期刊
WIRELESS PERSONAL COMMUNICATIONS
卷 117, 期 2, 页码 637-654出版社
SPRINGER
DOI: 10.1007/s11277-020-07891-1
关键词
Privacy; Semi-supervised; Unsupervised; Transfer learning; HAR
This paper addresses the challenge faced by machine learning in human activity recognition systems by proposing solutions for transfer learning with privacy preservation in both centralized and distributed settings. The algorithms presented in the paper transfer knowledge without the need to share original data and effectively protect data privacy.
One of the challenges faced by machine learning in human activity recognition systems is the different distributions of the training and test samples. Transfer learning constitutes a solution to this problem. On the other hand, to perform transfer learning, it is necessary to have access to the original dataset. However, access to the dataset to implement the transfer learning algorithms results in a privacy breach. To deal with this challenge, this paper presents semi-supervised and unsupervised scenarios for privacy-preserving transfer learning in centralized and distributed manner. In the proposed distributed algorithms, it is not necessary to share the original data among the clients to implement the transfer learning algorithms. Instead, the transfer learning process can be fulfilled without having the original datasets. PPSETR and PPUSTR algorithms transfer the knowledge while preserving the privacy of the datasets on the client side. In contrast, PPDSETR and PPDUSTR algorithms provide the privacy protection of the distributed data on both the client and server sides. The proposed semi-supervised algorithms reduce the recognition error rate by 20.58% and the unsupervised algorithms decrease the recognition error rate by about 15.97% while these algorithms considerably preserve the privacy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据