关键词: 室内定位, 粒子滤波, 麻雀算法, XGBoost

Abstract: In indoor environments, wireless signals are affected by various factors such as reflection, scattering or diffuse reflection of electromagnetic waves from indoor walls and other objects, which causes the positioning point of the target to jump and the motion trajectory to be uneven. This paper proposes an indoor location tracking algorithm based on Sparrow Search Algorithm (SSA) optimized extreme gradient learning machine (XGBoost) combined with particle filter (PF). First, SSA-XGBoost is used to transform the fingerprint positioning problem into a machine learning problem, and the mapping relationship between the position coordinates and the wireless signal strength is constructed. Secondly, according to the measurement value obtained by the SSA-XGBoost algorithm, the PF algorithm is used to obtain the predicted value of the target point. Finally, the predicted value is fused with the obtained measurement value to locate the position of the target point. Experimental results show that the errors of the proposed algorithm are reduced by 34.2%, 23.5% and 37.3% respectively compared with the traditional SSA-XGBoost algorithm, which proves that the proposed method has better positioning effect in the actual environment.

Key words: indoor positioning, particle filter, swarm algorithm, XGBoost