Evaluating mobility models for temporal prediction with high-granularity mobility data

Yohan Chon, Hyojeong Shin, Elmurod Talipov, Hojung Cha

Research output: Chapter in Book/Report/Conference proceedingConference contribution

59 Citations (Scopus)

Abstract

A mobility model is an essential requirement in accurately predicting an individual's future location. While extensive studies have been conducted to predict human mobility, previous work used coarse-grained mobility data with limited ability to capture human movements at a fine-grained level. In this paper, we empirically analyze several mobility models for predicting temporal behavior of an individual user. Unlike previous approaches, which employed coarse-grained mobility data with partial temporal-coverage, we use fine-grained and continuous mobility data for the evaluation of mobility models.We explore the regularity and predictability of human mobility, and evaluate location-dependent and location-independent models with several feature-aided schemes. Our experimental results show that a location-dependent predictor is better than a location-independent predictor for predicting temporal behavior of individual user. The duration of stay at a location is strongly correlated to the arrival time at the current location and the return-tendency to the next location, rather than recent k location sequences.We also find that false-positive predictions can be reduced by adaptive use of mobility models.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012
Pages206-212
Number of pages7
DOIs
Publication statusPublished - 2012 Jun 4
Event10th IEEE International Conference on Pervasive Computing and Communications, PerCom 2012 - Lugano, Switzerland
Duration: 2012 Mar 192012 Mar 23

Publication series

Name2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012

Other

Other10th IEEE International Conference on Pervasive Computing and Communications, PerCom 2012
CountrySwitzerland
CityLugano
Period12/3/1912/3/23

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Chon, Y., Shin, H., Talipov, E., & Cha, H. (2012). Evaluating mobility models for temporal prediction with high-granularity mobility data. In 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012 (pp. 206-212). [6199868] (2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012). https://doi.org/10.1109/PerCom.2012.6199868
Chon, Yohan ; Shin, Hyojeong ; Talipov, Elmurod ; Cha, Hojung. / Evaluating mobility models for temporal prediction with high-granularity mobility data. 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012. 2012. pp. 206-212 (2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012).
@inproceedings{f25f6033f5a94eb8ba3d99ab813b60d1,
title = "Evaluating mobility models for temporal prediction with high-granularity mobility data",
abstract = "A mobility model is an essential requirement in accurately predicting an individual's future location. While extensive studies have been conducted to predict human mobility, previous work used coarse-grained mobility data with limited ability to capture human movements at a fine-grained level. In this paper, we empirically analyze several mobility models for predicting temporal behavior of an individual user. Unlike previous approaches, which employed coarse-grained mobility data with partial temporal-coverage, we use fine-grained and continuous mobility data for the evaluation of mobility models.We explore the regularity and predictability of human mobility, and evaluate location-dependent and location-independent models with several feature-aided schemes. Our experimental results show that a location-dependent predictor is better than a location-independent predictor for predicting temporal behavior of individual user. The duration of stay at a location is strongly correlated to the arrival time at the current location and the return-tendency to the next location, rather than recent k location sequences.We also find that false-positive predictions can be reduced by adaptive use of mobility models.",
author = "Yohan Chon and Hyojeong Shin and Elmurod Talipov and Hojung Cha",
year = "2012",
month = "6",
day = "4",
doi = "10.1109/PerCom.2012.6199868",
language = "English",
isbn = "9781467302586",
series = "2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012",
pages = "206--212",
booktitle = "2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012",

}

Chon, Y, Shin, H, Talipov, E & Cha, H 2012, Evaluating mobility models for temporal prediction with high-granularity mobility data. in 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012., 6199868, 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012, pp. 206-212, 10th IEEE International Conference on Pervasive Computing and Communications, PerCom 2012, Lugano, Switzerland, 12/3/19. https://doi.org/10.1109/PerCom.2012.6199868

Evaluating mobility models for temporal prediction with high-granularity mobility data. / Chon, Yohan; Shin, Hyojeong; Talipov, Elmurod; Cha, Hojung.

2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012. 2012. p. 206-212 6199868 (2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Evaluating mobility models for temporal prediction with high-granularity mobility data

AU - Chon, Yohan

AU - Shin, Hyojeong

AU - Talipov, Elmurod

AU - Cha, Hojung

PY - 2012/6/4

Y1 - 2012/6/4

N2 - A mobility model is an essential requirement in accurately predicting an individual's future location. While extensive studies have been conducted to predict human mobility, previous work used coarse-grained mobility data with limited ability to capture human movements at a fine-grained level. In this paper, we empirically analyze several mobility models for predicting temporal behavior of an individual user. Unlike previous approaches, which employed coarse-grained mobility data with partial temporal-coverage, we use fine-grained and continuous mobility data for the evaluation of mobility models.We explore the regularity and predictability of human mobility, and evaluate location-dependent and location-independent models with several feature-aided schemes. Our experimental results show that a location-dependent predictor is better than a location-independent predictor for predicting temporal behavior of individual user. The duration of stay at a location is strongly correlated to the arrival time at the current location and the return-tendency to the next location, rather than recent k location sequences.We also find that false-positive predictions can be reduced by adaptive use of mobility models.

AB - A mobility model is an essential requirement in accurately predicting an individual's future location. While extensive studies have been conducted to predict human mobility, previous work used coarse-grained mobility data with limited ability to capture human movements at a fine-grained level. In this paper, we empirically analyze several mobility models for predicting temporal behavior of an individual user. Unlike previous approaches, which employed coarse-grained mobility data with partial temporal-coverage, we use fine-grained and continuous mobility data for the evaluation of mobility models.We explore the regularity and predictability of human mobility, and evaluate location-dependent and location-independent models with several feature-aided schemes. Our experimental results show that a location-dependent predictor is better than a location-independent predictor for predicting temporal behavior of individual user. The duration of stay at a location is strongly correlated to the arrival time at the current location and the return-tendency to the next location, rather than recent k location sequences.We also find that false-positive predictions can be reduced by adaptive use of mobility models.

UR - http://www.scopus.com/inward/record.url?scp=84861594261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861594261&partnerID=8YFLogxK

U2 - 10.1109/PerCom.2012.6199868

DO - 10.1109/PerCom.2012.6199868

M3 - Conference contribution

AN - SCOPUS:84861594261

SN - 9781467302586

T3 - 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012

SP - 206

EP - 212

BT - 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012

ER -

Chon Y, Shin H, Talipov E, Cha H. Evaluating mobility models for temporal prediction with high-granularity mobility data. In 2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012. 2012. p. 206-212. 6199868. (2012 IEEE International Conference on Pervasive Computing and Communications, PerCom 2012). https://doi.org/10.1109/PerCom.2012.6199868