arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.14738cs.AI
收藏

面向个性化和情境感知的Transformer模型:用于预测可穿戴传感器数据后干预的生理反应

Personalized and Context-Aware Transformer Models for Predicting Post-Intervention Physiological Responses from Wearable Sensor Data

Harvard University(哈佛大学);Princeton University(普林斯顿大学)

Esther Brown, Victoria Dean, Finale Doshi-Velez

AI总结:

本文提出基于Transformer的模型,用于预测干预后生理指标的时间轨迹及变化方向,通过结合多时间窗百分比变化和用户标记事件,验证个性化预测的可行性。

摘要:

消费者可穿戴设备能够连续监测与压力和恢复相关的生理数据,但将其转化为可操作的个性化压力管理建议仍具挑战性。本文提出一个框架,用于预测干预后的生理指标轨迹及变化方向。我们的方法结合了Transformer模型来预测多时间窗的百分比变化、各时间窗的变化方向(正、负或中性)以及使用可穿戴传感器数据叠加用户标记事件和干预的实证研究。该概念验证表明个性化干预后预测是可行的。我们鼓励未来将其整合到压力管理工具中,以提供针对每个人当天的个性化干预建议,并在进一步验证后进行更大规模研究及必要的监管审查。

英文摘要:

Consumer wearables enable continuous measurement of physiological data related to stress and recovery, but turning these streams into actionable, personalized stress-management recommendations remains a challenge. In practice, users often do not know how a given intervention, defined as an activity intended to reduce stress, will affect heart rate (HR), heart rate variability (HRV), or inter-beat intervals (BBI) over the next 15 to 120 minutes. We present a framework that predicts post-intervention trajectories and the direction of change for these physiological indicators across time windows. Our methodology combines a Transformer model for multi-horizon trajectories of percent change relative to a pre-intervention baseline, direction-of-change calls (positive, negative, or neutral) at each horizon, and an empirical study using wearable sensor data overlaid with user-tagged events and interventions. This proof of concept shows that personalized post-intervention prediction is feasible. We encourage future integration into stress-management tools for personalized intervention recommendations tailored to each person's day following further validation in larger studies and, where applicable, appropriate regulatory review.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