PCA clustering algorithm for indoor positioning in WLAN

In WLAN indoor location system,aiming at the problem of time-varying characteristic of received signal strength (RSS) which reduces indoor positioning accuracy,a clustering algorithm based on principal component analysis (PCA) albino RSS was put forward.The algorithm firstly treated the RSS with PCA whitening treatment to remove the correlation and improve reliability and rationality of the cluster centers.Then,K-means clustering method was used to cluster the RSS and the clustering accuracy was improved effectively,so as to improve positioning accuracy.Experimental results show that compared with the traditional clustering algorithm without PCA,probability of positioning error within 2 meters has improved 44.8% in positioning accuracy,and the performance of positioning system has been more excellent.