BNCI 2015-009 AMUSE (Auditory Multi-class Spatial ERP) dataset
The BNCI 2015-009 AMUSE dataset comprises EEG recordings from 21 healthy subjects performing an auditory oddball task using spatial hearing as a discriminating cue. The dataset implements a P300-based brain-computer interface paradigm with multi-class auditory stimuli presented from five spatially distributed speakers at varying inter-stimulus intervals. Preprocessed data includes 60 EEG channels and 2 EOG channels sampled at 100 Hz (downsampled from 250 Hz acquisition rate), with offline classification achieving up to 100% accuracy on best-performing individual subjects.
- Participants
- 21
- Citations
- 91
- HED
- v8.4.0
- Size
- 4.57 GB
- Version
- v1.0.0
- Updated
- Jun 3, 2026