Combination linear lines of position and neural network for mobile station location estimation

Abstract

To enhance the effectiveness and accuracy of mobile station location estimation, author utilizes time of arrival measurements from three base stations and one angle of arrival information at the serving base station to locate mobile station in non-line-of-sight environments. This article makes use of linear lines of position, rather than circular lines of position, to give location estimation of the mobile station. It is much easier to solve two linear line equations rather than nonlinear circular ones. Artificial neural networks are widely used techniques in various areas due to overcoming the problem of exclusive and nonlinear relationships. The proposed algorithms employ the intersections of three linear lines of position and one angle of arrival line, based on Levenburg–Marquardt algorithm, to determine the mobile station location without requiring a priori information about the non-line-of-sight error. The simulation results show that the proposed algorithms can always provide much better location estimation than Taylor series algorithm, hybrid lines of position algorithm as well as the geometrical positioning methods for different levels of biased, unbiased, and distance-dependent non-line-of-sight errors.

Neural Network Localization With TOA Measurements Based on Error Learning and Matching

“…Each neuron in output layer compares its computed value with its target value to determine the corresponding error and then propagates this error back to the neurons in the previous layers to update the weights and biases between neurons. Some existing algorithms, such as back-propagation algorithm [18] and Levenburg-Marquardt algorithm [28] can be used to update the weights and biases.…”

“…An indoor fingerprint localization system with channel state information is proposed in [27], a deep learning is utilized to train all the weights of neural network in the offline stage, while a probabilistic method based on the RBF function is presented to obtain the estimated location in the online stage. Two forms of neural network localization methods combining with hybrid lines of position algorithm are proposed in [28] to determine the position of MT without priori information about NLOS error. Based on the NLOS channel classification and ranging error regression model, a convolutional neural network (CNN) localization method is proposed in [29].…”