moabb.datasets.Han2024Fatigue#

class moabb.datasets.Han2024Fatigue(subjects=None, sessions=None)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

Han2024Fatigue

SSVEP, 32 classes

AuthorsYuheng Han, Yufeng Ke, Ruiyan Wang, Tao Wang, Dong Ming

🇨🇳 Tianjin University, CN·2024
SSVEP Code: Han2024Fatigue 24 subjects 2 sessions 64 ch 1000 Hz 32 classes 2.0 s trials CC BY 4.0

Class Labels: 8, 8.5, 9, 9.5, 10, 10.5, 11, 11.5, ...

Read Paper Compare Similar Report Issue

Overview

SSVEP fatigue dataset with two frequency paradigms.

Dataset from

This dataset contains 64-channel EEG recordings from 24 healthy subjects (12 males, 12 females, aged 18-26) performing two SSVEP-BCI tasks:

  • - Low-frequency paradigm: 16 targets (8.0-15.5 Hz, 0.5 Hz step)
  • High-frequency paradigm: 16 targets (25.5-33.0 Hz, 0.5 Hz step)

Both paradigms used JFPM encoding with phases cycling through 0, 0.5pi, pi, 1.5pi in a 4x4 matrix layout.

The experiment consisted of two phases: training (6 blocks per frequency condition) and fatigue (24 blocks per condition). Each block contained 16 trials (2 s stimulation per trial).

EEG was recorded at 1000 Hz with a Synamps2 system (Neuroscan) and 64 channels. Each epoch spans 3000 samples (3 s at 1000 Hz).

Data is stored as [16, 64, 3000, N_blocks] matrices (targets, channels, timepoints, blocks) in per-subject zip files on Zenodo. Each subject has 4 separate files: low_frequency_train, low_frequency_fatigue, high_frequency_train, high_frequency_fatigue.

In MOABB, this is mapped as:

  • - Session '0': Training blocks (6 blocks per condition, 12 total)
  • Session '1': Fatigue blocks (24 blocks per condition, 48 total)
Open in Overview tab →

Citation & Impact

Stimulus Protocol
../_images/Han2024Fatigue.svg

2s task window per trial · 32-class ssvep paradigm · 1 runs/session across 2 sessions

HED Event Tags
HED tags32/32 events annotated

Source: MOABB BIDS HED annotation mapping.

Experimental-stimulus
32
Label
32
Sensory-event
32
Visual-presentation
32
8
Sensory-eventExperimental-stimulusVisual-presentationLabel
8.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
9
Sensory-eventExperimental-stimulusVisual-presentationLabel
9.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
10
Sensory-eventExperimental-stimulusVisual-presentationLabel
10.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
11
Sensory-eventExperimental-stimulusVisual-presentationLabel
11.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
12
Sensory-eventExperimental-stimulusVisual-presentationLabel
12.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
13
Sensory-eventExperimental-stimulusVisual-presentationLabel
13.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
14
Sensory-eventExperimental-stimulusVisual-presentationLabel
14.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
15
Sensory-eventExperimental-stimulusVisual-presentationLabel
15.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
25.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
26
Sensory-eventExperimental-stimulusVisual-presentationLabel
26.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
27
Sensory-eventExperimental-stimulusVisual-presentationLabel
27.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
28
Sensory-eventExperimental-stimulusVisual-presentationLabel
28.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
29
Sensory-eventExperimental-stimulusVisual-presentationLabel
29.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
30
Sensory-eventExperimental-stimulusVisual-presentationLabel
30.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
31
Sensory-eventExperimental-stimulusVisual-presentationLabel
31.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
32
Sensory-eventExperimental-stimulusVisual-presentationLabel
32.5
Sensory-eventExperimental-stimulusVisual-presentationLabel
33
Sensory-eventExperimental-stimulusVisual-presentationLabel

