中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM

文献类型：期刊论文

作者Zhang, Yuexia1; Gao, Xile4; Luo, Haiyong4; Zhao, Fang2; Wang, Qu3; Ye, Langlang4
刊名SENSORS
出版日期2019-02-02
卷号19期号:4页码:20
关键词human activity recognition indoor positioning deep learning Stacking Denoising Autoencoder LightGBM
ISSN号1424-8220
DOI10.3390/s19040947
英文摘要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.
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
语种英语
WOS记录号WOS:000460829200198
出版者MDPI
源URL[http://119.78.100.204/handle/2XEOYT63/4131]  
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.Beijing Informat Sci & Technol Univ, Sch Informat & Commun Engn, Beijing 100876, Peoples R China
2.Beijing Univ Posts & Telecommun, Sch Software Engn, Beijing 100876, Peoples R China
3.Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing 100876, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Yuexia,Gao, Xile,Luo, Haiyong,et al. A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM[J]. SENSORS,2019,19(4):20.
APA Zhang, Yuexia,Gao, Xile,Luo, Haiyong,Zhao, Fang,Wang, Qu,&Ye, Langlang.(2019).A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM.SENSORS,19(4),20.
MLA Zhang, Yuexia,et al."A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM".SENSORS 19.4(2019):20.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。