A Fingerprint Localization Method Based on Weighted KNN Algorithm

Wireless Sensor Network (WSN) is an emerging next-generation sensor network that has a wide range of application prospects. The localization technology is one of the most important key technologies for WSN. However, in a complex indoor environment, fluctuations in received signal strength can seriously degrade positioning accuracy. In this paper, we propose a fingerprint localization method based on received signal strength (RSS) distance and improved weighted k-Nearest Neighbor (KNN) algorithm. The fingerprint database is established in the off-line phase. The real-time RSS values of the on-line measurement points are measured, and the two-stage RSS distance is calculated using the Euclidean distance. Finally, in order to solve the problem of non-Gaussian distribution of measurement noise, we use an improved weighted KNN algorithm to calculate the final position coordinates of the measurement point. Simulation results show that this method can reduce the influence of signal strength fluctuations and improve the positioning accuracy.