ChatPPG.
Join free

Paperdoi:10.1016/j.bspc.2026.110531

A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity

Venue listedDated May 9, 2026Added Nov 9, 2026

  • GP

Authors: Gianluca Rho; Nicola Carbonaro; Marco Laurino; Alessandro Tognetti; Alberto Greco (University of Pisa)

Biomedical Signal Processing and Control

Publisher (opens in a new tab) Cite
Open codeOpen weightsCC BY 4.0

TL;DR

Ensemble of convolutional denoising autoencoders cleans wrist PPG during high-intensity activity, followed by a PRV tracking step, for time-domain HRV (meanHR, stdRR, RMSSD). Code and trained PyTorch weights released CC BY 4.0 on Zenodo (2026-11-09).

  • Form factor: wrist

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Signal denoising

Signals

PPGIMU

Keywords

HRVPrvRmssdDenoising AutoencoderMotion ArtifactWristEnsembleOpen Weights

Datasets used

How it works

How Method works: Setup → Method → TargetSetup: Signals (PPG, ACC); Form factor (wrist). Method: Method. Target: Signal denoising.SetupSignals: PPG, ACCSignalsPPG, ACCForm factor: wristForm factorwristMethodMethodTargetSignal denoisingSignal denoising

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Rho, G., Carbonaro, N., Laurino, M., Tognetti, A., & Greco, A. (2026). A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity. Biomedical Signal Processing and Control. https://doi.org/10.1016/j.bspc.2026.110531
Rho, Gianluca, Nicola Carbonaro, Marco Laurino, Alessandro Tognetti, and Alberto Greco. 2026. "A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity." Biomedical Signal Processing and Control. https://doi.org/10.1016/j.bspc.2026.110531.
Rho, G., Carbonaro, N., Laurino, M., Tognetti, A. and Greco, A. (2026) 'A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity', Biomedical Signal Processing and Control. doi: 10.1016/j.bspc.2026.110531.
Rho, Gianluca, et al. "A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity." Biomedical Signal Processing and Control, 2026. https://doi.org/10.1016/j.bspc.2026.110531.
G. Rho, N. Carbonaro, M. Laurino, A. Tognetti, and A. Greco, "A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity," Biomedical Signal Processing and Control, 2026, doi: 10.1016/j.bspc.2026.110531.
@article{rho2026deep,
  title         = {{A Deep Learning approach for estimating Time-Domain Heart Rate Variability parameters from wrist photoplethysmography during daily activity}},
  author        = {Rho, Gianluca and Carbonaro, Nicola and Laurino, Marco and Tognetti, Alessandro and Greco, Alberto},
  year          = {2026},
  journal       = {Biomedical Signal Processing and Control},
  doi           = {10.1016/j.bspc.2026.110531}
}

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Models

Datasets