发表机构
Kennesaw State University; University of Georgia（肯尼索州立大学; 佐治亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SeqSmoother，一种基于Transformer的时序校正器，从腕部加速度计估计睡眠心率，利用频谱描述符、频率锚点和次谐波特征，在13折评估中实现1.60 bpm的MAE，并揭示了准确性-可用性权衡。
AI 中文摘要
大型纵向队列研究通常包含腕部加速度计数据，但缺乏光学心率传感，这促使我们从睡眠期间已收集的运动信号中恢复心脏信息。我们提出了SeqSmoother，一种基于Transformer的时间校正器，用于从腕部加速度计数据估计睡眠心率（HR）。SeqSmoother结合了频谱描述符、一个由Nightbeat派生的中间频率锚点，以及一个基于物理学的次谐波特征，旨在识别谐波频率锁定。所有推理时特征均来自腕部加速度计，而ECG仅用于构建参考HR标签和训练标签质量权重。我们使用13个参与者不相交的保留折评估SeqSmoother，并在匹配的60秒窗口和15秒步长协议下与官方Nightbeat实现进行比较。在所有折外预测中，SeqSmoother实现了参与者宏平均绝对误差（MAE）为1.60 bpm。在Nightbeat保留的匹配区间内，Nightbeat的绝对误差低于SeqSmoother（0.615对1.091 bpm），而SeqSmoother在符合条件的记录中提供了更大比例的估计；Nightbeat为SeqSmoother符合条件的折外网格的72.85%生成了最终估计。此外，所提出的次谐波比率在识别参考定义的谐波锁定候选者方面实现了0.972的AUROC。这些发现揭示了学习时间建模与质量门控信号处理之间的准确性-可用性权衡，同时为基于物理信息的方法识别基于加速度计的睡眠心率估计中的频率跟踪失败提供了实证支持。
英文摘要
Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already collected during sleep. We present SeqSmoother, a transformer-based temporal corrector for sleep heart rate (HR) estimation from wrist accelerometry. SeqSmoother combines spectral descriptors with an intermediate Nightbeat-derived frequency anchor and a physics-motivated sub-harmonic feature designed to identify harmonic frequency lock-on. All inference-time features are derived from wrist accelerometry, while ECG is used only to construct reference HR labels and training-label quality weights. We evaluate SeqSmoother using 13 participant-disjoint held-out folds and compare it with the official Nightbeat implementation under a matched 60-s window and 15-s step protocol. Across all out-of-fold predictions, SeqSmoother achieved a participant-macro MAE of 1.60 bpm. On Nightbeat-retained matched intervals, Nightbeat achieved lower absolute error than SeqSmoother (0.615 versus 1.091 bpm), while SeqSmoother provided estimates over a larger portion of the eligible recording; Nightbeat produced final estimates for 72.85% of the SeqSmoother-eligible out-of-fold grid. Separately, the proposed sub-harmonic ratio achieved an AUROC of 0.972 for identifying reference-defined harmonic lock-on candidates. These findings reveal an accuracy-availability trade-off between learned temporal modeling and quality-gated signal processing while providing empirical support for a physics-informed approach to identifying frequency-tracking failures in accelerometer-based sleep HR estimation.
Comments8 pages, submitted in BHI 2026
