NeuroTechX / NeuroTechX/moabb

[Dataset] Add Pan2024 SSVEP dataset

Open
#888 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

  • Suggested Name for MOABB: Pan2023
  • Full Title: Pan2023 Motor Imagery Dataset
  • Paradigm: ⚠️ Motor Imagery (NOT SSVEP) - Issue title is incorrect
  • Category: Motor Imagery

Link Status

⚠️ Data Link: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/251NOW - Returns WAF challenge
Correct Data DOI: https://doi.org/10.7910/DVN/O5CQFA
Paper: https://iopscience.iop.org/article/10.1088/1741-2552/ad0a01 (Working - but describes MI, not SSVEP)
Code Reference: https://github.com/PLC-TJU/RSF/blob/main/loaddata/pan2023.py (Working)

⚠️ IMPORTANT: Paradigm Correction Needed

The issue title states "SSVEP" but the actual dataset is Motor Imagery (MI). The paper and code reference both confirm this is a Motor Imagery dataset with left-hand and right-hand MI classification.

Publication Details

Field Value
Journal Journal of Neural Engineering
Year 2023
DOI 10.1088/1741-2552/ad0a01
Authors Pan Lincong, Wang Kun, Huang Yongzhi, Sun Xinwei, Meng Jiayuan, Yi Weibo, Xu Minpeng, Jung Tzyy-Ping, Ming Dong

Technical Specifications

Parameter Value
Number of Subjects 14 (5 females, aged 22-25, 2 left-handed)
Number of Channels 28
Sampling Frequency 250 Hz (downsampled from 1000 Hz)
Sessions per Subject 2
Trials per Session 120
Total Trials per Subject 240
Trial Duration 4 seconds
Classes 2 (left-hand MI, right-hand MI)
Data Format Epoched (MATLAB .mat files)
BIDS Format ❌ No
Equipment Neuroscan SynAmps2 amplifier

Electrode Configuration

FC5, FC3, FC1, FCz, FC2, FC4, FC6, C5, C3, C1, Cz, C2, C4, C6, CP5, CP3, CP1, CPz, CP2, CP4, CP6, P5, P3, P1, Pz, P2, P4, P6

Description

Motor Imagery dataset from PLC-TJU group featuring a Riemannian geometry-based adaptive boosting and voting ensemble (RAVE) algorithm for decoding motor imagery EEG signals.

Original Suggestion

Created as part of dataset discovery initiative.

Related

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

Paradigm Correction: This dataset is Motor Imagery (left/right hand MI for RAVE algorithm), NOT SSVEP as stated in the issue title.

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 linked Python loader at github.com/PLC-TJU/RSF/blob/main/loaddata/pan2023.py and the corrected DOI, confirming that the data is a 14-subject, two-class Motor Imagery dataset rather than SSVEP. Done should include a consistent Pan2023 name and the corrected paradigm, links, metadata, and data source; the issue does not name MOABB files or tests to run.

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
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.