用于直接事件时间监督的边界密度似然
Boundary Density Likelihood for Direct Event-Time Supervision
AI总结：
该研究提出BDL方法，针对事件时间直接训练序列模型，在睡眠研究中显著提升事件检测性能，验证了直接事件时间监督的有效性。
摘要：
事件检测将长记录转换为一组稀疏的排序时间戳。然而，许多序列模型是针对样本级分割进行训练的，仅在训练后将预测状态转换为事件。我们探究直接针对评估输出进行训练是否能提升检测性能。边界密度似然（Boundary Density Likelihood, BDL）为每个标注事件分配一个单位目标质量，通过平滑和时间下采样保留该质量，并使用泊松目标函数估计每个输出分箱中的预期事件质量；局部峰值成为排序后的检测结果。在预先指定的五重嵌套睡眠研究中，BDL-Hard将汇总的折外出平均精度均值（mAP）从0.586提升至0.705，较区间分割提升11.9个百分点（95%区间为[10.8, 13.0]），严格一分钟平均精度（AP）从0.071提升至0.286（提升4.0倍，增加21.5个百分点），且在每个外折均实现提升。独立的保留集重复实验复现了该效应方向。匹配的边界-二值交叉熵（boundary-BCE）检测器达到0.702的mAP，表明直接边界监督与事件解码贡献了大部分增益，泊松目标函数的贡献较小。离线卷积模型呈现相同趋势；因果模型、Transformer及按患者分组的癫痫发作实验则留下更广泛的泛化性待探究。我们的结果支持在时间戳定义评估输出时，基于事件时间进行训练。
英文摘要：
Event detection turns long recordings into a sparse set of ranked timestamps. Yet many sequence models are trained for samplewise segmentation and only convert predicted states into events after training. We ask whether training directly for the evaluated output improves detection. Boundary Density Likelihood (BDL) assigns one unit of target mass to each annotated event, preserves that mass through smoothing and temporal downsampling, and uses a Poisson objective to estimate expected event mass in each output bin; local peaks become ranked detections. In a prespecified five-fold nested sleep study, BDL-Hard raises pooled out-of-fold mAP from 0.586 to 0.705 over interval segmentation (+11.9 percentage points; 95% interval [10.8, 13.0]) and strict one-minute AP from 0.071 to 0.286 (4.0x; +21.5 points), improving on every outer fold. A separate held-out rerun reproduces the direction of the effect. A matched boundary-BCE detector reaches 0.702 mAP, showing that direct boundary supervision and event decoding account for most of the gain, with a smaller contribution from the Poisson objective. The same trend appears with an offline convolutional model; causal, Transformer, and patient-grouped seizure experiments leave broader generalization unresolved. Our results support training on event times when timestamps define the evaluated output.
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。
