Models, datasets, and raw results of "Measurement of sweat gland activity by discrete sweat sensing, statistics, and deep learning"

The paper investigated the use of deep learning for deriving the number of active sweat glands and the sweat rate per gland from a(n in-silico) discrete sweat sensing device. The study was completely in silico. This dataset includes the trained neural networks that were evaluated for this study (.keras, version in READ ME), the synthetic datasets that were used for training and testing (.parquet) and the results of the tests (.xlsx). The latter contains more results than presented in the paper (including the precision and recall).

本论文探究了利用深度学习技术，从硅基模拟（in silico）离散式汗液传感装置中提取活跃汗腺总数与单腺体汗液分泌速率的研究方法。本研究全程采用硅基模拟方式开展。本数据集包含本次研究中评估所用的经训练神经网络（文件格式为.keras，版本信息详见READ ME）、用于模型训练与测试的合成数据集（文件格式为.parquet），以及测试结果文件（文件格式为.xlsx）。该测试结果文件包含的内容较论文中呈现的更为丰富，涵盖了精确率（precision）与召回率（recall）等指标。