Research on Fingerprinting Indoor Positioning Algorithm via Whitening RSS and Fuzzy C-Means Clustering

Abstract

Due to pervasive penetration of the Wireless Local Area Networks (WLAN) and portable smartphones, the indoor positioning technology based on WLAN has developed rapidly. Especially the Wi-Fi fingerprint-based positioning has attracted continuous attention because of its low cost, high applicability and accuracy. The current fingerprintbased positioning algorithm still has a tremendous challenge both in accuracy and efficiency. To improve and optimize the issues, a novel indoor positioning algorithm based on Whitening RSS and Fuzzy C-Means (FCM) clustering approach is proposed in this paper. Firstly, in offline phase, the preprocessing of gathered RSS data samples is conducted by whitening methods, removing the correlation of the signals, to build the fingerprint database. Then the computation complexity is reduced by dividing the whole database into various sub-databases through FCM clustering algorithm. Meanwhile, the membership degrees obtained from FCM are added to the position calculation as a weight parameter to improve accuracy. Simulation results indicate that the proposed algorithm extraordinary achieves high performance in reducing the computation complexity and enhancing the positioning accuracy.