Space grid resolution impact on accuracy of the indoor localization fingerprinting

Indoor wireless localization has significant importance in wireless network technology and has wide deployment in a real-time indoor people and objects tracking. Location fingerprinting, which is based on received signal strength measurements, is a frequently used approach for indoor applications. In this paper, we examine the localization fingerprinting method through the enhanced well-known Weighted k-Nearest Neighbour (WkNN) method with MultiDimensional Scaling (MDS) through the post-processing step of transformation of signal-space and physical-space. The aim of this transformation step is to de-correlate and refine initially obtained location estimates. Impact of the variation of space-grid resolution on accuracy of the presented localization techniques is examined. Performances of the initial estimates obtained by the basic and enhanced WkNN localization methods are verified through the experiments with real environment data.