Cross-position activity recognition with stratified transfer learning

doi:10.1016/j.pmcj.2019.04.004

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Cross-position activity recognition with stratified transfer learning
	Huang, Meiyu 2; Chen, Yiqiang 3,4; Wang, Jindong 3,4; Yu, Han 1
刊名	PERVASIVE AND MOBILE COMPUTING
	2019-07-01
卷号	57 页码:1-13
关键词	Activity recognition Transfer learning Domain adaptation Pervasive computing
ISSN号	1574-1192
DOI	10.1016/j.pmcj.2019.04.004
英文摘要	Human activity recognition (HAR) aims to recognize the activities of daily living by utilizing the sensors attached to different body parts. HAR relies on the machine learning models trained using sufficient activity data. However, when the labels from a certain body position (i.e. target domain) are missing, how to leverage the data from other positions (i.e. source domain) to help recognize the activities of this position? This problem can be divided into two steps. Firstly, when there are several source domains available, it is often difficult to select the most similar source domain to the target domain. Secondly, with the selected source domain, we need to perform accurate knowledge transfer between domains in order to recognize the activities on the target domain. Existing methods only learn the global distance between domains while ignoring the local property. In this paper, we propose a Stratified Transfer Learning (STL) framework to perform both source domain selection and activity transfer. STL is based on our proposed Stratified distance to capture the local property of domains. STL consists of two components: 1) Stratified Domain Selection (STL-SDS), which can select the most similar source domain to the target domain; and 2) Stratified Activity Transfer (STL-SAT), which is able to perform accurate knowledge transfer. Extensive experiments on three public activity recognition datasets demonstrate the superiority of STL. (C) 2019 Elsevier B.V. All rights reserved.
资助项目	National Key RD Plan of China[2017YFB1002802] ; NSFC[61572471] ; NSFC[61472399] ; NSFC[61702520] ; Beijing Municipal Science & Technology Commission[Z171100000117017]
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000470252100001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4211]
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.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore 2.China Acad Space Technol, Qian Xuesen Lab Space Technol, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Devices, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Huang, Meiyu,Chen, Yiqiang,Wang, Jindong,et al. Cross-position activity recognition with stratified transfer learning[J]. PERVASIVE AND MOBILE COMPUTING,2019,57:1-13.
APA	Huang, Meiyu,Chen, Yiqiang,Wang, Jindong,&Yu, Han.(2019).Cross-position activity recognition with stratified transfer learning.PERVASIVE AND MOBILE COMPUTING,57,1-13.
MLA	Huang, Meiyu,et al."Cross-position activity recognition with stratified transfer learning".PERVASIVE AND MOBILE COMPUTING 57(2019):1-13.