Spread Spectrum Signals Classification Based on the Wigner-Ville Distribution and Neural Network Probability Density Function Estimation

A spread spectrum signal recognition can be accomplished by exploiting the particular features of modulation presented in a received signal observed in presence of noise. These modulation features are the result of slight transmitter component variations and acts as an individual signature of a transmitter. The paper describes a spread spectrum signal classification algorithm based on using the Wigner-Ville distribution (WVD), noise reduction procedure with using a two- dimensional filter and the RBF neural network probability density function estimator which extracts the features vector used for the final signal classification. The numerical simulation results for the P4-coded signals are presented.