发表机构
Chittagong University of Engineering and Technology; BRAC University; Hanyang University（吉大港工程与技术大学; 布拉格大学; 汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对智能手机PPG心率估计在自由生活条件下不可靠的问题，提出MoWaveQFormer，一种运动条件质量门控Transformer，通过运动特定滤波和软门控处理信号质量，在BUT PPG v2.0上实现7.85 bpm的MAE，为实时部署提供紧凑方案。
AI 中文摘要
基于光电容积描记法（PPG）的心率（HR）估计在智能手机上于自由生活条件下仍不可靠，因为运动伪影在不同活动中的频谱结构各异，且诸如BUT PPG v2.0等基准将信号质量仅标记为二元的好或坏，丢弃了部分可用的数据。本研究开发了一种心率估计架构，该架构显式地以运动类型和信号质量为条件，而非将两者同等对待。我们提出了MoWaveQFormer，一种在ECG监督下训练的三阶段架构。阶段1根据加速度计导出的频谱能量为每个窗口分配一个离散的运动组，无需可训练参数。阶段2使用该索引从三个可学习的FIR滤波器组中选择一个，用于对PPG信号进行特定运动的频谱整形。阶段3将得到的子带嵌入到补丁令牌中，通过源自质量标签的可微分软门对它们重新加权，并使用Transformer对其进行编码，其池化输出回归到心率，与ECG监督损失和脉搏传输时间一致性项联合训练。在BUT PPG v2.0（3,888条记录，50名受试者）的受试者独立划分中，MoWaveQFormer实现了7.85 bpm的平均绝对误差，为五种方法中最低，且相对于三个基线有显著改进（Wilcoxon检验，p<0.05）。消融和Bland-Altman分析表征了每个组件的贡献。凭借816,445个参数和低于3毫秒的延迟，MoWaveQFormer适用于实时部署，有待在智能手机硬件上验证。用可微分的条件处理取代与运动无关的滤波和二元质量丢弃，为更可靠的自由生活PPG心血管监测提供了一条紧凑的途径。
英文摘要
Photoplethysmography (PPG)-based heart-rate (HR) estimation on smartphones remains unreliable in free-living conditions because motion artifacts vary in spectral structure across activities, and benchmarks such as BUT PPG v2.0 label signal quality only as binary good or bad, discarding partially usable data. This study develops an HR estimation architecture that explicitly conditions motion type and signal quality rather than treating both uniformly. We propose MoWaveQFormer, a three-stage architecture trained under ECG supervision. Stage 1 assigns each window a discrete motion group based on accelerometer-derived spectral energy, without trainable parameters. Stage 2 uses this index to select one of the three learnable FIR filter banks for motion-specific spectral shaping of the PPG signal. Stage 3 embeds the resulting sub-bands into patch tokens, re-weights them via a differentiable soft gate derived from the quality label, and encodes them with a Transformer whose pooled output is regressed to HR, trained jointly with an ECG-supervised loss and a pulse-transit-time consistency term. In a subject-independent split of BUT PPG v2.0 (3,888 recordings, 50 subjects), MoWaveQFormer achieved a mean absolute error of 7.85 bpm, the lowest among five methods, with significant improvements over three baselines (Wilcoxon test, p<0.05). Ablation and Bland-Altman analyses characterize each component's contribution. With 816,445 parameters and sub-3-ms latency, MoWaveQFormer suits real-time deployment, pending validation on smartphone hardware. Replacing motion-agnostic filtering and binary quality discarding with differentiable conditioned processing offers a compact pathway to more reliable free-living PPG-based cardiovascular monitoring.
CommentsSubmitted to arXiv. 8 pages, 5 figures
