T3S: Effective Representation Learning for Trajectory Similarity Computation

Yang, P; Wang, H; Zhang, Y; Qin, L; Zhang, W; Lin, X

T3S: Effective Representation Learning for Trajectory Similarity Computation

Yang, P Wang, H Zhang, Y

Qin, L Zhang, W Lin, X

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2021 IEEE 37th International Conference on Data Engineering (ICDE), 2021, 2021-April, pp. 2183-2188
Issue Date:: 2021-06-22

Closed Access

	Filename	Description	Size
	T3S_Effective_Representation_Learning_for_Trajectory_Similarity_Computation.pdf	Published version	2.11 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yang, P
dc.contributor.author	Wang, H
dc.contributor.author	Zhang, Y https://orcid.org/0000-0002-2674-1638
dc.contributor.author	Qin, L
dc.contributor.author	Zhang, W
dc.contributor.author	Lin, X
dc.date	2021-04-19
dc.date.accessioned	2022-03-30T03:37:34Z
dc.date.available	2022-03-30T03:37:34Z
dc.date.issued	2021-06-22
dc.identifier.citation	2021 IEEE 37th International Conference on Data Engineering (ICDE), 2021, 2021-April, pp. 2183-2188
dc.identifier.isbn	9781728191843
dc.identifier.issn	1084-4627
dc.identifier.uri	http://hdl.handle.net/10453/155705
dc.description.abstract	Advances of the sensor and GPS techniques have motivated the proliferation of trajectory data in a wide spectrum of applications. Trajectory similarity computation is one of the most fundamental problems in trajectory analytics. Considering that the high complexity of similarity computation is usually a bottleneck for large-scale trajectory data analysis, there are many research efforts for reducing the complexity such as the approximate algorithms. However, most of them are proposed for only one or two specific similarity measures, and thus cannot support different similarity measures well. In this paper, we propose a deep learning based model, namely T3S, which embeds each trajectory (i.e., a sequence of points) into a vector (point) in a d-dimensional space, and hence can significantly accelerate the similarity computation between the trajectories. By applying recurrent and attention neural networks, T3S can capture various unique characteristics of the trajectories such as the ordering of the points, spatial and structural information. Furthermore, our learning based T3S can easily handle any trajectory similarity measures by adjusting its parameters through the training. Extensive experiments on two real-life datasets demonstrate the effectiveness and efficiency of T3S. T3S outperforms state-of-the-art deep learning based methods under four popular trajectories similarity measures.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2021 IEEE 37th International Conference on Data Engineering (ICDE)
dc.relation.ispartof	2021 IEEE 37th International Conference on Data Engineering
dc.relation.ispartofseries	IEEE International Conference on Data Engineering
dc.relation.isbasedon	10.1109/icde51399.2021.00221
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	T3S: Effective Representation Learning for Trajectory Similarity Computation
dc.type	Conference Proceeding
utslib.citation.volume	2021-April
utslib.location.activity	Chania, Greece
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2022-03-30T03:37:32Z
pubs.finish-date	2021-04-22
pubs.publication-status	Published
pubs.start-date	2021-04-19
pubs.volume	2021-April

Abstract:

Advances of the sensor and GPS techniques have motivated the proliferation of trajectory data in a wide spectrum of applications. Trajectory similarity computation is one of the most fundamental problems in trajectory analytics. Considering that the high complexity of similarity computation is usually a bottleneck for large-scale trajectory data analysis, there are many research efforts for reducing the complexity such as the approximate algorithms. However, most of them are proposed for only one or two specific similarity measures, and thus cannot support different similarity measures well. In this paper, we propose a deep learning based model, namely T3S, which embeds each trajectory (i.e., a sequence of points) into a vector (point) in a d-dimensional space, and hence can significantly accelerate the similarity computation between the trajectories. By applying recurrent and attention neural networks, T3S can capture various unique characteristics of the trajectories such as the ordering of the points, spatial and structural information. Furthermore, our learning based T3S can easily handle any trajectory similarity measures by adjusting its parameters through the training. Extensive experiments on two real-life datasets demonstrate the effectiveness and efficiency of T3S. T3S outperforms state-of-the-art deep learning based methods under four popular trajectories similarity measures.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/155705