A Fingerprint Database Reconstruction Method Based on Ordinary Kriging Algorithm for Indoor Localization

Constructing a fingerprint database using the received signal strength is a widely used solution for indoor positioning to fit the positioning result online through matching the database with algorithm. Traditional fingerprint database construction methods are time-consuming and difficult to sample in special locations. In this paper, Kriging interpolation algorithm is proposed to interpolate or extrapolate fingerprint databases, in order to solve such problems, such as large workload, long time-consuming and difficult of sampling special features in the construction of fingerprint databases. The experiment is done using the Kriging algorithm and Inverse Distance Weighted algorithm to interpolate the database with 60% sampling points as known parameter. The experimental results show that the interpolation error of the Kriging algorithm is 4.49dBm, which is 5% lower than that by the Inverse Distance Weighted algorithm.