A Hybrid Markov and LSTM Model for Indoor Location Prediction

doi:10.1109/ACCESS.2019.2961559

	A Hybrid Markov and LSTM Model for Indoor Location Prediction
	Wang, Peixiao 3,4; Wang, Hongen 2; Zhang, Hengcai 1,4; Lu, Feng 1,4; Wu, Sheng 3,4
刊名	IEEE ACCESS
	2019
卷号	7 页码:185928-185940
关键词	Indoor location prediction movement trajectory Markov-LSTM
ISSN号	2169-3536
DOI	10.1109/ACCESS.2019.2961559
通讯作者	Zhang, Hengcai(zhanghc@lreis.ac.cn) ; Wu, Sheng(wusheng@fzu.edu.cn)
英文摘要	Accurate and robust indoor location prediction plays an important role in indoor location services. Markov chains (MCs) have been widely adopted for location prediction due to their strong interpretability. However, multi-order Markov chains (k-MCs) are not suitable for predicting long sequences due to problems of dimensionality. This study proposes a hybrid Markov model for location prediction that integrates a long short-term memory model (LSTM); this hybrid model is referred to as the Markov-LSTM. First, a multi-step Markov transition matrix is defined to decompose the k-MC into multiple first-order MCs. The LSTM is then introduced to combine multiple first-order MCs to improve prediction performance. Extensive experiments are conducted using real indoor Wi-Fi positioning datasets collected in a shopping mall. The results show that the Markov-LSTM model significantly outperforms five existing baseline methods in terms of its predictive performance.
资助项目	National Natural Science Foundation of China[41771436] ; National Natural Science Foundation of China[41701521] ; National Key Research and Development Program of China[2016YFB0502104] ; National Key Research and Development Program of China[2017YFB0503500] ; Digital Fujian Program[2016-23]
WOS关键词	PEOPLE MOVEMENT ; VIEW
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000510024300016
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program of China ; Digital Fujian Program
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/132156]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhang, Hengcai; Wu, Sheng
作者单位	1.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, IGSNRR, Beijing 100101, Peoples R China 2.Shandong Univ Sci & Technol, Coll Geomat, Qingdao 266590, Peoples R China 3.Fuzhou Univ, Acad Digital China, Fuzhou 350002, Peoples R China 4.Fuzhou Univ, Fujian Collaborat Innovat Ctr Big Data Applicat G, Fuzhou 350002, Peoples R China
推荐引用方式 GB/T 7714	Wang, Peixiao,Wang, Hongen,Zhang, Hengcai,et al. A Hybrid Markov and LSTM Model for Indoor Location Prediction[J]. IEEE ACCESS,2019,7:185928-185940.
APA	Wang, Peixiao,Wang, Hongen,Zhang, Hengcai,Lu, Feng,&Wu, Sheng.(2019).A Hybrid Markov and LSTM Model for Indoor Location Prediction.IEEE ACCESS,7,185928-185940.
MLA	Wang, Peixiao,et al."A Hybrid Markov and LSTM Model for Indoor Location Prediction".IEEE ACCESS 7(2019):185928-185940.