Noise reduction for radio map crowdsourcing building in WLAN indoor localization system

Abstract Recent years have witnessed a growing interest in using WLAN fingerprint-based method for indoor localization system because of its cost-effectiveness and availability compared to other systems. In order rapidly deploy system, the crowdsourcing is applied alternate traditional deployment method. this paper, we proposed fast radio map building utilizing sensors inside mobile device Multidimensional Scaling (MDS) The collects RSS sensor data while user walking along straight line computes position information data. reduce noise location space map, short-term Fourier transform (STFT) used detect usage mode switching improve step determination accuracy. When much fewer values are needed conventional methods, which lends greater influence noises erroneous measurements values. Accordingly, an imprecise built based on these acquire smoother accuracy, MDS infer optimal value at each by exploiting correlation nearby locations. Experimental results show that expected goal achieved