DiffPhys: Enhancing Signal-to-Noise Ratio in Remote Photoplethysmography Signal Using a Diffusion Model Approach
Bioengineering · 23.07.2024 · 11 (8) · 743
DOI: 10.3390/bioengineering11080743 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 23.07.2024. Verfasst von Shutao Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: PanopticAI, Hong Kong Science and Technology Parks, New Territories, Hong Kong, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovation and Technology Fund (ITF) Technology Start-up Support Scheme for Universities (TSSSU+), Research Talent Hub for Incubatees and I&T Tenants of the HKSTPC and the Cyberport (RTH-SPC), HKSTP Incubation Program and HKUST Sports Science and Technology Research Grant (SSTRG).
Abstract (Originalsprache)
Remote photoplethysmography (rPPG) is an emerging non-contact method for monitoring cardiovascular health based on facial videos. The quality of the captured videos largely determines the efficacy of rPPG in this application. Traditional rPPG techniques, while effective for heart rate (HR) estimation, often produce signals with an inadequate signal-to-noise ratio (SNR) for reliable vital sign measurement due to artifacts like head motion and measurement noise. Another pivotal factor is the overlooking of the inherent properties of signals generated by rPPG (rPPG-signals). To address these limitations, we introduce DiffPhys, a novel deep generative model particularly designed to enhance the SNR of rPPG-signals. DiffPhys leverages the conditional diffusion model to learn the distribution of rPPG-signals and uses a refined reverse process to generate rPPG-signals with a higher SNR. Experimental results demonstrate that DiffPhys elevates the SNR of rPPG-signals across within-database and cross-database scenarios, facilitating the extraction of cardiovascular metrics such as HR and HRV with greater precision. This enhancement allows for more accurate monitoring of health conditions in non-clinical settings.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- PanopticAI, Hong Kong Science and Technology Parks, New Territories, Hong Kong, China.
- Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, China.
ORCID-Profile: Shutao Chen
Förderung
- Innovation and Technology Fund (ITF) Technology Start-up Support Scheme for Universities (TSSSU+)
- Research Talent Hub for Incubatees and I&T Tenants of the HKSTPC and the Cyberport (RTH-SPC)
- HKSTP Incubation Program and HKUST Sports Science and Technology Research Grant (SSTRG)
Zitieren
APA
Chen, S., Wong, K. L., Chin, J. W., Chan, T. T., & So, R. H. Y. (2024). DiffPhys: Enhancing Signal-to-Noise Ratio in Remote Photoplethysmography Signal Using a Diffusion Model Approach. Bioengineering, 11(8), 743. https://doi.org/10.3390/bioengineering11080743
Vancouver
Chen S, Wong KL, Chin JW, Chan TT, So RHY. DiffPhys: Enhancing Signal-to-Noise Ratio in Remote Photoplethysmography Signal Using a Diffusion Model Approach. Bioengineering. 2024;11(8):743. doi:10.3390/bioengineering11080743
BibTeX
@article{Chen2024,
author = {Chen, Shutao and Wong, Kwan-Long and Chin, Jing-Wei and Chan, Tsz-Tai and So, Richard H Y},
title = {DiffPhys: Enhancing Signal-to-Noise Ratio in Remote Photoplethysmography Signal Using a Diffusion Model Approach},
journal = {Bioengineering},
year = {2024},
volume = {11},
number = {8},
pages = {743},
doi = {10.3390/bioengineering11080743}
}
EUVIMED