A Joint-Norm Robust Principal Component Analysis Model for Fingerprint Indoor Localization

Abstract

Indoor localization services are emerging as an important application of Internet of Things, which drives the development of related technologies in indoor scenarios. In recent years, various localization algorithms for different indoor scenarios have been proposed. The indoor localization algorithm based on fingerprints has attracted much attention due to its good performance without extra hardware devices. However, due to complex indoor scenarios, fingerprint mismatching often occurs, which degrades the localization accuracy. In this article, a joint-norm robust principal component analysis (JR-PCA in brief) assisted indoor localization algorithm has been proposed which applies weighted kernel norm & L <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2,1</inf> -norm , which can improve the localization accuracy through aggregating the reference points (RPs) and conducting robust feature extraction based on clustering. More specifically, one-way hierarchical clustering termination method is proposed to obtain reasonable RP clusters adaptively according to the preset RPs. A two-phase fingerprint matching algorithm of JRPCA based on clustering is proposed to further increase the difference between similar RPs and thus improve the localization accuracy. To validate the proposed algorithm, extensive experiments are conducted in real indoor scenarios. The experimental results show that the proposed cluster-based JRPCA algorithm outperforms other existing algorithms in terms of robustness and accuracy.