A novel method for jamming recognition based on multi-slices of cyclic spectrum density

A novel algorithm for jamming recognition in wireless communication is proposed in this paper. The algorithm is based on multi-slices of the signals´ cyclic spectrum density. The principal component analysis algorithm is adopted to decrease the dimensions of cyclic spectrum density function slices.One jamming recognition system was established for the new algorithm. In the recognition system, the cyclic spectrum density of signal samples was used as the original feature data. multi-slices data of cyclic spectrum density was needed to reduce the amount of computation.In the next step, the principal component analysis algorithm was used to optimize multi-slices data for the probabilistic neural network classifier.It is the last that probabilistic neural network classifier was used to identify the jamming signals.Simulation results show that the proposed algorithm gave a higher recognition rate than traditional method, especially when the jamming to signal ratio is lower. The results verified the validity of the proposed algorithm.