Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
- Signals
- ECG, EEG
- Form factor
- clinical_PSG
- License
- MIT
- Architecture
U-Time-derived EEG teacher → single-lead ECG student (attention transfer + softmax KD)
- Type
- Task model
- Form factor
- Clinical PSG
- Parameters
- Not reported
- Architecture
- U-Time-derived EEG teacher → single-lead ECG student (attention transfer + softmax KD)
- Venue
- Not reported
- Year
- Not reported
- arXiv
- Not reported
- DOI
- Not reported
- Weights
- Not released
- Licence
- MIT (opens in a new tab)
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Oct 19, 2026
- Updated
- Oct 19, 2026
Original description
This codebase implements knowledge distillation approach for ECG based sleep staging assisted by EEG based sleep staging model. Knowledge distillation is incorporated here by softmax distillation and another approach by Attention transfer based feature training. The combination of both is the proposed model.
The code implementation was done with Pytorch-lightning framework inside a docker container. Dependencies used inside the docker can be found in requirements.txt
Experiments can be reproduced by following the procedure mentioned in Reproducibility section
Verbatim fromGitHub· Description from the repository README; licence: MIT
How it works
- Architecture
- U-Time-derived EEG teacher → single-lead ECG student (attention transfer + softmax KD)
- Inputs
- ECG, EEG
- Approach
- sleep · staging · knowledge distillation · u time
Datasets
Papers· 1
Cite
APA
Sleep_Staging_KD (EEG→ECG knowledge distillation). (n.d.).
BibTeX
@misc{sleepstagingkdsleepstagingkd,
title = {{Sleep\_Staging\_KD (EEG→ECG knowledge distillation)}}
}Built from the hub record. Check it against the publisher before submitting.
History
Added to the ChatPPG research hub