Mining region-based movement patterns for energy-efficient object tracking in sensor networks

S. Tseng, Ming Hua Hsieh, Kawuu W. Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

In recent years, a number of studies have been done on object tracking sensor networks (OTSNs) due to the wide applications. One important issue in OTSNs is the energy saving strategy for object tracking and most existing solutions are based on statistical methods. In this paper, we propose a data mining-based approach for energy-efficient object tracking in OTSNs. First, a data mining methodology named RM-Mine is proposed for discovering the region-based movement patterns of moving objects in an OTSN. Moreover, we also propose the corresponding prediction strategies for tracking objects in energy-efficient way. Through empirical evaluations on various simulation conditions, RM-Mine and the proposed prediction strategies are shown to deliver excellent performance in terms of scalability, accuracy and energy efficiency.

Original languageEnglish
Title of host publicationProceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008
Pages188-196
Number of pages9
DOIs
StatePublished - 1 Dec 2008
Event8th International Conference on Intelligent Systems Design and Applications, ISDA 2008 - Kaohsiung, Taiwan
Duration: 26 Nov 200828 Nov 2008

Publication series

NameProceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008
Volume3

Conference

Conference8th International Conference on Intelligent Systems Design and Applications, ISDA 2008
CountryTaiwan
CityKaohsiung
Period26/11/0828/11/08

Keywords

  • Data mining
  • Location prediction
  • Object tracking
  • Region movement patterns
  • Sensor Networks

Fingerprint Dive into the research topics of 'Mining region-based movement patterns for energy-efficient object tracking in sensor networks'. Together they form a unique fingerprint.

Cite this