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.
- Form factor
- Wrist
- Signals
- PPG, IMU, Temp
- License
none declared (no LICENSE file in repo at the recorded commit; all rights reserved by default)
- Type
- Task model
- Form factor
- Wrist
- Parameters
- Not reported
- Architecture
- Not reported
- Venue
- Not reported
- Year
- Not reported
- arXiv
- Not reported
- DOI
- Not reported
- Weights
- Open
- Licence
- none declared (no LICENSE file in repo at the recorded commit; all rights reserved by default)
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Oct 19, 2026
- Updated
- Oct 19, 2026
Original description
The method estimates ECG-aligned inter-beat intervals (IBIs) from wearable photoplethysmography (PPG), then refines the estimates with a causal, learnable state-space model (SSM). Motion (IMU) and temperature are used as auxiliary signals when available. The result is a continuous IBI sequence from which standard HRV measures, including SDNN, RMSSD, and LF/HF power, are computed.
The following are the reported IBI results (mean ± standard deviation across subjects/folds, in ms). r is Pearson correlation with ECG-derived IBI.
For full SDNN, RMSSD, and frequency-domain results, see the manuscript. Example experiment artifacts—checkpoints, per-subject arrays, and fold summaries—are in results/.
Verbatim fromGitHub· Description from the repository README

How it works
- Inputs
- PPG, IMU, Temp
- Approach
- code release · open weights
Datasets
Cite
APA
Continuous HRV from PPG (state-space). (n.d.).
BibTeX
@misc{continuoushrvppgcontinuous,
title = {{Continuous HRV from PPG (state-space)}}
}Built from the hub record. Check it against the publisher before submitting.
History
Added to the ChatPPG research hub
