Paper
Analysis of factors affecting the predictive performance of foundation models for PPG signals (Ljubljana MSc thesis)
University of Ljubljana repository, MSc thesis in Slovenian (2026-10-08)
Licence: other-OA (OpenAlex)
TL;DR
Methodological framework for analysing and comparing PPG foundation models with synthetic tasks: how well representations encode PPG morphological features, and how performance varies with physiologically motivated pulse segments, aggregation, input-window length and noise. Uses an extended two-Gaussian pulse generator. Preliminary synthetic evaluation showed large performance differences tied to task properties; complemented by cross-validated real tasks (BP and HR estimation, SpO2-desaturation event detection).
- Form factor: mixed
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
How it works
Cite this paper
APA
Mujagić, A. (2026). Analysis of factors affecting the predictive performance of foundation models for PPG signals (Ljubljana MSc thesis). University of Ljubljana repository, MSc thesis in Slovenian. https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=250111
BibTeX
@article{mujagic2026analysis,
title = {{Analysis of factors affecting the predictive performance of foundation models for PPG signals (Ljubljana MSc thesis)}},
author = {Mujagić, Amer},
year = {2026},
journal = {University of Ljubljana repository, MSc thesis in Slovenian},
url = {https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=250111}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
