Multi-Aspect Embedding for Attribute-Aware Trajectories

doi:10.3390/sym11091149

	Multi-Aspect Embedding for Attribute-Aware Trajectories
	Boonchoo, Thapana 1,2; Ao, Xiang 1,2; He, Qing 1,2
	2019-09-01
发表期刊	SYMMETRY-BASEL
卷号	11 期号:9 页码:17
摘要	Motivated by the proliferation of trajectory data produced by advanced GPS-enabled devices, trajectory is gaining in complexity and beginning to embroil additional attributes beyond simply the coordinates. As a consequence, this creates the potential to define the similarity between two attribute-aware trajectories. However, most existing trajectory similarity approaches focus only on location based proximities and fail to capture the semantic similarities encompassed by these additional asymmetric attributes (aspects) of trajectories. In this paper, we propose multi-aspect embedding for attribute-aware trajectories (MAEAT), a representation learning approach for trajectories that simultaneously models the similarities according to their multiple aspects. MAEAT is built upon a sentence embedding algorithm and directly learns whole trajectory embedding via predicting the context aspect tokens when given a trajectory. Two kinds of token generation methods are proposed to extract multiple aspects from the raw trajectories, and a regularization is devised to control the importance among aspects. Extensive experiments on the benchmark and real-world datasets show the effectiveness and efficiency of the proposed MAEAT compared to the state-of-the-art and baseline methods. The results of MAEAT can well support representative downstream trajectory mining and management tasks, and the algorithm outperforms other compared methods in execution time by at least two orders of magnitude.
关键词	trajectory similarity computation multi-aspect embedding representation learning
DOI	10.3390/sym11091149
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFB1002104] ; National Natural Science Foundation of China[U1811461] ; National Natural Science Foundation of China[61602438] ; National Natural Science Foundation of China[91846113] ; National Natural Science Foundation of China[61573335] ; Project of Youth Innovation Promotion Association CAS
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000489177900085
出版者	MDPI
引用统计	被引频次：3[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/2XEOYT63/4629
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Boonchoo, Thapana; He, Qing
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Boonchoo, Thapana,Ao, Xiang,He, Qing. Multi-Aspect Embedding for Attribute-Aware Trajectories[J]. SYMMETRY-BASEL,2019,11(9):17.
APA	Boonchoo, Thapana,Ao, Xiang,&He, Qing.(2019).Multi-Aspect Embedding for Attribute-Aware Trajectories.SYMMETRY-BASEL,11(9),17.
MLA	Boonchoo, Thapana,et al."Multi-Aspect Embedding for Attribute-Aware Trajectories".SYMMETRY-BASEL 11.9(2019):17.