Recognition Algorithm of Emitter Signals Based on PCA+CNN

摘要

In order to solve the problem of low recognition rate of emitter signal under low SNR by the traditional method, a recognition algorithm based on PCA+CNN is proposed. The radar emitter signal is processed time-frequency image. The image is processed, and is reduced dimensionality by PCA. Learning model is adjusted by pretraining, and the softmax classifier commonly used on the pretraining model adopts supervised sizing and recognition, finally complete the identification task. The simulation results show that the algorithm can achieve high recognition rate, compared with traditional algorithm.