发表机构
Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过控制归一化来源，评估了基于伪影标注预训练的 SAFE-EDA 模型在腕部 EDA 情感识别中的效果，发现预训练增益仅在未使用用户自身数据时显著，且伪影监督优于自监督，强调了报告归一化选择的重要性。
AI 中文摘要
腕部皮肤电活动（EDA）的幅度因人而异，因此情感识别模型在分类前会对输入进行归一化。在留出受试者上测试此类模型的研究很少报告归一化统计数据的来源，然而，从留出受试者自身的记录中计算出的统计数据提供了设备在首次佩戴时并不拥有的信息。我们探究了这一选择如何改变预训练所测得的好处。一个紧凑的卷积网络 SAFE-EDA 在来自 43 名受试者的专家伪影标注上进行了预训练，并与在可穿戴压力和情感检测（WESAD）数据集（15 名受试者，留一受试者交叉验证）上从头训练的同一网络进行了比较，同时将两种归一化来源与四种窗口跳跃进行了交叉组合。当统计数据仅来自训练受试者时，预训练将宏 F1 提高了 0.078 至 0.227；当统计数据来自留出用户的完整记录时，增益降至 0.020 至 0.050 之间，且不再显著。伪影监督比在同一记录上的自监督预训练有用得多（0.078 对比 0.008）。在两个数据集的 13 种配置中，预训练网络在 12 种配置下表现更好，但在第二个数据集（26 名受试者）上，逐用户归一化反而增加了增益而非减少，因此这种交互作用取决于数据。在 50 项已发表的 WESAD 研究中，只有五项说明了用于归一化的数据。报告这一选择对于区分首次使用性能与校准后性能是必要的。
英文摘要
Wrist electrodermal activity (EDA) differs in amplitude from one person to the next, so affect-recognition models normalize their input before classification. Studies that test such models on held-out subjects seldom report where the normalization statistics come from, yet statistics computed from the held-out subject's own recording give the model information that a device does not have when it is first worn. We asked how this choice alters the measured benefit of pretraining. A compact convolutional network, SAFE-EDA, was pretrained on expert artifact annotations from 43 subjects and compared with the same network trained from scratch on the Wearable Stress and Affect Detection (WESAD) dataset (15 subjects, leave-one-subject-out), with two normalization sources crossed with four window hops. When the statistics came only from training subjects, pretraining raised macro-F1 by 0.078 to 0.227; when they came from the held-out user's full recording, the gain fell to between 0.020 and 0.050 and was no longer significant. Artifact supervision was far more useful than self-supervised pretraining on the same recordings (0.078 versus 0.008). Across 13 configurations in two datasets, the pretrained network was better in 12, but on the second dataset (26 subjects) per-user normalization increased the gain instead of reducing it, so the interaction depends on the data. Only five of 50 published WESAD studies state which data were used for normalization. Reporting this choice is necessary to separate first-use performance from performance after calibration.
Comments12 pages, 6 figures, 6 tables, plus 2 pages of supplementary material. Code: https://github.com/rtb-1005/SAFE-EDA
