 to reproduce the tutorial on this dataset.

Citation

Jiaheng Wang, Lin Yao, Yueming Wang (2025). Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4). 10.82901/nemar.nm000325

Provenance

¹Contributed to nemar in BIDS format.

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

³Persistent identifier: 10.82901/nemar.nm000325.

Related & sibling datasets

NM000291EEG · 14 subj NM000294EEG · 12 subj NM000300EEG · 10 subj NM000315EEG · 10 subj NM000306EEG · 15 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · events.json · channels · eeg.json

Provenance

ODC-BY · 10.82901/nemar.nm000325

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`NM000325`
Title	Wang2025: Four-class motor imagery dataset (ZJU-MI-EEG / MI4)
Author (year)	—
Canonical	—
Importable as	`NM000325`
Year	2025
Authors	Jiaheng Wang, Lin Yao, Yueming Wang
License	ODC-BY
Citation / DOI	10.82901/nemar.nm000325
Source links	OpenNeuro \| NeMAR \| Source URL

NM000325: eeg dataset, 15 subjects#

Quickstart#

About This Dataset#

NEMAR Metadata#

Acquisition#

Participants#

Experimental Protocol#

HED Event Annotations#

Paradigm-Specific Parameters#

Tags#

Documentation#

References#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#