ReliaGate：面向低风险可穿戴设备压力预测的可靠性路由
ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction
查看机构详情
- Dartmouth College（达特茅斯学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究提出ReliaGate框架，通过事后门控模块在可穿戴压力预测中实现固定标签可靠性路由，在四个可穿戴数据集上验证了其性能，为相关研究提供了操作框架。
中文摘要 AI 辅助
我们研究可穿戴压力系统应何时呈现预测结果而非更改预测结果。在低风险的反思与总结场景中，总体准确率是不够的，因为弃权（不执行）可减少误差，但会使部分人获得极少或没有信息。我们提出固定标签可靠性路由：在锁定分类器输出协议规定的压力/非压力标签后，事后门控模块要么呈现该未改变的标签，要么将其作为不可用结果弃权。ReliaGate 将已确立的置信度、信号质量/可信度、一致性、训练标准化的非典型性以及训练拟合的几何线索组合为事后正确性分数。我们使用受试者不重叠的折叠、验证选择的路由、配对的保留受试者区间，以及汇总和受试者层面的分析，对四个可穿戴数据集进行评估。WESAD 点估计值支持 ReliaGate，UBFC-Phys 的主要覆盖/风险区间支持 ReliaGate，E4 检查结果则参差不齐。ReliaGate 提供了一个操作框架，用于研究跨受试者的呈现标签误差、输出可用性和接受输出分布，无需修改标签，也不提供临床或有限样本风险保证。
英文摘要
We study when a wearable stress system should surface a prediction rather than change it. In low-stakes reflection and summary settings, aggregate accuracy is insufficient because withholding can reduce error while leaving some people with little or no information. We formulate fixed-label reliability routing: after a locked classifier emits a protocol-defined stress/non-stress label, a post-hoc gate surfaces that unchanged label or withholds it as unavailable. ReliaGate assembles established confidence, signal-quality/trust, agreement, train-standardized atypicality, and train-fitted geometry cues into a post-hoc correctness score. We evaluate four wearable datasets using subject-disjoint folds, validation-selected routing, paired held-out-subject intervals, and pooled and per-subject analyses. WESAD point estimates favored ReliaGate, UBFC-Phys primary coverage/risk intervals favored ReliaGate, and E4 checks were mixed. ReliaGate provides an operational framework for studying surfaced-label error, output availability, and accepted-output distribution across subjects, without revising labels or providing clinical or finite-sample risk guarantees.
