Optimization of ANN applied to non-linear system identification based in UWB

In this work we propose a hybrid technique for artificial neural network optimization based in UWB system. This technique is a combination of real-coded genetic (GA) and back propagation (BP) algorithms simulating an ultra wideband (UWB) system. The main idea is to apply the back propagation over the five more adapted individuals of each generation produced by the real coded GA, in order to allow the evolution of these individuals before the crossover operation. The combined algorithms are used in non-linear system identification. Some solutions are presented to solve common problems arising from the application of genetic algorithm