RespDiff:一种用于从PPG信号估计呼吸波形的端到端多尺度RNN扩散模型
RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signals
AI总结:
针对呼吸频率连续监测不便的问题,提出端到端多尺度RNN扩散模型RespDiff,可从PPG信号估计呼吸波形,无需手工特征与低质量信号排除,结合多尺度编码、双向RNN与谱损失,在BIDMC数据集上RR估计MAE达1.18 bpm,优于现有方法。
摘要:
呼吸频率(RR)是一项关键健康指标,通常需在不便的场景下监测,限制了其连续监测的实用性。越来越多地集成到可穿戴设备中的光电容积描记法(PPG)传感器,为以便携方式连续估计RR提供了可能。本文提出了RespDiff——一种用于从PPG信号估计呼吸波形的端到端多尺度RNN扩散模型。RespDiff无需手工设计特征,也无需排除低质量信号段,适用于真实场景。该模型采用多尺度编码器提取不同分辨率的特征,并使用双向RNN处理PPG信号、提取呼吸波形。此外,还引入了谱损失项进一步优化模型。在BIDMC数据集上开展的实验表明,RespDiff优于以往的知名研究:其RR估计的平均绝对误差(MAE)为1.18 bpm,而其他方法的MAE在1.66至2.15 bpm之间,展现了其在真实应用中实现稳健、准确呼吸监测的潜力。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。