Localization with beacon based support vector machine in Wireless Sensor Networks

Recent developments in radio technology and processing systems, Wireless Sensor Networks (WSNs) are tremendously being used to perform an assortment of tasks from their atmosphere. Localization plays the most important task in WSNs. Accuracy is the one of the major problems facing localization. In this paper, we propose an improved localization algorithm based on the learning concept of support vector machine (SVM). In SVM classification the finite size of grid cells offer the localization accuracy. The localization error using the proposed algorithm is calculated and compared with basic SVM and fuzzy logic. Simulation result demonstrates that the improved support vector machine can effectively reduce the localization error and thus achieve the objective of better accuracy.

I. Introduction II

Wireless Sensor Networks (WSNs) are composed of a large number of sensor nodes that consists of four components: sensing element, processing element, transmission element and power element. The potential applications of Wireless Sensor Networks are environmental monitoring, target tracking, surveillance, military, security, etc. In Wireless Sensor Networks, the fundamental problem is localization i.e, determining the location of nodes. Global Positioning System (GPS) is the most obvious solution of this problem. But the huge, expensive cost and power consumption of GPS, different algorithms are developed for the localization. While designing the localization algorithms the key aspects or issues such as: limited resource, the number and density of node network topology, device capability, localization accuracy, kind of signals and mobility of node (static node or mobile node) must be considered [1].