An Agent Architecture with Tools and Memory for Selective Correction of Wrist PPG Heart Rate Estimates

📄 arXiv: 2610.30688v1 📥 PDF

作者: Xu Wang, Shuhan Yi, Zhen Cheng

分类: cs.LG

发布日期: 2026-10-22

备注: 71 pages, including 48 pages of Supplementary Information


💡 一句话要点

提出一种新型代理架构以解决腕部PPG心率估计的选择性修正问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱八:物理动画 (Physics-based Animation)

关键词: 腕部PPG 心率估计 运动伪影 选择性修正 代理架构 实时监测 可穿戴设备 数据集

📋 核心要点

  1. 现有腕部PPG心率估计方法在运动伪影影响下,修正虽然能降低平均误差,但可能导致个别窗口的估计误差加重。
  2. 本文提出了一种新型代理架构,结合工具和记忆,通过生成候选估计并评估其益处和危害,优化心率估计的选择性修正。
  3. 在多个公开数据集上测试后,十个估计器的宏平均MAE从9.09 bpm降低到4.45 bpm,显示出显著的性能提升。

📝 摘要(中文)

腕部光电容积描记法(PPG)心率估计易受运动伪影影响,传统修正方法虽然能降低平均误差,但可能加重个别窗口的误差。本文提出了一种围绕固定心率估计器的代理架构,结合工具和记忆,通过脉搏、运动和有限历史证据生成候选估计,并利用预测的益处和危害指导选择。独立的风险门控机制决定保留、修正或拒绝每个输出。在PPG-DaLiA数据集上训练后,本文在多个数据集上测试,结果显示平均绝对误差(MAE)最大降低了44.5%。

🔬 方法详解

问题定义:本文旨在解决腕部PPG心率估计中,由于运动伪影导致的估计误差问题。现有方法在修正过程中可能会加重个别窗口的误差,影响整体准确性。

核心思路:论文提出了一种代理架构,围绕固定心率估计器,结合工具和记忆,生成多个候选估计,并通过评估其潜在益处和危害来指导选择,从而实现选择性修正。

技术框架:整体架构包括候选估计生成模块、风险门控机制和最终输出选择模块。候选估计基于脉搏、运动状态和有限历史数据生成,风险门控机制则决定保留、修正或拒绝每个输出。

关键创新:最重要的创新在于引入了独立的风险门控机制,能够量化修正的益处与危害,从而在选择性修正中实现更高的准确性和可靠性。与现有方法相比,该架构能够更好地平衡修正的风险与收益。

关键设计:在模型训练中,使用了PPG-DaLiA数据集,采用了固定权重的方式进行测试。关键参数包括候选估计的生成策略和风险门控的阈值设置,确保在不同数据集上均能有效降低MAE。

📊 实验亮点

实验结果显示,在四个公开数据集上,十个估计器的宏平均MAE最大降低了44.5%,在GalaxyPPG数据集上取得了最大的性能提升。此外,60%和80%目标覆盖率下,数值修正对总误差的贡献超过窗口选择,验证了该方法的有效性。

🎯 应用场景

该研究在可穿戴设备的心率监测领域具有广泛的应用潜力,能够为运动健康管理、医疗监测等提供更为准确的心率估计。未来,该架构可进一步优化,应用于实时心率分析和个性化健康建议,提升用户体验和健康管理效果。

📄 摘要(原文)

Wrist photoplethysmography (PPG) heart rate estimates are vulnerable to motion artifacts, and corrections that reduce mean error can worsen individual windows. We propose an agent architecture with tools and memory around a fixed heart rate estimator. Pulse, motion, and limited historical evidence generate candidate estimates, whose predicted benefits and harms guide selection. An independent risk gate determines whether to retain, correct, or reject each output. We trained the architecture on PPG-DaLiA and tested it on Wrist Exercise, GalaxyPPG, and WildPPG with frozen weights. Across these four public datasets, mean absolute error (MAE), macro-averaged over ten estimators, decreased by up to 44.5%, with the largest reduction on GalaxyPPG. Beneficial and harmful corrections decreased and increased absolute error by more than 1 bpm, respectively. Their ten-estimator macro-averaged proportions ranged from 16.06% to 36.64% and from 1.68% to 6.77%, respectively, across the four datasets. At 60% and 80% target coverage, numerical correction on the same accepted windows contributed more to total error reduction than window selection. We implemented real-time wearable acquisition, Bluetooth reception, and smartphone deployment of a selected estimator and the framework. In backend analysis of four prototype recordings from one participant, ten-estimator macro-averaged MAE decreased from 9.09 to 4.45 bpm without additional rejection. Under the evaluated conditions, the architecture improved average accuracy while quantifying correction benefits and harms, supporting wearable heart rate analysis that considers error, correction risk, and coverage.