A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition

doi:10.1109/TKDE.2018.2855159

	A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition
	Hu, Chunyu 1,2,3; Chen, Yiqiang 1,2,3; Peng, Xiaohui 1,2,3; Yu, Han 4,5,6; Gao, Chenlong 1,2,3; Hu, Lisha 1,2,3
	2019-06-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	31 期号:6 页码:1038-1050
摘要	Recognizing activities of daily living is an important research topic for health monitoring and elderly care. However, most existing activity recognition models only work with static and pre-defined sensor configurations. Enabling an existing activity recognition model to adapt to the emergence of new sensors in a dynamic environment is a significant challenge. In this paper, we propose a novel feature incremental learning method, namely the Feature Incremental Random Forest (FIRF), to improve the performance of an existing model with a small amount of data on newly appeared features. It consists of two important components - 1) a mutual information based diversity generation strategy (MIDGS) and 2) a feature incremental tree growing mechanism (FITGM). MIDGS enhances the internal diversity of random forests, while FITGM improves the accuracy of individual decision trees. To evaluate the performance of FIRF, we conduct extensive experiments on three well-known public datasets for activity recognition. Experimental results demonstrate that FIRF is significantly more accurate and efficient compared with other state-of-the-art methods. It has the potential to allow the dynamic exploitation of new sensors in changing environments.
关键词	Feature incremental learning activity recognition random forest
DOI	10.1109/TKDE.2018.2855159
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2017YFB1002801] ; Natural Science Foundation of China[61572471] ; Natural Science Foundation of China[61502456] ; Natural Science Foundation of China[61472399] ; Beijing Municipal Science & Technology Commission[Z161100000216140] ; Nanyang Technological University, Nanyang Assistant Professorship (NAP)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:000466933700002
出版者	IEEE COMPUTER SOC
引用统计	被引频次：27[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4238
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yiqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100864, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 4.Nanyang Technol Univ, SCSE, Singapore 639798, Singapore 5.NTU UBC Res Ctr Excellence Act Living Elderly LIL, Singapore 639798, Singapore 6.Alibaba NTU Singapore Joint Res Inst, Singapore 639798, Singapore
推荐引用方式 GB/T 7714	Hu, Chunyu,Chen, Yiqiang,Peng, Xiaohui,et al. A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2019,31(6):1038-1050.
APA	Hu, Chunyu,Chen, Yiqiang,Peng, Xiaohui,Yu, Han,Gao, Chenlong,&Hu, Lisha.(2019).A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,31(6),1038-1050.
MLA	Hu, Chunyu,et al."A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 31.6(2019):1038-1050.