PulseAugur
实时 07:45:13

新型 Transformer 模型可从 PPG 信号估算血压

研究人员开发了一种名为 DMT 的新型基于 Transformer 的模型,用于从 PPG 信号估算血压,无需袖带。该模型通过其注意力层内的特征调制来整合人口统计学信息,并包含一个专注于血压相关波形形态的辅助头。在 PulseDB 数据集上,与先前的人口统计学增强基线相比,DMT 在收缩压误差方面降低了 47%,在舒张压误差方面降低了 50%。 AI

影响 引入了一种袖带式血压估算的新方法,有望改善可穿戴健康监测。

排序理由 这是一篇详细介绍新模型及其在特定数据集上性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Yidan Shen, Neville Mathew, Maham Rahimi, Deependra Dhakal, George Zouridakis, Xin Fu, Renjie Hu ·

    DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals

    arXiv:2606.11125v1 Announce Type: cross Abstract: Blood pressure (BP) is a key marker for cardiovascular risk assessment and therapeutic decision-making, and Photoplethysmography (PPG) enables low-cost, wearable-friendly cuffless BP estimation. However, even with recent progress,…

  2. arXiv cs.LG TIER_1 English(EN) · Renjie Hu ·

    DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals

    Blood pressure (BP) is a key marker for cardiovascular risk assessment and therapeutic decision-making, and Photoplethysmography (PPG) enables low-cost, wearable-friendly cuffless BP estimation. However, even with recent progress, many PPG-based models are trained with BP regress…