The Bitbrain Open Access Sleep (BOAS) dataset
The Bitbrain Open Access Sleep (BOAS) dataset comprises 128 nights of simultaneous polysomnography (PSG) and wearable EEG headband recordings from 108 unique participants, designed to validate wearable EEG technology against clinical PSG for sleep monitoring. The dataset includes human-consensus sleep stage labels derived from expert scoring of PSG recordings, as well as AI-generated sleep stage labels for both PSG and wearable EEG data using a deep learning model. Additional demographic metadata (age, sex, BMI) are provided for each participant, offering a comprehensive resource for sleep staging research and wearable EEG validation.
- Participants
- 128
- Channels
- 2
- Citations
- 7
- Size
- 33.5 GB
- Version
- v1.0.0
- Updated
- Aug 19, 2026