RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signals

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Miao, Yuyang, Chen, Zehua, Li, Chang, Mandic, Danilo
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929529473204224
author Miao, Yuyang
Chen, Zehua
Li, Chang
Mandic, Danilo
author_facet Miao, Yuyang
Chen, Zehua
Li, Chang
Mandic, Danilo
contents Respiratory rate (RR) is a critical health indicator often monitored under inconvenient scenarios, limiting its practicality for continuous monitoring. Photoplethysmography (PPG) sensors, increasingly integrated into wearable devices, offer a chance to continuously estimate RR in a portable manner. In this paper, we propose RespDiff, an end-to-end multi-scale RNN diffusion model for respiratory waveform estimation from PPG signals. RespDiff does not require hand-crafted features or the exclusion of low-quality signal segments, making it suitable for real-world scenarios. The model employs multi-scale encoders, to extract features at different resolutions, and a bidirectional RNN to process PPG signals and extract respiratory waveform. Additionally, a spectral loss term is introduced to optimize the model further. Experiments conducted on the BIDMC dataset demonstrate that RespDiff outperforms notable previous works, achieving a mean absolute error (MAE) of 1.18 bpm for RR estimation while others range from 1.66 to 2.15 bpm, showing its potential for robust and accurate respiratory monitoring in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04366
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signals
Miao, Yuyang
Chen, Zehua
Li, Chang
Mandic, Danilo
Signal Processing
Artificial Intelligence
Human-Computer Interaction
Respiratory rate (RR) is a critical health indicator often monitored under inconvenient scenarios, limiting its practicality for continuous monitoring. Photoplethysmography (PPG) sensors, increasingly integrated into wearable devices, offer a chance to continuously estimate RR in a portable manner. In this paper, we propose RespDiff, an end-to-end multi-scale RNN diffusion model for respiratory waveform estimation from PPG signals. RespDiff does not require hand-crafted features or the exclusion of low-quality signal segments, making it suitable for real-world scenarios. The model employs multi-scale encoders, to extract features at different resolutions, and a bidirectional RNN to process PPG signals and extract respiratory waveform. Additionally, a spectral loss term is introduced to optimize the model further. Experiments conducted on the BIDMC dataset demonstrate that RespDiff outperforms notable previous works, achieving a mean absolute error (MAE) of 1.18 bpm for RR estimation while others range from 1.66 to 2.15 bpm, showing its potential for robust and accurate respiratory monitoring in real-world applications.
title RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signals
topic Signal Processing
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2410.04366