An Improved XGBoost Indoor Localization Algorithm

Abstract

This paper proposes an improved XGBoost Wi-Fi indoor positioning algorithm aiming at the accuracy problem caused by the change of environment.The method first uses Extreme Gradient Boosting (XGBoost) algorithm to establish indoor positioning model, which can achieve indoor positioning. When the environment changes, further combine error compensation (EC) method to improve the initial positioning. In addition, the positioning trajectory is compared with the actual trajectory and the unimproved positioning trajectory to verify the stability of the algorithm. The experimental results show that the 80-th percentile of the achieved accuracy is 1.11m after the change of environment, which is significantly better than the unimproved positioning algorithms based on support vector machine, random forest and extreme gradient promotion, and the obtained positioning trajectory tends to converge with the actual trajectory.