Experimental Analysis on Weight ${K}$ -Nearest Neighbor Indoor Fingerprint Positioning

Wi-Fi deployed inside a building can be used for positioning indoor users. A commonly used technology is weighted <inline-formula> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula>-nearest neighbor (WKNN) fingerprint which positions a user based on <inline-formula> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> nearest reference points measured beforehand. The challenge lies in how to configure the value of <inline-formula> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> to obtain the best positioning accuracy. In this paper, we propose a self-adaptive WKNN (SAWKNN) algorithm with a dynamic <inline-formula> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula>. By adjusting the value of <inline-formula> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> based on the signal strength, SAWKNN can obtain a better positioning accuracy than traditional WKNN. In particular, a significant percentage of the SAWKNN positioning makes use of a value <inline-formula> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> = 1. The performance of the proposed algorithm has been evaluated in real-world experiments.