发表机构
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出HealthCAT框架，结合纯编码器Transformer与AttentiveCAT实现可穿戴传感器数据的健康指标预测及时间解释，在两个数据集上的F1分数、准确率优于基线，可支持健康监测等应用。
AI 中文摘要
可穿戴传感器持续采集细粒度多变量时间序列数据，为建模与健康结局相关的行为模式提供了可能。然而，现有深度学习方法优先考虑预测准确性而非可解释性，限制了其在健康研究中的应用。本研究提出HealthCAT，一种灵活框架，将纯编码器Transformer与注意力类激活令牌（AttentiveCAT）相结合，生成特定类别、时间步级别的解释，这些解释可映射回领域相关的行为周期（如一天中的时间），支持对可穿戴传感器数据的个体层面分析。我们使用两个真实世界可穿戴传感器数据集（共306名参与者）对HealthCAT进行评估。HealthCAT在两个数据集上的F1分数较深度学习基线最高提升17%，准确率最高提升12%（p<0.05）。在掩码实验中，HealthCAT识别的时间步在所有掩码条件下均比随机选择具有显著更高的预测价值（p<0.05），表明识别的时间步具有预测信息性。通过将预测性能与经验证的时间步级可解释性相结合，HealthCAT将可穿戴传感器分析从聚合指标推进到支持健康监测、行为模式分析及健康研究中干预设计的时间模式。本研究的意义在于，它能从可穿戴传感器数据中准确预测健康指标，同时提供关于身体活动模式何时及如何发生的见解，而非仅依赖聚合汇总指标。
英文摘要
Wearable sensors continuously capture fine-grained multivariate time-series data, providing opportunities to model behavioural patterns associated with health outcomes. However, existing deep learning methods prioritise predictive accuracy over interpretability, limiting their application in health research. In this study, we present HealthCAT, a flexible framework that integrates an Encoder-only Transformer with an Attentive Class Activation Token (AttentiveCAT) to generate class-specific, time-step-level interpretations. These interpretations can be mapped back onto behavioural cycles that are relevant to the domain (e.g., time-of-day), supporting individual-level analysis of wearable sensor data. We evaluated HealthCAT using two real-world wearable sensor datasets (306 participants in total). HealthCAT outperformed deep learning baselines by up to 17\% in F1-score and 12\% in accuracy on both datasets ($p<0.05$). In masking experiments, the time steps identified by HealthCAT carried significantly more predictive value than random selection across all masking conditions ($p<0.05$), indicating that the identified time steps are predictively informative. By coupling predictive performance with validated time-step-level interpretability, HealthCAT moves wearable sensor analysis beyond aggregated metrics towards temporal patterns that support health monitoring, behavioural pattern analysis, and intervention design in health research. The significance of this work is that it enables accurate prediction of health indicators from wearable sensor data while providing insights into when and how physical activity patterns occur, rather than relying solely on aggregated summary measures.