HED tree view

Tree · 8
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 8.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 9
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 9.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 10
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 10.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 11
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 11.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 12
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 12.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 13
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 13.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 14
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 14.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 15
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 15.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 25.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 26
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 26.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 27
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 27.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 28
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 28.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 29
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 29.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 30
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 30.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 31
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 31.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 32
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 32.5
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Tree · 33
├─ Sensory-event
├─ Experimental-stimulus
├─ Visual-presentation
└─ Label
Channel Summary
Total channels64
EEG64
Montage10-05
Sampling1000 Hz
ReferenceCz
Filter{'bandpass_hz': [0.15, 200.0]}
Notch / line50 Hz

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

SSVEP fatigue dataset with two frequency paradigms.

Dataset from [1].

This dataset contains 64-channel EEG recordings from 24 healthy subjects (12 males, 12 females, aged 18-26) performing two SSVEP-BCI tasks:

  • Low-frequency paradigm: 16 targets (8.0-15.5 Hz, 0.5 Hz step)

  • High-frequency paradigm: 16 targets (25.5-33.0 Hz, 0.5 Hz step)

Both paradigms used JFPM encoding with phases cycling through 0, 0.5*pi, pi, 1.5*pi in a 4x4 matrix layout.

The experiment consisted of two phases: training (6 blocks per frequency condition) and fatigue (24 blocks per condition). Each block contained 16 trials (2 s stimulation per trial).

EEG was recorded at 1000 Hz with a Synamps2 system (Neuroscan) and 64 channels. Each epoch spans 3000 samples (3 s at 1000 Hz).

Note

Channel selection is critical for this dataset. Using all 64 channels with CCA-based methods yields near-chance accuracy because the high channel-to-sample ratio causes overfitting. The paper uses 9 occipital channels (PO7, PO3, POz, PO4, PO8, O1, Oz, O2, and one additional) and achieves >90% with TRCA. Users should pick occipital channels before classification.

Additionally, the cross-session evaluation (training on alert session ‘0’, testing on fatigued session ‘1’) is a challenging domain-shift problem that standard CCA/TRCA may not handle well without fatigue-aware strategies.

Data is stored as [16, 64, 3000, N_blocks] matrices (targets, channels, timepoints, blocks) in per-subject zip files on Zenodo. Each subject has 4 separate files: low_frequency_train, low_frequency_fatigue, high_frequency_train, high_frequency_fatigue.

In MOABB, this is mapped as: - Session ‘0’: Training blocks (6 blocks per condition, 12 total) - Session ‘1’: Fatigue blocks (24 blocks per condition, 48 total)

References

[1]

Y. Han, Y. Ke, R. Wang, T. Wang, and D. Ming, “Enhancing SSVEP-BCI Performance Under Fatigue State Using Dynamic Stopping Strategy,” IEEE Trans. Neural Syst. Rehab. Eng., vol. 32, pp. 1407-1415, 2024. DOI: 10.1109/TNSRE.2024.3380635

from moabb.datasets import Han2024Fatigue
dataset = Han2024Fatigue()
data = dataset.get_data(subjects=[1])
print(data[1])

Dataset summary

#Subj

24

#Chan

64

#Classes

32

#Trials / class

6-24

Trials length

2 s

Freq

1000 Hz

#Sessions

2

Participants

  • Population: healthy

Equipment

  • Amplifier: Synamps2 (Neuroscan)

  • Montage: standard_1005

  • Reference: Cz

Preprocessing

  • Data state: epoched

Data Access

Experimental Protocol

  • Paradigm: ssvep

  • Task type: gaze-shifting

  • Feedback: none

  • Stimulus: JFPM visual flicker

__init__(subjects=None, sessions=None)[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)[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.

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]#

Get path to local copy of a subject data.

Parameters:

  • subject (int) – Number of subject to use

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

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

Returns:

path – Local path to the given data file. This path is contained inside a list of length one, for compatibility.

Return type:

list of str

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