Comparison of CART-based localization and SVMs-based localization in WSN

Author

Zhou, Wenyong ; Liu, Chunhua ; Liu, Hongbing

Author_Institution

Sch. of Comput. & Inf. Technol., Xinyang Normal Univ., Xinyang, China

fYear

2012

fDate

29-31 May 2012

Firstpage

340

Lastpage

343

Abstract

Localization of sensor nodes is essential for wireless sensor network when it is applied to the special applications. We formed two models to estimate the location of sensor nodes, CART-based localization and SVMs-based Localization. During the training process, the received signal strength of the reference nodes is selected as the input of two models and the location information is regarded as the output of two models. During the localization process, the decision trees of CART and support vector machines are used to estimate the location of blindfolded nodes. We demonstrate the practicality and feasibility of the two models through simulations in the 100m×100m area.

Keywords

decision trees; support vector machines; telecommunication computing; wireless sensor networks; CART based localization; SVM based localization; WSN; blindfolded node location; location information; sensor node localization; signal strength; support vector machines; wireless sensor network; Accuracy; Base stations; Data models; Kernel; Mathematical model; Training; Wireless sensor networks; localization; received signal strength; regression; support vector machines; wireless sensor network;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation (ICNC), 2012 Eighth International Conference on

Conference_Location

Chongqing

ISSN

2157-9555

Print_ISBN

978-1-4577-2130-4

Type

conf

DOI

10.1109/ICNC.2012.6234509

Filename

6234509