首个专用于皮肤电活动的奠基模型，用2.5万小时数据训练
A foundation model for electrodermal activity data
- 构建25000小时公开皮肤电数据集EDAMAME，覆盖634人
- 新模型UME在8/10任务中超越基线，计算量仅为通用模型的1/20
- 适合生理信号研究者、可穿戴设备开发者使用
基础模型已从自然语言和视觉拓展至时间序列领域，包括生理信号。然而，皮肤电活动（EDA）建模进展受限于缺乏大规模、高质量且公开的数据集。EDA反映交感神经系统活动，广泛用于推断认知负荷、压力与参与度。目前仅有少数可穿戴设备支持持续无感采集，且现有大规模数据集为私有。为此，我们整合了来自24个公开数据集的EDA信号，构建了包含超过25,000小时数据、覆盖634名用户的EDAMAME数据集。基于此，我们训练了首个专用于EDA的奠基模型UME。在十项评估场景中的八项，UME表现优于基线模型，并达到通用时间序列基础模型水平，同时仅需20倍更少的计算资源。研究结果也揭示了EDA建模的固有挑战，推动后续研究以释放其全部潜力。所有数据集、模型权重与代码均已公开，以支持进一步研究。
原文摘要 · Abstract (English)
Foundation models have recently extended beyond natural language and vision to timeseries domains, including physiological signals. However, progress in electrodermal activity (EDA) modeling is hindered by the absence of large-scale, curated, and openly accessible datasets. EDA reflects sympathetic nervous system activity and is widely used to infer cognitive load, stress, and engagement. Yet very few wearable devices provide continuous, unobtrusive sensing, and the only large-scale archive to date is proprietary. To address this gap, we compile EDAMAME, a collection of EDA traces from 24 public datasets, comprising more than 25,000 hours from 634 users. Using this resource, we train UME, the first dedicated foundation model for EDA. In eight out of ten scenarios, UME outperforms baselines and matches generalist timeseries foundation models while using 20x fewer computational resources. Our findings, however, also highlight the intrinsic challenges of EDA modeling, motivating further research to unlock its full potential. All datasets, model weights, and code are released to support further research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。