Localization of wireless sensor networks with a mobile beacon

Abstract

A vast majority of localization techniques proposed for sensor networks are based on triangulation methods in Euclidean geometry. This study proposes a novel approach known as MSVM that utilizes a mobile beacon to implement location estimation on wireless sensor networks. MSVM is based on Support Vector Machine(SVM). In the approach, the problem of localization is converted into classification, which takes advantage of the signal information generated by mobile beacon between virtual beacon nodes and unknown nodes to compute the location. In this way, expensive beacon nodes with GPS function can be avoided, saving investment on wireless sensor nodes. Shown by the simulation test, the approach has quite high localization precision. © 2013 Asian Network for Scientific Information.