Support Vector Machines for indoor sensor localization

Author

Farjow, Wissam ; Chehri, Abdellah ; Hussein, Mouftah ; Fernando, Xavier

Author_Institution

Dept. or Electr. & Comput. Eng., Ryerson Univ., Toronto, ON, Canada

fYear

2011

fDate

28-31 March 2011

Firstpage

779

Lastpage

783

Abstract

Fingerprinting is chosen as the localization approach as fingerprinting has a higher accuracy than other approaches such as time-of-arrival or angel-of arrival. This paper introduces a positioning system based on IEEE802.15.4/ZigBee-based sensor networks. The system uses fingerprinting and employs Support Vector Machines (SVMs) to estimate node position. The system is cost-effective since it works with real deployed IEEE 802.15.4/ZigBee sensors nodes. The whole system requires minimal setup time, which makes it readily available for real-world applications.

Keywords

Zigbee; support vector machines; telecommunication computing; wireless sensor networks; IEEE802.15.4; ZigBee-based sensor network; fingerprinting; indoor sensor localization; node position estimation; positioning system; support vector machines; Accuracy; Fingerprint recognition; IEEE 802.11 Standards; Measurement uncertainty; Mobile communication; Support vector machines; Zigbee; Localization; Support Vector Machines; ZigBee;

fLanguage

English

Publisher

ieee

Conference_Titel

Wireless Communications and Networking Conference (WCNC), 2011 IEEE

Conference_Location

Cancun, Quintana Roo

ISSN

1525-3511

Print_ISBN

978-1-61284-255-4

Type

conf

DOI

10.1109/WCNC.2011.5779231

Filename

5779231