File Download
  Links for fulltext
     (May Require Subscription)
  • Find via Find It@HKUL
Supplementary

Article: Using Micro-Genetic Algorithms to Improve Localization in Wireless Sensor Networks

TitleUsing Micro-Genetic Algorithms to Improve Localization in Wireless Sensor Networks
Authors
Issue Date2006
PublisherThe Academy Publisher.
Citation
Journal of Communications, 2006, v. 1 n. 4, p. 1 - 10 How to Cite?
AbstractWireless sensor networks are widely adopted inmany location-sensitive applications including disastermanagement, environmental monitoring, militaryapplications where the precise estimation of each nodeposition is inevitably important when the absolute positionsof a relatively small portion as anchor nodes of theunderlying network were predetermined. Intrinsically,localization is an unconstrained optimization problem basedon various distance/path measures. Most of the existinglocalization methods focus on using different heuristic-basedor mathematical techniques to increase the precision inposition estimation. However, there were recent studiesshowing that nature-inspired algorithms like the ant-basedor genetic algorithms can effectively solve many complexoptimization problems. In this paper, we propose to adaptan evolutionary approach, namely a micro-geneticalgorithm, as a post-optimizer into some existing localizationmethods such as the Ad-hoc Positioning System (APS) tofurther improve the accuracy of their position estimation.Obviously, our proposed MGA is highly adaptable andeasily integrated into other localization methods.Furthermore, the remarkable improvements attained byour proposed MGA on both isotropic and anisotropictopologies of our simulation tests prompt for severalinteresting directions for further investigation.
Persistent Identifierhttp://hdl.handle.net/10722/73832
ISSN
2015 SCImago Journal Rankings: 0.170

 

DC FieldValueLanguage
dc.contributor.authorTam, VWLen_HK
dc.contributor.authorCheng, KYen_HK
dc.contributor.authorWong Lui, KSen_HK
dc.date.accessioned2010-09-06T06:55:11Z-
dc.date.available2010-09-06T06:55:11Z-
dc.date.issued2006en_HK
dc.identifier.citationJournal of Communications, 2006, v. 1 n. 4, p. 1 - 10en_HK
dc.identifier.issn1796-2021-
dc.identifier.urihttp://hdl.handle.net/10722/73832-
dc.description.abstractWireless sensor networks are widely adopted inmany location-sensitive applications including disastermanagement, environmental monitoring, militaryapplications where the precise estimation of each nodeposition is inevitably important when the absolute positionsof a relatively small portion as anchor nodes of theunderlying network were predetermined. Intrinsically,localization is an unconstrained optimization problem basedon various distance/path measures. Most of the existinglocalization methods focus on using different heuristic-basedor mathematical techniques to increase the precision inposition estimation. However, there were recent studiesshowing that nature-inspired algorithms like the ant-basedor genetic algorithms can effectively solve many complexoptimization problems. In this paper, we propose to adaptan evolutionary approach, namely a micro-geneticalgorithm, as a post-optimizer into some existing localizationmethods such as the Ad-hoc Positioning System (APS) tofurther improve the accuracy of their position estimation.Obviously, our proposed MGA is highly adaptable andeasily integrated into other localization methods.Furthermore, the remarkable improvements attained byour proposed MGA on both isotropic and anisotropictopologies of our simulation tests prompt for severalinteresting directions for further investigation.-
dc.languageengen_HK
dc.publisherThe Academy Publisher.en_HK
dc.relation.ispartofJournal of Communicationsen_HK
dc.titleUsing Micro-Genetic Algorithms to Improve Localization in Wireless Sensor Networksen_HK
dc.typeArticleen_HK
dc.identifier.emailTam, VWL: vtam@eee.hku.hken_HK
dc.identifier.emailWong Lui, KS: kslui@eee.hku.hken_HK
dc.identifier.authorityTam, VWL=rp00173en_HK
dc.identifier.authorityWong Lui, KS=rp00188en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.hkuros117251en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats