Localization Algorithm Based on SVM-Data Fusion in Wireless Sensor Networks

Author

Wang, Wei ; Huang, Tinglei ; Liu, Hui ; Pang, Fei

Author_Institution

Sch. of Electron. Eng., Guilin Univ. of Electron. Technol., Guilin, China

fYear

2009

fDate

14-17 Oct. 2009

Firstpage

447

Lastpage

450

Abstract

This positioning process of the wireless sensor network (WSN) nodes is interfered by multipath, multiple access, especially NLOS transmission effect, Basing on TOA/TDOA positioning technology, the article brings forward TOA/TDOA measurement data model, and improves on a location algorithm which bases on least square support vector machine (LS-SVM). On one network with uniformly distributed nodes, node localization experiments show that SVM data fusion location algorithm can effectively reduce the effect of distance estimation error on positioning accuracy, minish coverage loop holes and network cost.

Keywords

direction-of-arrival estimation; least mean squares methods; sensor fusion; support vector machines; telecommunication computing; time-of-arrival estimation; wireless sensor networks; NLOS transmission effect; SVM-data fusion; TOA-TDOA positioning technology; distance estimation error; least square support vector machine; measurement data model; minish coverage loop holes; network cost; node localization algorithm; time-of-arrival estimation; uniformly distributed nodes; wireless sensor network node; Base stations; Computer networks; Coordinate measuring machines; Distributed computing; Electronics packaging; Packaging machines; Position measurement; Sensor fusion; Support vector machines; Wireless sensor networks; Data fusion; Node localization; Support vector machine (SVM); Wireless Sensor Network (WSN);

fLanguage

English

Publisher

ieee

Conference_Titel

Genetic and Evolutionary Computing, 2009. WGEC '09. 3rd International Conference on

Conference_Location

Guilin

Print_ISBN

978-0-7695-3899-0

Type

conf

DOI

10.1109/WGEC.2009.16

Filename

5402798