Faulty measurements impact on wireless local area network positioning performance

Abstract

Indoor positioning methods based on wireless local area network (WLAN) signal measurements have gained popularity because of high localisation accuracy. These methods use radio-maps obtained from wireless signal measurement surveys on location grids. Measurement sets from various WLAN access points are called fingerprints and they can be used to identify locations where the measurements are collected. WLAN positioning methods face unexpected changes in signal patterns because of attenuation changes or transient faults in WLAN cards or access points that often make signal strength readings unavailable. This study studies the effect of faulty measurements on the performance of popular state-of-the-art WLAN indoor positioning methods. Additionally, an integrity monitoring preprocessing algorithm is provided that demonstrates a possibility of faulty measurements mitigation for conventional methods such as K-nearest-neighbour. This is achieved by detecting and excluding faulty measurements prior to classification. Performance figures are provided for both simulated and empirical environments.