基于优化PSO-LSSVM的NLOS识别方法研究

In order to solve the problem of sharp drop in positioning accuracy caused by Non Line of Sight (NLOS) in indoor positioning, this paper proposes a recognition strategy to optimize the PSO-LSSVM, which combines the non-line-of-sight propagation and the line-of-sight ( LOS) propagation identification problem is transformed into a binary classification problem. The method uses the optimized particle swarm algorithm to optimize the two parameters of the least squares support vector machine, which has a certain significance to improve the accuracy of the positioning result and the robustness of the positioning algorithm. Experiments show that the algorithm improves the accuracy of NLOS/LOS classification, its performance is higher than the traditional PSO-LSSVM algorithm, and it has certain reliability.