moabb.datasets.MAMEM2

class moabb.datasets.MAMEM2(subjects=None, sessions=None)

Bases: BaseMAMEM

[source]

Dataset Snapshot

MAMEM2

SSVEP, 5 classes (6.66 vs 7.50 vs 8.57 vs 10.00 vs 12.00)

AuthorsVangelis P. Oikonomou, Georgios Liaros, Kostantinos Georgiadis, Elisavet Chatzilari, Katerina Adam, Spiros Nikolopoulos, Ioannis Kompatsiaris

🇬🇷 Centre for Research and Technology Hellas (CERTH), GR·2016

SSVEP Code: MAMEM2 11 subjects 1 session 256 ch 250 Hz 5 classes 5.0 s trials ODC-By 1.0

Class Labels: 6.66, 7.50, 8.57, 10.00, 12.00

Quickstart Read Paper Compare Similar Report Issue

Overview

SSVEP MAMEM 2 dataset.

Dataset from Data acquisition details are documented in

EEG signals with 256 channels captured from 11 subjects executing a SSVEP-based experimental protocol. Five different frequencies (6.66, 7.50, 8.57, 10.00 and 12.00 Hz) have been used for the visual stimulation,and the EGI 300 Geodesic EEG System, using a stimulation, HydroCel Geodesic Sensor Net (HCGSN) and a sampling rate of 250 Hz has been used for capturing the signals.

Subjects were exposed to flickering lights from five violet boxes with frequencies [6.66Hz, 7.5Hz, 8.57Hz, 10Hz, and 12Hz] simultaneously. Prior to and during each flicking window, one of the boxes is marked by a yellow arrow indicating the box to be focused on by the subject. 256 channel EEG recordings were captured.

From, each subject underwent a single adaptation period before the first of their 5 sessions (unlike experiment 1 in which each session began with its own adaptation period). In the adaptation period, the subject is exposed to ten 5-second flickering windows from the five boxes simultaneously, with the target frequencies specified in the FREQUENCIES2.txt file under 'adaptation'. The flickering windows are separated by 5 seconds of rest, and the 100s adaptation period precedes the first session by 30 seconds.

Each session consisted of the following: For the series of frequencies specified in the FREQUENCIES2.txt file under 'sessions': A 5 second window with all boxes flickering and the subject focusing on the specified frequency's marked box, followed by 5 seconds of rest. This gives a total of 25 flickering windows for each session (not including the first adaptation period). Five minutes of rest before the next session (not including the 5th session).

The order of chosen frequencies is the same for each session, although there are small-moderate variations in the actual frequencies of each individual window. Note: Each 'session' in experiment 1 includes an adaptation period, unlike experiment 2 and 3 where each subject undergoes only one adaptation period before their first 'session'.

Waveforms and Annotations File names are in the form T0NNn, where NN is the subject number and n is a - e for the session letter or x for the adaptation period. Each session lasts in the order of several minutes and is sampled at 250Hz. Each session and adaptation period has the following files: A waveform file of the EEG signals (.dat) along with its header file (.hea). If the channel corresponds to an international 10-20 channel then it is labeled as such. Otherwise, it is just labeled 'EEG'. An annotation file (.flash) containing the locations of each individual flash. An annotation file (.win) containing the locations of the beginning and end of each 5 second flickering window. The annotations are labeled as '(' for start and ')' for stop, along with auxiliary strings indicating the focal frequency of the flashing windows.

The FREQUENCIES2.txt file indicates the approximate marked frequencies of the flickering windows, equal for each session, adaptation, and subject. These values are equal to those contained in the .win annotations.

Observed artifacts: During the stimulus presentation to subject S007 the research stuff noted that the subject had a tendency to eye blink. As a result the interference, in matters of artifacts, on the recorded signal is expected to be high.

Show more ▾Open in Overview tab →

Benchmark Context

WithinSession

Included in 1 MOABB benchmark table(s). Scores are across available pipelines (WithinSession accuracy).

Sample frame: 11 subjects × 1 sessions

• SSVEP all classes 6 pipelinesMax 39.36 · Median 23.92 · Mean 27.87 · Std 7.31

Citation & Impact

• Paper DOI10.48550/arXiv.1602.00904
• CitationsLoading…
• Public APICrossref | OpenAlex
• MOABB tables1 (WithinSession)
• Page Views
  30d: 11 · all-time: 211

  #39 of 151 · Top 26% most viewed

  Updated: 2026-03-21 UTC

Stimulus Protocol

5s task window per trial · 5-class ssvep paradigm · 5 runs/session across 1 sessions

HED Event Tags

HED tags5/5 events annotated

Source: MOABB BIDS HED annotation mapping.

Experimental-stimulus

5

Label

5

Sensory-event

5

Visual-presentation

5

6.66

Sensory-eventExperimental-stimulusVisual-presentationLabel

7.50

Sensory-eventExperimental-stimulusVisual-presentationLabel

8.57

Sensory-eventExperimental-stimulusVisual-presentationLabel

10.00

Sensory-eventExperimental-stimulusVisual-presentationLabel

12.00

Sensory-eventExperimental-stimulusVisual-presentationLabel

HED tree view

Tree · 6.66

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

Tree · 7.50

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

Tree · 8.57

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

Tree · 10.00

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

Tree · 12.00

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

Channel Summary

Total channels256

EEG256

MontageGSN-HydroCel-256

Sampling250 Hz

ReferenceCz

Notch / line50 Hz

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

Overview

SSVEP MAMEM 2 dataset.

