Indoor Positioning Optimization Based on Genetic Algorithm and RBF Neural Network

In UWB wireless indoor positioning, due to the influence of the indoor environment, the ranging error is often very large. In order to eliminate the influence of these environmental factors as much as possible and improve the accuracy of indoor wireless location, an indoor positioning optimization algorithm combining genetic algorithm and RBF neural network(GA-RBF) is proposed in this paper. We use genetic algorithm to find the optimal parameters of RBF network, so as to give full play to the advantages of RBF neural network for fast and high precision approximation. A large number of sample data are used to train genetic RBF neural network, the experimental results show that the positioning error of this algorithm is within 10cm, which can achieve a high positioning accuracy in the not line of sight (NLOS) environment. Compared with the traditional RBF neural network algorithm, its optimization performance has been greatly improved.