"A hierarchical Neural Network-based receiver for GNSS systems"

In this paper a novel method to solve the fine synchronization problem in GNSS receivers is presented. In particular a hierarchical neural network-based solution, able to estimate the channel in which the receiver operates, will be shown. The proposed method is based on two different Neural Networks and it is able to improve the fine tracking performances in urban environment. The solution takes advantage of the Self Organizing Map (SOM) properties, a particular type of Neural Networks useful in unsupervised systems, to improve the performances in presence of multipath.