Mobility prediction-based smartphone energy optimization for everyday location monitoring

Yohan Chon, Elmurod Talipov, Hyojeong Shin, Hojung Cha

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

101 Citations (Scopus)

Abstract

Monitoring a user's mobility during daily life is an essential requirement in providing advanced mobile services. While extensive attempts have been made to monitor user mobility, previous work has rarely addressed issues with battery lifetime in real deployment. In this paper, we introduce SmartDC, a mobility prediction-based adaptive duty cycling scheme to provide contextual information about a user's mobility: time-resolved places and paths. Unlike previous approaches that focused on minimizing energy consumption for tracking raw coordinates, we propose efficient techniques to maximize the accuracy of monitoring meaningful places with a given energy constraint. SmartDC comprises unsupervised mobility learner, mobility predictor, and Markov decision process-based adaptive duty cycling. SmartDC estimates the regularity of individual mobility and predicts residence time at places to determine efficient sensing schedules. Our experiment results show that SmartDC consumes 81% less energy than the periodic sensing schemes, and 87% less energy than a scheme employing context-aware sensing, yet it still correctly monitors 80% of a user's location changes within a 160-second delay.

Original languageEnglish
Title of host publicationSenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems
Pages82-95
Number of pages14
DOIs
Publication statusPublished - 2011 Dec 19
Event9th ACM Conference on Embedded Networked Sensor Systems, SenSys 2011 - Seattle, WA, United States
Duration: 2011 Nov 12011 Nov 4

Other

Other9th ACM Conference on Embedded Networked Sensor Systems, SenSys 2011
CountryUnited States
CitySeattle, WA
Period11/11/111/11/4

Fingerprint

Smartphones
Monitoring
Energy utilization
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Chon, Y., Talipov, E., Shin, H., & Cha, H. (2011). Mobility prediction-based smartphone energy optimization for everyday location monitoring. In SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems (pp. 82-95) https://doi.org/10.1145/2070942.2070952
Chon, Yohan ; Talipov, Elmurod ; Shin, Hyojeong ; Cha, Hojung. / Mobility prediction-based smartphone energy optimization for everyday location monitoring. SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. 2011. pp. 82-95
@inproceedings{575a52135a114b84afdf7f6109d678fc,
title = "Mobility prediction-based smartphone energy optimization for everyday location monitoring",
abstract = "Monitoring a user's mobility during daily life is an essential requirement in providing advanced mobile services. While extensive attempts have been made to monitor user mobility, previous work has rarely addressed issues with battery lifetime in real deployment. In this paper, we introduce SmartDC, a mobility prediction-based adaptive duty cycling scheme to provide contextual information about a user's mobility: time-resolved places and paths. Unlike previous approaches that focused on minimizing energy consumption for tracking raw coordinates, we propose efficient techniques to maximize the accuracy of monitoring meaningful places with a given energy constraint. SmartDC comprises unsupervised mobility learner, mobility predictor, and Markov decision process-based adaptive duty cycling. SmartDC estimates the regularity of individual mobility and predicts residence time at places to determine efficient sensing schedules. Our experiment results show that SmartDC consumes 81{\%} less energy than the periodic sensing schemes, and 87{\%} less energy than a scheme employing context-aware sensing, yet it still correctly monitors 80{\%} of a user's location changes within a 160-second delay.",
author = "Yohan Chon and Elmurod Talipov and Hyojeong Shin and Hojung Cha",
year = "2011",
month = "12",
day = "19",
doi = "10.1145/2070942.2070952",
language = "English",
isbn = "9781450307185",
pages = "82--95",
booktitle = "SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems",

}

Chon, Y, Talipov, E, Shin, H & Cha, H 2011, Mobility prediction-based smartphone energy optimization for everyday location monitoring. in SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. pp. 82-95, 9th ACM Conference on Embedded Networked Sensor Systems, SenSys 2011, Seattle, WA, United States, 11/11/1. https://doi.org/10.1145/2070942.2070952

Mobility prediction-based smartphone energy optimization for everyday location monitoring. / Chon, Yohan; Talipov, Elmurod; Shin, Hyojeong; Cha, Hojung.

SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. 2011. p. 82-95.

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

TY - GEN

T1 - Mobility prediction-based smartphone energy optimization for everyday location monitoring

AU - Chon, Yohan

AU - Talipov, Elmurod

AU - Shin, Hyojeong

AU - Cha, Hojung

PY - 2011/12/19

Y1 - 2011/12/19

N2 - Monitoring a user's mobility during daily life is an essential requirement in providing advanced mobile services. While extensive attempts have been made to monitor user mobility, previous work has rarely addressed issues with battery lifetime in real deployment. In this paper, we introduce SmartDC, a mobility prediction-based adaptive duty cycling scheme to provide contextual information about a user's mobility: time-resolved places and paths. Unlike previous approaches that focused on minimizing energy consumption for tracking raw coordinates, we propose efficient techniques to maximize the accuracy of monitoring meaningful places with a given energy constraint. SmartDC comprises unsupervised mobility learner, mobility predictor, and Markov decision process-based adaptive duty cycling. SmartDC estimates the regularity of individual mobility and predicts residence time at places to determine efficient sensing schedules. Our experiment results show that SmartDC consumes 81% less energy than the periodic sensing schemes, and 87% less energy than a scheme employing context-aware sensing, yet it still correctly monitors 80% of a user's location changes within a 160-second delay.

AB - Monitoring a user's mobility during daily life is an essential requirement in providing advanced mobile services. While extensive attempts have been made to monitor user mobility, previous work has rarely addressed issues with battery lifetime in real deployment. In this paper, we introduce SmartDC, a mobility prediction-based adaptive duty cycling scheme to provide contextual information about a user's mobility: time-resolved places and paths. Unlike previous approaches that focused on minimizing energy consumption for tracking raw coordinates, we propose efficient techniques to maximize the accuracy of monitoring meaningful places with a given energy constraint. SmartDC comprises unsupervised mobility learner, mobility predictor, and Markov decision process-based adaptive duty cycling. SmartDC estimates the regularity of individual mobility and predicts residence time at places to determine efficient sensing schedules. Our experiment results show that SmartDC consumes 81% less energy than the periodic sensing schemes, and 87% less energy than a scheme employing context-aware sensing, yet it still correctly monitors 80% of a user's location changes within a 160-second delay.

UR - http://www.scopus.com/inward/record.url?scp=83455176272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83455176272&partnerID=8YFLogxK

U2 - 10.1145/2070942.2070952

DO - 10.1145/2070942.2070952

M3 - Conference contribution

SN - 9781450307185

SP - 82

EP - 95

BT - SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems

ER -

Chon Y, Talipov E, Shin H, Cha H. Mobility prediction-based smartphone energy optimization for everyday location monitoring. In SenSys 2011 - Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. 2011. p. 82-95 https://doi.org/10.1145/2070942.2070952