Please use this identifier to cite or link to this item:
Title: A non-parametric generative model for human trajectories
Authors: Ouyang, K
Shokri, R 
Rosenblum, DS 
Yang, W 
Issue Date: 1-Jan-2018
Publisher: International Joint Conferences on Artificial Intelligence Organization
Citation: Ouyang, K, Shokri, R, Rosenblum, DS, Yang, W (2018-01-01). A non-parametric generative model for human trajectories. Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18} 2018-July : 3812-3817. ScholarBank@NUS Repository.
Abstract: © 2018 International Joint Conferences on Artificial Intelligence. All right reserved. Modeling human mobility and generating synthetic yet realistic location trajectories play a fundamental role in many (privacy-aware) analysis and design processes that operate on location data. In this paper, we propose a non-parametric generative model for location trajectories that can capture high-order geographic and semantic features of human mobility. We design a simple and intuitive yet effective embedding for locations traces, and use generative adversarial networks to produce data points in this space, which will finally be transformed back to a sequential location trajectory form. We evaluate our method on realistic location trajectories and compare our synthetic traces with multiple existing methods on how they preserve geographic and semantic features of real traces at both aggregated and individual levels. Our empirical results prove the capability of our generative model in preserving various useful properties of real data.
Source Title: Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}
ISBN: 9780999241127
ISSN: 10450823
DOI: 10.24963/ijcai.2018/530
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
0530.pdfPublished version1.27 MBAdobe PDF




checked on Jun 28, 2022

Page view(s)

checked on Jun 23, 2022


checked on Jun 23, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.