Improvements in Support Vector Machine based localization in Wireless Sensor Networks

Sensor networks are playing an important role in making the dream of ubiquitous computing come into reality. With a variety of applications, sensor networks have the potential to influence everyone´s life in the near future. However, in order for sensor network applications to realize this potential, there are a number of issues in deployment and exploitation of these networks that must be dealt with. Localization of the sensor nodes, which is the subject of this paper, is one of the basic problems that must be solved in order for sensor networks to be effectively used. This paper proposes to use a method based on Support Vector Machines (SVM) and probability to gain a fairly accurate localization of sensor nodes, while no extra equipment is assumed on the sensor nodes, as opposed to many of the existing methods. We demonstrate that Probabilistic SVM method (or PSVM) provides a significant improvement over existing localization methods, particularly in sparse networks and rough environments. In addition, we are proposing a post processing step for PSVM called ARPoFiL, which provides even more improvement to the accuracy of the location of sensor nodes.