Abstract

In recent years, using cell phone log data tomodel humanmobility patterns became an active research area. This problem is a challenging data mining problem due to huge size and non-uniformity of the log data, which introduces several granularity levels for the specification of temporal and spatial dimensions. This paper focuses on the prediction of the location of the next activity of the mobile phone users. There are several versions of this problem. In this work, we have concentrated on the following three problems: predicting the location and the time of the next user activity, predicting the location of the next activity of the user when the location of the user changes, and predicting both the location and the time of the activity of the user when the user's location changes. We have developed sequential pattern mining-based techniques for these three problems and validated the success of these methods with real data obtained from one of the largest mobile phone operators in Turkey. Our results are very encouraging, since we were able to obtain quite high accuracy results under small prediction sets.

Original languageEnglish (US)
JournalComputer Journal
Volume59
Issue number6
DOIs
StatePublished - Jun 1 2016

Fingerprint

Mobile phones
Data mining
Specifications

Keywords

  • Human mobility patterns
  • Location and time prediction
  • Mobile phone user
  • Sequence mining

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Predicting the location and time of mobile phone users by using sequential pattern mining techniques. / Ozer, Mert; Keles, Ilkcan; Toroslu, Hakki; Karagoz, Pinar; Davulcu, Hasan.

In: Computer Journal, Vol. 59, No. 6, 01.06.2016.

Research output: Contribution to journalArticle

Ozer, Mert ; Keles, Ilkcan ; Toroslu, Hakki ; Karagoz, Pinar ; Davulcu, Hasan. / Predicting the location and time of mobile phone users by using sequential pattern mining techniques. In: Computer Journal. 2016 ; Vol. 59, No. 6.
@article{3b1adde2e4204d058d7f4fc458ac6ef3,
title = "Predicting the location and time of mobile phone users by using sequential pattern mining techniques",
abstract = "In recent years, using cell phone log data tomodel humanmobility patterns became an active research area. This problem is a challenging data mining problem due to huge size and non-uniformity of the log data, which introduces several granularity levels for the specification of temporal and spatial dimensions. This paper focuses on the prediction of the location of the next activity of the mobile phone users. There are several versions of this problem. In this work, we have concentrated on the following three problems: predicting the location and the time of the next user activity, predicting the location of the next activity of the user when the location of the user changes, and predicting both the location and the time of the activity of the user when the user's location changes. We have developed sequential pattern mining-based techniques for these three problems and validated the success of these methods with real data obtained from one of the largest mobile phone operators in Turkey. Our results are very encouraging, since we were able to obtain quite high accuracy results under small prediction sets.",
keywords = "Human mobility patterns, Location and time prediction, Mobile phone user, Sequence mining",
author = "Mert Ozer and Ilkcan Keles and Hakki Toroslu and Pinar Karagoz and Hasan Davulcu",
year = "2016",
month = "6",
day = "1",
doi = "10.1093/comjnl/bxv075",
language = "English (US)",
volume = "59",
journal = "Computer Journal",
issn = "0010-4620",
publisher = "Oxford University Press",
number = "6",

}

TY - JOUR

T1 - Predicting the location and time of mobile phone users by using sequential pattern mining techniques

AU - Ozer, Mert

AU - Keles, Ilkcan

AU - Toroslu, Hakki

AU - Karagoz, Pinar

AU - Davulcu, Hasan

PY - 2016/6/1

Y1 - 2016/6/1

N2 - In recent years, using cell phone log data tomodel humanmobility patterns became an active research area. This problem is a challenging data mining problem due to huge size and non-uniformity of the log data, which introduces several granularity levels for the specification of temporal and spatial dimensions. This paper focuses on the prediction of the location of the next activity of the mobile phone users. There are several versions of this problem. In this work, we have concentrated on the following three problems: predicting the location and the time of the next user activity, predicting the location of the next activity of the user when the location of the user changes, and predicting both the location and the time of the activity of the user when the user's location changes. We have developed sequential pattern mining-based techniques for these three problems and validated the success of these methods with real data obtained from one of the largest mobile phone operators in Turkey. Our results are very encouraging, since we were able to obtain quite high accuracy results under small prediction sets.

AB - In recent years, using cell phone log data tomodel humanmobility patterns became an active research area. This problem is a challenging data mining problem due to huge size and non-uniformity of the log data, which introduces several granularity levels for the specification of temporal and spatial dimensions. This paper focuses on the prediction of the location of the next activity of the mobile phone users. There are several versions of this problem. In this work, we have concentrated on the following three problems: predicting the location and the time of the next user activity, predicting the location of the next activity of the user when the location of the user changes, and predicting both the location and the time of the activity of the user when the user's location changes. We have developed sequential pattern mining-based techniques for these three problems and validated the success of these methods with real data obtained from one of the largest mobile phone operators in Turkey. Our results are very encouraging, since we were able to obtain quite high accuracy results under small prediction sets.

KW - Human mobility patterns

KW - Location and time prediction

KW - Mobile phone user

KW - Sequence mining

UR - http://www.scopus.com/inward/record.url?scp=84983740865&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983740865&partnerID=8YFLogxK

U2 - 10.1093/comjnl/bxv075

DO - 10.1093/comjnl/bxv075

M3 - Article

VL - 59

JO - Computer Journal

JF - Computer Journal

SN - 0010-4620

IS - 6

ER -