A modified WKNN indoor Wi-Fi localization method with differential coordinates

The k-nearest neighbor (KNN) based indoor localization methods are practical to the wireless sensor network constructed by internet of things. The weighted KNN (WKNN) method is designed as the enhanced KNN but actually does not outperform KNN. Inspired by the technique of differential coordinates from satellite-based localization, in this paper we propose the differential coordinate based WKNN (DC-WKNN) using Wi-Fi technology to further improve the accuracy for WKNN by canceling the localization error calculated between the position of the first and the second WKNN estimated coordinates. Simulation results show that the proposed DC-WKNN provides higher accuracy than both WKNN and KNN for the dense reference point localization area.