发表机构
University of Pittsburgh; University of Maryland, College Park（匹兹堡大学; 马里兰大学帕克分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出COVER方法，通过辅助信息引导的错误学习和固定尺度细化，在睡眠分期级联中最大化覆盖率，在Sleep-EDF-20上达到50.4%的平均覆盖率，优于现有基线。
AI 中文摘要
传统的睡眠分期方法对每个脑电图（EEG）时段应用相同的模型。这种统一部署在较小模型能够可靠处理的时段上浪费了计算资源，因此推动了级联（cascade）方法的发展，其中主分类器接受其可靠的预测，并将剩余部分交给更强大的模型处理。本文研究了这种级联的第一阶段：在规定的可接受风险目标下，最大化固定主预测的覆盖率。我们提出了COVER（面向覆盖率的错误排序），它整合了两项关键创新：（i）辅助信息引导的主错误学习，用学习到的错误分数替代最大软概率（MSP），同时保留主标签；以及（ii）固定尺度评分器细化，基于该分数直接最大化经验可接受风险约束下的覆盖率，而不是优化所有时段的错误预测准确性。我们在Sleep-EDF-20数据集上以5%的可接受风险目标评估COVER，受试者从所有拟合和选择中留出。辅助信息引导的错误学习将平均受试者覆盖率从MSP的31.5%提高到48.8%，且受试者平均风险相似。在相同接受量下，当MSP接受与学习评分器在每个受试者中相同数量的时段（总计20,639个）时，错误从1,467降至867。固定尺度细化在嵌套开发中比其初始化增加了1.7个百分点的覆盖率，COVER在八个评估的评分器中达到了最高的平均覆盖率，为50.4%，受试者平均风险为4.5%，高于选择性排序基线SELE（49.3%）和概率融合比较器DuoF（43.6%）。据我们所知，这是首个将辅助信息引导的主错误学习与固定尺度覆盖率细化相结合用于选择性睡眠分期的工作，为级联睡眠分期中可靠性感知的计算分配提供了基础。
英文摘要
Traditional sleep-staging methods apply the same model to every EEG epoch. Such uniform deployment expends computation on epochs that a smaller model could handle reliably, motivating cascades in which a primary classifier accepts its reliable predictions and defers the remainder to a more capable model. In this paper, we study the first stage of such a cascade: maximizing the coverage of fixed primary predictions subject to a prescribed accepted-risk target. We propose COVER (COVerage-oriented Error Ranking), which integrates two key innovations: (i) auxiliary-informed primary-error learning, which replaces maximum softmax probability (MSP) with a learned error score while preserving the primary labels, and (ii) fixed-scale scorer refinement, which builds on this score to directly maximize coverage under an empirical accepted-risk constraint rather than error-prediction accuracy over all epochs. We evaluate COVER on Sleep-EDF-20 at a 5% accepted-risk target, with subjects held out from all fitting and selection. Auxiliary-informed error learning raises mean subject coverage from 31.5% for MSP to 48.8% at similar subject-equal risk. At equal acceptance volume, with MSP accepting the same number of epochs as the learned scorer in each subject (20,639 in total), errors fall from 1,467 to 867. Fixed-scale refinement then adds 1.7 percentage points of coverage over its initialization in nested development, and COVER attains the highest mean coverage among eight evaluated scorers, 50.4% at 4.5% subject-equal risk, above the selective-ranking baseline SELE (49.3%) and the probability-fusion comparator DuoF (43.6%). To the best of our knowledge, this is the first work to combine auxiliary-informed primary-error learning with fixed-scale coverage refinement for selective sleep staging, offering a basis for reliability-aware allocation of computation in cascaded sleep staging.
Comments20 pages, 3 figures; code and frozen-result reproduction: https://github.com/Kevin11Kaikai/COVER-Selective-Sleep-Staging
