A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM

doi:10.3390/s19040947

	A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM
	Gao, Xile 1; Luo, Haiyong 1; Wang, Qu 2; Zhao, Fang 3; Ye, Langlang 1; Zhang, Yuexia 4
	2019-02-02
发表期刊	SENSORS
ISSN	1424-8220
卷号	19 期号:4 页码:20
摘要	Recently, the demand for human activity recognition has become more and more urgent. It is widely used in indoor positioning, medical monitoring, safe driving, etc. Existing activity recognition approaches require either the location information of the sensors or the specific domain knowledge, which are expensive, intrusive, and inconvenient for pervasive implementation. In this paper, a human activity recognition algorithm based on SDAE (Stacking Denoising Autoencoder) and LightGBM (LGB) is proposed. The SDAE is adopted to sanitize the noise in raw sensor data and extract the most effective characteristic expression with unsupervised learning. The LGB reveals the inherent feature dependencies among categories for accurate human activity recognition. Extensive experiments are conducted on four datasets of distinct sensor combinations collected by different devices in three typical application scenarios, which are human moving modes, current static, and dynamic behaviors of users. The experimental results demonstrate that our proposed algorithm achieves an average accuracy of 95.99%, outperforming other comparative algorithms using XGBoost, CNN (Convolutional Neural Network), CNN + Statistical features, or single SDAE.
关键词	human activity recognition indoor positioning deep learning Stacking Denoising Autoencoder LightGBM
DOI	10.3390/s19040947
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2018YFB0505200] ; BUPT Excellent Ph.D. Students Foundation[CX2018102] ; National Natural Science Foundation of China[61872046] ; National Natural Science Foundation of China[61374214] ; Open Project of the Beijing Key Laboratory of Mobile Computing and Pervasive Device
WOS研究方向	Chemistry ; Electrochemistry ; Instruments & Instrumentation
WOS类目	Chemistry, Analytical ; Electrochemistry ; Instruments & Instrumentation
WOS记录号	WOS:000460829200198
出版者	MDPI
引用统计	被引频次：54[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/2XEOYT63/4132
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Luo, Haiyong
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 2.Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing 100876, Peoples R China 3.Beijing Univ Posts & Telecommun, Sch Software Engn, Beijing 100876, Peoples R China 4.Beijing Informat Sci & Technol Univ, Sch Informat & Commun Engn, Beijing 100876, Peoples R China
推荐引用方式 GB/T 7714	Gao, Xile,Luo, Haiyong,Wang, Qu,et al. A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM[J]. SENSORS,2019,19(4):20.
APA	Gao, Xile,Luo, Haiyong,Wang, Qu,Zhao, Fang,Ye, Langlang,&Zhang, Yuexia.(2019).A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM.SENSORS,19(4),20.
MLA	Gao, Xile,et al."A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM".SENSORS 19.4(2019):20.