A location predictor based on dependencies between multiple lifelog data

Masaaki Nishino, Yukihiro Nakamura, Takashi Yagi, Shinyo Muto, Masanobu Abe

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

8 Citations (Scopus)

Abstract

In this paper, we propose a method for predicting future locations of a person by exploiting the person's past lifelog data. To predict the future location of a person has many applications such as the delivery of information related to the predicted locations: information with limited lifetimes (sales in a supermarket), weather reports, and traffic reports. Most existing methods for prediction only use historical location data, thus they can only handle regular movements; irregular movements are not considered. Our method predicts future locations by using personal calendar entries in addition to GPS(Global positioning system) data. Using calendar entries makes it possible to predict the locations associated with the irregular events indicated by the entries. We make Dynamic Bayesian Networks models for integrating these different kinds of lifelog data so as to yield better predictions. In experiments on real data, our methods can predict irregular movements successfully even with long lead-times, while matching the accuracy of existing schemes in predicting usual movements.

Original languageEnglish
Title of host publicationProceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010
Pages11-18
Number of pages8
DOIs
Publication statusPublished - 2010
Event2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010 - San Jose, CA, United States
Duration: Nov 2 2010Nov 2 2010

Other

Other2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010
CountryUnited States
CitySan Jose, CA
Period11/2/1011/2/10

Fingerprint

human being
Bayesian networks
sales
Global positioning system
Sales
Lead
traffic
event
experiment
Experiments
time

Keywords

  • Calendar
  • Data mining
  • GPS

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Communication

Cite this

Nishino, M., Nakamura, Y., Yagi, T., Muto, S., & Abe, M. (2010). A location predictor based on dependencies between multiple lifelog data. In Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010 (pp. 11-18) https://doi.org/10.1145/1867699.1867702

A location predictor based on dependencies between multiple lifelog data. / Nishino, Masaaki; Nakamura, Yukihiro; Yagi, Takashi; Muto, Shinyo; Abe, Masanobu.

Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010. 2010. p. 11-18.

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

Nishino, M, Nakamura, Y, Yagi, T, Muto, S & Abe, M 2010, A location predictor based on dependencies between multiple lifelog data. in Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010. pp. 11-18, 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010, San Jose, CA, United States, 11/2/10. https://doi.org/10.1145/1867699.1867702
Nishino M, Nakamura Y, Yagi T, Muto S, Abe M. A location predictor based on dependencies between multiple lifelog data. In Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010. 2010. p. 11-18 https://doi.org/10.1145/1867699.1867702
Nishino, Masaaki ; Nakamura, Yukihiro ; Yagi, Takashi ; Muto, Shinyo ; Abe, Masanobu. / A location predictor based on dependencies between multiple lifelog data. Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010. 2010. pp. 11-18
@inproceedings{aeb7b108100141249e83dad2aeb722f4,
title = "A location predictor based on dependencies between multiple lifelog data",
abstract = "In this paper, we propose a method for predicting future locations of a person by exploiting the person's past lifelog data. To predict the future location of a person has many applications such as the delivery of information related to the predicted locations: information with limited lifetimes (sales in a supermarket), weather reports, and traffic reports. Most existing methods for prediction only use historical location data, thus they can only handle regular movements; irregular movements are not considered. Our method predicts future locations by using personal calendar entries in addition to GPS(Global positioning system) data. Using calendar entries makes it possible to predict the locations associated with the irregular events indicated by the entries. We make Dynamic Bayesian Networks models for integrating these different kinds of lifelog data so as to yield better predictions. In experiments on real data, our methods can predict irregular movements successfully even with long lead-times, while matching the accuracy of existing schemes in predicting usual movements.",
keywords = "Calendar, Data mining, GPS",
author = "Masaaki Nishino and Yukihiro Nakamura and Takashi Yagi and Shinyo Muto and Masanobu Abe",
year = "2010",
doi = "10.1145/1867699.1867702",
language = "English",
isbn = "9781450304344",
pages = "11--18",
booktitle = "Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010",

}

TY - GEN

T1 - A location predictor based on dependencies between multiple lifelog data

AU - Nishino, Masaaki

AU - Nakamura, Yukihiro

AU - Yagi, Takashi

AU - Muto, Shinyo

AU - Abe, Masanobu

PY - 2010

Y1 - 2010

N2 - In this paper, we propose a method for predicting future locations of a person by exploiting the person's past lifelog data. To predict the future location of a person has many applications such as the delivery of information related to the predicted locations: information with limited lifetimes (sales in a supermarket), weather reports, and traffic reports. Most existing methods for prediction only use historical location data, thus they can only handle regular movements; irregular movements are not considered. Our method predicts future locations by using personal calendar entries in addition to GPS(Global positioning system) data. Using calendar entries makes it possible to predict the locations associated with the irregular events indicated by the entries. We make Dynamic Bayesian Networks models for integrating these different kinds of lifelog data so as to yield better predictions. In experiments on real data, our methods can predict irregular movements successfully even with long lead-times, while matching the accuracy of existing schemes in predicting usual movements.

AB - In this paper, we propose a method for predicting future locations of a person by exploiting the person's past lifelog data. To predict the future location of a person has many applications such as the delivery of information related to the predicted locations: information with limited lifetimes (sales in a supermarket), weather reports, and traffic reports. Most existing methods for prediction only use historical location data, thus they can only handle regular movements; irregular movements are not considered. Our method predicts future locations by using personal calendar entries in addition to GPS(Global positioning system) data. Using calendar entries makes it possible to predict the locations associated with the irregular events indicated by the entries. We make Dynamic Bayesian Networks models for integrating these different kinds of lifelog data so as to yield better predictions. In experiments on real data, our methods can predict irregular movements successfully even with long lead-times, while matching the accuracy of existing schemes in predicting usual movements.

KW - Calendar

KW - Data mining

KW - GPS

UR - http://www.scopus.com/inward/record.url?scp=78650871105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650871105&partnerID=8YFLogxK

U2 - 10.1145/1867699.1867702

DO - 10.1145/1867699.1867702

M3 - Conference contribution

SN - 9781450304344

SP - 11

EP - 18

BT - Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, LBSN 2010 - Held in Conjunction with ACM SIGSPATIAL GIS 2010

ER -