Optimum frequencies selection for radar target classification by neural network

A simple method for selecting the optimum frequencies for radar target classification using a backpropagation neural network (BNN) is presented. Results indicate that the BNN can be used not only for identifying radar targets in the frequency domain, but also for determining the optimum frequencies as an additive result in the learning process of the BNN. This method is based on the sensitivity analysis of the input nodes of the BNN. The frequencies corresponding to the input nodes which have maximum sensitivities are selected as the optimum frequencies. This method was verified on five simple radar targets.<>