.png){kind=icon}
.png){kind=icon}
Return
Parameter-Efficient Deep Learning Models for Vital Sign Estimation From PPG
.png){kind=icon}
OA
AI
DOI：10.1049/htl2.70083.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En
Photoplethysmography (PPG) enables non-invasive estimation of vital signs across a range of sensors, from wrist wearables and clinical monitors to smartphone cameras. We present parameter-efficient, end-to-end deep models for heart rate (HR), blood oxygen saturation ( SpO2${\rm SpO}_{2}$) and respiratory rate (RR) estimation. These models operate directly on PPG signals and integrate preprocessing as a layer. Our family of fully convolutional architectures includes a baseline FCN, a residual FCN, a ConvNeXt-inspired FCN and a compact DCT-based variant. These models achieve strong cross-dataset performance while using only 3.3K–53K parameters. On PPG-DaLiA, the best performing model achieves 6.07 ±$\pm$ 2.70 bpm MAE for HR. In HR, SpO2${\rm SpO}_{2}$ and RR tasks on the BIDMC dataset, the best-performing method achieves error rates of 2.2 bpm, 3.14% and 1.49 breaths per minute, respectively. We also release MTHS, a smartphone-based vital-sign dataset comprising 62 fingertip-PPG recordings (35 men and 27 women) with 1-Hz HR and annotations. Additionally, we demonstrate practical feasibility via on-device deployment using TFLite on smartphones. These results show that compact, fully convolutional and DCT-based designs provide accurate, generalizable, and deployment-ready PPG vital-sign estimators across sensors and datasets.
Keywords:
deep learning
ML-healthcare
photoplethysmography
signal processing
vital sign estimation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
80
Citations:
730