The TDOA Algorithm Based on BP Neural Network Optimized by Cuckoo Search

Abstract

In the UWB indoor positioning system, the Non-Line of Sight (NLOS) error usually has a great influence on the positioning of the mobile platform. In order to reduce the influence of NLOS error on the positioning accuracy of mobile stations, this paper proposes a TDOA algorithm based on BP neural network optimized by Cuckoo Search (CS). The algorithm uses the cuckoo search to optimize and train the initial weights of the BP neural network, and then corrects the measured time difference of the Time Difference of Arrival (TDOA) after the training model. Finally, the Chan algorithm is used to perform the positioning calculation according to the corrected TDOA value. The simulation results show that the positioning accuracy of this algorithm is significantly improved compared with the traditional algorithm