Dataset from [1]. Data acquisition details are documented in [3].

EEG signals with 256 channels captured from 11 subjects executing a SSVEP-based experimental protocol. Five different frequencies (6.66, 7.50, 8.57, 10.00 and 12.00 Hz) have been used for the visual stimulation,and the EGI 300 Geodesic EEG System, using a stimulation, HydroCel Geodesic Sensor Net (HCGSN) and a sampling rate of 250 Hz has been used for capturing the signals.

Subjects were exposed to flickering lights from five violet boxes with frequencies [6.66Hz, 7.5Hz, 8.57Hz, 10Hz, and 12Hz] simultaneously. Prior to and during each flicking window, one of the boxes is marked by a yellow arrow indicating the box to be focused on by the subject. 256 channel EEG recordings were captured.

From [2], each subject underwent a single adaptation period before the first of their 5 sessions (unlike experiment 1 in which each session began with its own adaptation period). In the adaptation period, the subject is exposed to ten 5-second flickering windows from the five boxes simultaneously, with the target frequencies specified in the FREQUENCIES2.txt file under ‘adaptation’. The flickering windows are separated by 5 seconds of rest, and the 100s adaptation period precedes the first session by 30 seconds.

Each session consisted of the following: For the series of frequencies specified in the FREQUENCIES2.txt file under ‘sessions’: A 5 second window with all boxes flickering and the subject focusing on the specified frequency’s marked box, followed by 5 seconds of rest. This gives a total of 25 flickering windows for each session (not including the first adaptation period). Five minutes of rest before the next session (not including the 5th session).

The order of chosen frequencies is the same for each session, although there are small-moderate variations in the actual frequencies of each individual window. Note: Each ‘session’ in experiment 1 includes an adaptation period, unlike experiment 2 and 3 where each subject undergoes only one adaptation period before their first ‘session’.

Waveforms and Annotations File names are in the form T0NNn, where NN is the subject number and n is a - e for the session letter or x for the adaptation period. Each session lasts in the order of several minutes and is sampled at 250Hz. Each session and adaptation period has the following files: A waveform file of the EEG signals (.dat) along with its header file (.hea). If the channel corresponds to an international 10-20 channel then it is labeled as such. Otherwise, it is just labeled ‘EEG’. An annotation file (.flash) containing the locations of each individual flash. An annotation file (.win) containing the locations of the beginning and end of each 5 second flickering window. The annotations are labeled as ‘(’ for start and ‘)’ for stop, along with auxiliary strings indicating the focal frequency of the flashing windows.

The FREQUENCIES2.txt file indicates the approximate marked frequencies of the flickering windows, equal for each session, adaptation, and subject. These values are equal to those contained in the .win annotations.

Observed artifacts: During the stimulus presentation to subject S007 the research stuff noted that the subject had a tendency to eye blink. As a result the interference, in matters of artifacts, on the recorded signal is expected to be high.

References

[1]

Oikonomou, V. P., Liaros, G., Georgiadis, K., Chatzilari, E., Adam, K., Nikolopoulos, S., & Kompatsiaris, I. (2016). Comparative evaluation of state-of-the-art algorithms for SSVEP-based BCIs. arXiv preprint arXiv:1602.00904.

[2]

MAMEM Steady State Visually Evoked Potential EEG Database https://archive.physionet.org/physiobank/database/mssvepdb/

[3]

S. Nikolopoulos, 2016, DataAcquisitionDetails.pdf https://figshare.com/articles/dataset/MAMEM_EEG_SSVEP_Dataset_II_256_channels_11_subjects_5_frequencies_presented_simultaneously_/3153409?file=4911931

Code Examples

from moabb.datasets import MAMEM2
dataset = MAMEM2()
data = dataset.get_data(subjects=[1])
print(data[1])

Metadata

Dataset summary

#Subj	10
#Chan	256
#Classes	5
#Trials / class	20-30
Trials length	3 s
Freq	250 Hz
#Sessions	1

Participants

• Population: healthy

• Handedness: {‘right’: 10, ‘left’: 1}

Equipment

• Amplifier: EGI 300 Geodesic EEG System (GES 300)

• Montage: GSN-HydroCel-256

• Reference: Cz

Preprocessing

• Data state: raw

Data Access

• DOI: 10.48550/arXiv.1602.00904

• Data URL: https://figshare.com/articles/dataset/3153409

• Repository: GitHub

Experimental Protocol

• Paradigm: ssvep

• Feedback: none

• Stimulus: flickering box

__init__(subjects=None, sessions=None)

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)

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])

Notes

Use CacheConfig to configure caching for get_data(). Use moabb.datasets.bids_interface.get_bids_root to get the BIDS root path.

Added in version 1.5.

data_path(subject, path=None, force_update=False, update_path=None, verbose=None)

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)

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)

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 | pandas.DataFrame

get_block_repetition(paradigm, subjects, block_list, repetition_list)

Select data for all provided subjects, blocks and repetitions.

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

See also

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)

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 (sklearn.pipeline.Pipeline | None) – Optional processing pipeline to apply to the data. To generate an adequate pipeline, we recommend using moabb.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

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