Analysis of Location Estimation Algorithms for Wifi Fingerprint-based Indoor Localization

In Wifi fingerprint-based indoor localization, a well-known method of estimating user’s location is to find the nearest reference point using Euclidean distance in signal space. However, this paper shows that Euclidean distance is prone to error, and propose a new algorithm for selecting the nearest neighbor which penalizes signals from unstable access points and compensates for RSSI shifts due to various reasons. Experiments with real measurements show that the new algorithm reduces mean error distance compared to the Euclidean distance method.