Paperdoi:10.1145/3831657
A Context-Aware Framework for Optimal Filter Parameter Selection: Enhancing PRV Estimation in Wearable Wrist PPG Signals
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)
TL;DR
Argues that fixed one-size-fits-all band-pass filtering before peak detection / pulse rate variability (PRV) can introduce large PRV errors even with minimal motion, and that best cutoffs differ by person and contextual state. Proposes a person- and context-aware framework that adaptively selects filter parameters per window, gating by signal quality and choosing band-pass cutoffs. Across three datasets, reports adaptive filtering improved PRV (RMSSD) accuracy by up to 279 ms vs a fixed filter, improved stress detection, and increased usable IBIs without losing accuracy.
- Form factor: wrist
Abstract
Wearable biosensing allows for continuous monitoring and intervention in daily settings. Wrist photoplethysmography (PPG) is a commonly used method for measuring cardiac activity ambulatorily. A typical data preprocessing step is to apply a fixed, one-size-fits-all band-pass filter before peak detection and pulse rate variability (PRV) calculation. However, our analyses reveal that fixed filtering can cause significant errors in PRV estimation even with minimal motion artifacts, and the best filter settings differ across individuals and contextual states. Based on these findings, we introduce a person- and context-aware framework to adaptively select filter parameters at a window level. We instantiate this framework using models that gate segments by signal quality and select band-pass cutoff frequencies for each window. In tests across three datasets, our adaptive method improved PRV (RMSSD) accuracy by up to 279ms compared to a fixed filter and enhanced stress detection. It also increased the amount of usable inter-beat intervals without losing accuracy. Our collective results suggest shifting focus from solely removing motion artifacts toward adaptive selection of filter configurations that considers who is being measured and their state.
Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/legalcode
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
Naito, Y., Yamane, N., Sathyanarayana, A., Goodwin, M. S., & Mishra, V. (2026). A Context-Aware Framework for Optimal Filter Parameter Selection: Enhancing PRV Estimation in Wearable Wrist PPG Signals. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. https://doi.org/10.1145/3831657
BibTeX
@inproceedings{naito2026contextaware,
title = {{A Context-Aware Framework for Optimal Filter Parameter Selection: Enhancing PRV Estimation in Wearable Wrist PPG Signals}},
author = {Naito, Yuna and Yamane, Natasha and Sathyanarayana, Aarti and Goodwin, Matthew S. and Mishra, Varun},
year = {2026},
booktitle = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
doi = {10.1145/3831657}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
