SVM-based indoor localization in Wireless Sensor Networks
Abstract
The need to locate objects and to be situated in the space, whether inside or outside, has long been the focus of a substantial amount of research. Especially in Wireless Sensor Networks, indoor localization has become an important issue in many fields of applications. In this paper, we propose an indoor location solution based on Support Vector Machine (SVM). SVM is a class of learning algorithms defined to resolve discrimination and regression problems. In fact, with many works, it turned out that it is very difficult to properly locate a target with only the RSSI measurements. Thus, the idea is to use multi-class SVM with RSSI measurements to propose a zoning localization approach. The performed experiments using different datasets, collected from two real world environments in both a hospital and a laboratory building, and the comparison with Artificial Neural Networks (ANN) confirm the effectiveness of our SVM-based localization proposal. Experimental results show that the system achieves a correct classification rate of around 90% with misclassification is in rooms where there is no wall separating them.