WiFi Fingerprint based Indoor Localization with Iterative Weighted KNN for WiFi AP Missing

In this paper, a real WiFi fingerprint-based indoor localization system is considered, where three primary components including the APP in smart phone, the server system and the embedded localization algorithm, have been designed. This paper proposes a dedicated data preprocessing algorithm to solve the singular-collection problem. Furthermore, the issue of WiFi access point (AP) missing is discussed and the theoretical analysis is presented under the condition of a two-AP scenario. Finally, because of unequal amount of location information contained in received signal strength (RSS) from different AP, the weighted RSS (WRSS) and the iterative weighted K nearest neighbor (IWKNN) algorithm are proposed for localization. Experimental results shows the proposed scheme achieves a competitive localization accuracy.