A New TDOA Localization Algorithm based BP Neural Network

In a localization system, time difference of arrival (TDOA) technique is widely used to estimate the location of a mobile station (MS). To improve the performance of MS location estimation, a novel algorithm based artificial neural network (NN) is proposed in non-line-of-sight (NLOS) environments. BP neural network is a classic artificial neural network and may be effectively used for mathematical modeling and prediction. The parameters, such as the weights and biases of the single neural network are obtained after the training. TDOA information data are given as input to the neural network models, and coordinates x and y of the nodes are taken as the outputs. The simulation results show that the proposed algorithm can obtain more precise location accuracy. Index Terms - Localization, TDOA, BP neural network