arXiv：cs.LG（机器学习，全量分类）· Haochen Chai, Xinbi Luo, Zining Liu, Fangfang Jiang·· 15 小时前AI 评分32
SAFE-EDA：伪影标注可部分替代逐用户校准，研究揭示归一化来源如何影响腕部 EDA 情感识别
Artifact Annotations Partially Substitute for Per-User Calibration: SAFE-EDA and a Normalization-Controlled Evaluation of Wrist-EDA Affect Recognition
AI 导读
研究提出 SAFE-EDA 卷积网络，用 43 名受试者的专家伪影标注预训练，在 WESAD 数据集（15 人，留一受试者）上评估腕部 EDA 情感识别。当归一化统计仅来自训练受试者时，预训练将 macro-F1 提升 0.078 至 0.227；若使用留出用户自身录制的统计，增益降至 0.020 至 0.050 且不再显著。
正文
Abstract: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.
| Comments: | 12 pages, 6 figures, 6 tables, plus 2 pages of supplementary material. Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.01692 [cs.LG] |
| (or arXiv:2610.01692v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01692 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haochen Chai [view email]
[v1]
Thu, 1 Oct 2026 13:45:54 UTC (207 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org