期刊
SENSORS
卷 19, 期 1, 页码 -出版社
MDPI
DOI: 10.3390/s19010057
关键词
human activity recognition; transfer learning; deep learning; sensor data
资金
- National Natural Science Foundation of China [61772159]
- Science and technology Special Project of National Regional Innovation Center [2017QYCX12]
- Natural Science Foundation of Shandong Province [ZR2017MF026]
- HIT.NSRIF.201703 Innovation Foundation (Key Cultivation Project) of Harbin Institute of Technology [HIT.NSRIF.201703]
Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individual using a model trained on data from other users. The decline on the accuracy of recognition restricts activity recognition in practice. At present, there is little research on the transferring of deep learning model in this field. This is the first time as we known, an empirical study was carried out on deep transfer learning between users with unlabeled data of target. We compared several widely-used algorithms and found that Maximum Mean Discrepancy (MMD) method is most suitable for HAR. We studied the distribution of features generated from sensor data. We improved the existing method from the aspect of features distribution with center loss and get better results. The observations and insights in this study have deepened the understanding of transfer learning in the activity recognition field and provided guidance for further research.
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