nm000199 NEMAR-native dataset

Learning from label proportions for a visual matrix speller (ERP)

This dataset comprises event-related potential (ERP) recordings from 13 healthy subjects performing a visual P300 speller task using a 6×7 character matrix. The study introduces learning from label proportions (LLP), an unsupervised classification approach that enables calibration-free brain-computer interface operation by exploiting known target/non-target stimulus ratios. Subjects completed three copy-spelling sessions without prior calibration, achieving 84.5% character accuracy, demonstrating the feasibility of LLP for practical BCI applications.

EEG
Download zip Issues GitHub

Compute on this dataset

Two routes today, with a third (in-browser one-click submission) landing soon.

  1. NeuroScience Gateway (NSG) portal.

    NSG runs EEGLAB / Brainstorm / MNE pipelines on supercomputing time donated by SDSC. Create an account, point a job at this dataset's S3 prefix (s3://nemar/nm000199), and submit.
    nsgportal.org →

  2. Local processing with nemar-cli.

    Pull the dataset to your machine and run any toolbox locally. Honors the published version pinning. 

    npm install -g nemar-cli
nemar dataset clone nm000199
cd nm000199 && nemar dataset get
  3. Just the files.

    rclone, aria2c, or any HTTPS client works against data.nemar.org/nm000199/ — the manifest carries presigned S3 URLs.

Direct compute access is coming soon. One-click NSG submission from this page is scoped for a follow-up phase. Tracked on nemarOrg/website#6.
DOI 10.82901/nemar.nm000199

Loading demographics…

Files

Loading file index…