Enhanced fingerprinting in WLAN-based indoor positioning using hybrid search techniques

Abstract

Selective matching between the received signal strength (RSS) measured by the target and the pre-stored fingerprints can improve fingerprinting algorithms by reducing their computational requirements. This is achieved by minimizing the number of search points needed to find the best match between the target RSS and the pre-stored fingerprints. Therefore, in this paper we propose a hybrid solution of clustering and fast search techniques to reduce the computational requirements of fingerprinting. The performance of the proposed method is quantified by evaluating the positioning accuracy, precision and the required number of search points. Our results show that the proposed hybrid technique can drastically reduce the number of search points, at a tolerable reduction of accuracy and precision.