UWB indoor location based on improved least square support vector machine considering anchor anomaly

Abstract

In the UWB indoor positioning system, the positioning anchor is extremely susceptible to interference, which affects the accuracy, stability and reliability of the positioning system. When the anchor is subject to strong interference, its data will fluctuate abnormally and accurate positioning cannot be completed. In order to solve the localization problem of anchor anomaly in UWB indoor positioning system, this paper proposes a localization model based on the least squares support vector machine optimized by particle swarm optimization. Firstly, the distance between the label and the anchor is collected using bilateral ranging. Then, the indoor positioning model is established using the least squares support vector machine. Finally, the particle swarm algorithm is introduced to optimize the penalty factor and kernel width of the least squares support vector machine. The experimental results show that the average positioning accuracy of the particle swarm optimization least squares support vector machine positioning model can reach 0.02m under normal anchor conditions, and the average positioning accuracy can reach 0.03m under abnormal anchor conditions.