SeqSmoother：从腕部加速度计估算睡眠心率，MAE 低至 1.60 bpm
Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
不用光学传感器，光靠手表加速度数据就能估睡眠心率，SeqSmoother 把 MAE 做到 1.60 bpm，还跟 Nightbeat 掰了手腕，精度和覆盖率的取舍讲得很清楚。
arXiv 论文提出 SeqSmoother，一个基于 transformer 的睡眠心率估算模型，仅用腕部加速度计信号推断心率。模型结合频谱特征、Nightbeat 频率锚点和物理启定的次谐波特征，用于识别谐波锁定。在 13 个参与者互斥的留出折上，SeqSmoother 的参与者宏平均 MAE 为 1.60 bpm。与官方 Nightbeat 在 60 秒窗口、15 秒步长协议下对比：Nightbeat 在保留区间上绝对误差更低（0.615 vs 1.091 bpm），但仅对 72.85% 的有效网格给出结果，SeqSmoother 覆盖范围更大。次谐波比率识别谐波锁定的 AUROC 达到 0.972。
Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
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.
