WiFi Location Fingerprint Indoor Positioning Method Based on WKNN

Abstract

Wireless Fidelity (WiFi) based fingerprint indoor positioning can directly utilize existing commercial WiFi devices, the deployment cost is low, easy to expand, and has good non-invasiveness, which has gradually become a hot spot of indoor positioning technology researchers. The positioning method of this paper combines the Received Signal Strength (RSS) ranging method and the location fingerprint method. On this basis, the Weighted K-Nearest Neighbor (WKNN) matching algorithm is used to match the fingerprint data in the location fingerprint database. In view of the strong problem of indoor wireless signal oscillation, this paper uses Kalman filtering method to process the signal strength value. The simulation is carried out under the MATLAB platform. The results show that the proposed method is superior to the existing K-Nearest Neighbors (KNN) and Nearest Neighbors (NN) algorithms in the same simulation environment, which significantly improves the indoor positioning accuracy.