nm000348
Yang et al. 2025 — A multi-day and high-quality EEG dataset for motor imagery brain-computer interface
EEG Zarr
A multi-day EEG dataset for motor imagery brain-computer interface (MI-BCI) research collected at Shanghai University (WBCIC-SHU). It contains recordings from 51 healthy, BCI-naive participants who performed left- and right-hand motor imagery over three sessions on different days. A subset of 11 participants also performed a three-class paradigm that adds foot-hooking imagery. Recordings were made with a 59-channel EEG system and the dataset is accompanied by benchmark classification results using CSP, FBCSP, EEGNet, deepConvNet and FBCNet.
- Participants
- 51
- Channels
- 59 (10-10)
- Citations
- 44
- HED
- v8.4.0
- Size
- 154 GB
- Version
- v1.0.5
- Updated
- Aug 18, 2026