Complete User Mobility via User and Trajectory Embeddings
Nowadays, human movements are recorded with a variety of tools, forming different trajectorysets which are usually isolated from each other. These isolated trajectories come from different tools such as Twitter, Facebook, and so on that are related to one individual. Thus, it is important to link tr...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8536386/ |
id |
doaj-8fe0561bf663496aac1b2f45765060c7 |
---|---|
record_format |
Article |
spelling |
doaj-8fe0561bf663496aac1b2f45765060c72021-03-29T21:24:37ZengIEEEIEEE Access2169-35362018-01-016721257213610.1109/ACCESS.2018.28814578536386Complete User Mobility via User and Trajectory EmbeddingsGuowei Wang0https://orcid.org/0000-0003-2142-9263Dongliang Liao1Jing Li2School of Computer Science and Technology, University of Science and Technology of China, Hefei, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, ChinaNowadays, human movements are recorded with a variety of tools, forming different trajectorysets which are usually isolated from each other. These isolated trajectories come from different tools such as Twitter, Facebook, and so on that are related to one individual. Thus, it is important to link trajectories to users who generate them in order to provide massive information for facilitating trajectory mining tasks. Most previous work took advantage of trajectory similarities or trajectory classification models to solve this problem. However, these methods ignored the users’ movement patterns, which play a critical role in mining information from these users’ trajectories. In this paper, we propose a novel approach called trajectory linking via user embedding and trajectory embedding to learn the movement patterns of users and trajectories simultaneously, and use those movement patterns to link trajectories to users. More specifically, we leverage a graph-based location embedding method to learn the semantics of locations based on categorical and spatial information of locations. Then, a novel dual-objective neural network model is designed to integrate the sequential dependency and temporal regularity of trajectories to learn the movement patterns of users and their trajectories at the same time. A trajectory is then linked to the user who has the most similar movement pattern with it. Moreover, the advantages of our approach are empirically verified on real-world public trajectory datasets with convincing results.https://ieeexplore.ieee.org/document/8536386/Data miningneural networktrajectory miningtrajectory linkinguser profile |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Guowei Wang Dongliang Liao Jing Li |
spellingShingle |
Guowei Wang Dongliang Liao Jing Li Complete User Mobility via User and Trajectory Embeddings IEEE Access Data mining neural network trajectory mining trajectory linking user profile |
author_facet |
Guowei Wang Dongliang Liao Jing Li |
author_sort |
Guowei Wang |
title |
Complete User Mobility via User and Trajectory Embeddings |
title_short |
Complete User Mobility via User and Trajectory Embeddings |
title_full |
Complete User Mobility via User and Trajectory Embeddings |
title_fullStr |
Complete User Mobility via User and Trajectory Embeddings |
title_full_unstemmed |
Complete User Mobility via User and Trajectory Embeddings |
title_sort |
complete user mobility via user and trajectory embeddings |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Nowadays, human movements are recorded with a variety of tools, forming different trajectorysets which are usually isolated from each other. These isolated trajectories come from different tools such as Twitter, Facebook, and so on that are related to one individual. Thus, it is important to link trajectories to users who generate them in order to provide massive information for facilitating trajectory mining tasks. Most previous work took advantage of trajectory similarities or trajectory classification models to solve this problem. However, these methods ignored the users’ movement patterns, which play a critical role in mining information from these users’ trajectories. In this paper, we propose a novel approach called trajectory linking via user embedding and trajectory embedding to learn the movement patterns of users and trajectories simultaneously, and use those movement patterns to link trajectories to users. More specifically, we leverage a graph-based location embedding method to learn the semantics of locations based on categorical and spatial information of locations. Then, a novel dual-objective neural network model is designed to integrate the sequential dependency and temporal regularity of trajectories to learn the movement patterns of users and their trajectories at the same time. A trajectory is then linked to the user who has the most similar movement pattern with it. Moreover, the advantages of our approach are empirically verified on real-world public trajectory datasets with convincing results. |
topic |
Data mining neural network trajectory mining trajectory linking user profile |
url |
https://ieeexplore.ieee.org/document/8536386/ |
work_keys_str_mv |
AT guoweiwang completeusermobilityviauserandtrajectoryembeddings AT dongliangliao completeusermobilityviauserandtrajectoryembeddings AT jingli completeusermobilityviauserandtrajectoryembeddings |
_version_ |
1724193012230127616 |