Aiming at the problem of low speed and positioning fluctuations of indoor WiFi fingerprints. Firstly, we use the method of Gauss fitting and averaging to acquire the average value of the received signal. Secondly, we use a distance to be similarity measure to define a threshold to classify the fingerprint database. Finally, By improving the K nearest neighbor algorithm and on the basis of classification, Implement fast matching of K nearest neighbor. The experimental results show that the time efficiency of the classified location system has been greatly improved, with an average decrease of 62.8%; In the positioning accuracy, WiFi fingerprint positioning of the average error from 4.17 m down to 2.12 m.
Gaussian fitting Multiple measurements for averaging Database classification Fast matching of K nearest neighbor
This is a preview of subscription content, log in to check access.
Z. Yang, Z. Zhou, Y. Liu, From RSSI to CSI: indoor localization via channel response. ACM Comput. Surv. 7(3), 165–181 (2013)zbMATHGoogle Scholar
C. Laoudias, Device self-calibration in location systems using signal strength histograms. J. Locat. Based Serv. 7(3), 165–181 (2013)CrossRefGoogle Scholar
S.H. Fang, T.N. Lin, K.C. Lee, A novel algorithm for multipath fingerprinting in indoor WLAN environments. IEEE Trans. Wirel. Commun. 7(9), 3579–3588 (2008)CrossRefGoogle Scholar
P.A. Zandbergen, Accuracy of iPhone locations: a comparison of assisted GPS, WiFi and cellular positioning. Trans. GIS 13(s1), 5–25 (2009)CrossRefGoogle Scholar
K. Pahlavan, X. Li, J.P. Makela, Indoor geolocation science and technology. IEEE Commun. Mag. (IEEE Press) 40(2), 112–118 (2002)CrossRefGoogle Scholar
A. Kushki, K.N. Plataniotis, A.N. Venetsanopoulos, Kernel-based positioning in wireless local area networks. IEEE Trans. Mobile Comput. 6(6), 689–705 (2007)CrossRefGoogle Scholar