NeuroTechX / NeuroTechX/moabb

[Dataset] Add datasets from ResearchGate public EEG list

Open
#915 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.1k
Forks
264
Avg merge
1d 13m
Merged PRs (30d)
23

Description

Dataset Information

Description

A ResearchGate discussion thread where researchers have shared links to various public EEG datasets over several years. This thread aggregates community knowledge about available EEG data sources, though many links may be duplicates of datasets listed in other meta-lists or already implemented in MOABB.

Note: This resource requires manual review as ResearchGate discussion threads are not directly scrapeable. The content below is based on commonly mentioned datasets in such discussions.


Commonly Referenced Datasets (to verify against thread)

Likely Already in MOABB
  • BCI Competition datasets - Multiple implemented via BNCI
  • PhysioNet EEG Motor Movement/Imagery - PhysionetMI
  • DEAP - Emotion dataset (not BCI-focused)
  • ERP CORE - All 7 paradigms implemented
Commonly Mentioned BCI Datasets to Verify
  • BCI Competition II - Dataset III (P300 Speller)
  • BCI Competition III - Dataset IIIa (Motor Imagery, 3 subjects)
  • BCI Competition III - Dataset IVa (Motor Imagery, 5 subjects)
  • BCI Competition IV - Dataset 1 (Motor Imagery)
  • BCI Competition IV - Dataset 2a (Motor Imagery) - Likely BNCI2014_001
  • BCI Competition IV - Dataset 2b (Motor Imagery) - Likely BNCI2014_004
Other Frequently Mentioned Sources
  • Kaggle BCI Challenge - Grasp-and-Lift EEG Detection
  • OpenBCI sample datasets
  • Emotiv sample datasets
  • MindBigData - MNIST of Brain Data (consumer-grade EEG)

Verification Tasks

Since this is a discussion thread, someone should:

  1. Visit the ResearchGate thread and extract all unique dataset links
  2. Cross-reference with datasets already in MOABB
  3. Cross-reference with other meta-lists (#913 OpenLists, #916 FieldTrip, #914 meagmohit)
  4. Create individual issues for any unique, BCI-relevant datasets not yet tracked

Known Overlaps with Other Meta-Issues

Many datasets mentioned in ResearchGate discussions are likely duplicates of:

  • #913 - OpenLists ElectrophysiologyData (comprehensive GitHub list)
  • #914 - meagmohit EEG-Datasets list
  • #916 - FieldTrip Open Data page
  • #909 - Neurocomputing 2024 review paper datasets

Access Limitations

  • ResearchGate may require login to view full discussion
  • Links in older posts may be broken
  • Some datasets may have moved or been deprecated

Notes

This is a META-ISSUE pointing to a discussion thread. The thread should be manually reviewed to extract actionable dataset links. Priority should be given to datasets not covered by other meta-lists.

Recommendation: Focus efforts on the more structured meta-lists (#913, #916) first, as they are better maintained and organized. Use this thread as a supplementary discovery resource.

Related

This issue is a sub-issue of #1 (Discover new datasets)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the ResearchGate discussion and comparing its dataset links with MOABB and meta-lists #913, #914, and #916. Check which entries are duplicates, inaccessible, or already implemented. Done means identifying unique BCI-relevant datasets and creating individual issues for those not already tracked, while noting that this issue is supplementary to the more structured lists.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.