学习何处关注：用于时间序列预测与PPG到生命体征重建的共享相对对齐模块

中文摘要 AI 辅助

PPG到生命体征重建将腕戴式光电容积脉搏波转换为临床波形，如心电图。长视野多变量时间序列预测支撑着能源、天气和交通领域的规划。两者均从条件序列生成目标序列，而当前模型硬编码了每个目标位置的读取来源，如同位复制或季节性循环，因此无法在任务间迁移。我们提出ROOSTER，一个通过学习这种对应关系来处理生命体征重建和时间序列预测的条件模块。其核心是目标-条件偏移上的周期梳状偏置，其中心、周期和锐度按头学习，因此一个模块可确定身份对齐或季节性滞后，并报告其发现。在从PPG进行生命体征重建时，ROOSTER在四个心率和呼吸频率基准上优于已发表的基线。在多变量时间序列预测中，它在四个基准上取得了最佳视野平均MSE，并在匹配三种子训练下，在24个数据集-视野设置中的20个上优于其扩展的预测模型。消融研究表明，相对偏置而非内容匹配承载了对齐。

英文摘要

PPG-to-vital-sign reconstruction turns a wrist-worn photoplethysmogram into clinical waveforms such as the ECG. Long-horizon multivariate time-series forecasting underpins planning in energy, weather, and traffic. Both generate a target sequence from a condition sequence, and current models hard-code where each target position reads it, as a same-position copy or seasonal recurrence, so neither transfers between tasks. We propose ROOSTER, one conditioning module that handles vital-sign reconstruction and time-series forecasting alike by learning this correspondence. Its core is a periodic-comb bias over the target-condition offset whose center, period, and sharpness are learned per head, so one module settles on the identity alignment or a seasonal lag and reports which it found. On vital-sign reconstruction from PPG, ROOSTER outperformed the published baselines on four heart-rate and respiratory-rate benchmarks. On multivariate time-series forecasting, it achieved the best horizon-averaged MSE on four benchmarks and outperformed the forecasting model it extends on 20 of 24 dataset-horizon settings under matched three-seed training. An ablation study indicated that the relative bias, not content matching, carried the alignment.

发表机构

• Neurogica Inc.（Neurogica 公司）

机构由 AI 辅助整理，请以论文原文为准。