A method for specific emitter identification based on surrounding-line bispectrum and convolutional neural network

Abstract

Specific emitter identification (SEI) is an association of radar signal to specific emitter primarily. SEI has been widely used in military and civilian spectrum management applications. We propose a SEI method based on deep learning (convolutional neural network), which uses the characteristics of the received steady-state signal. Particularly, we calculate the bispectrum of the signal as the unique feature. Then, we use surrounding-line bispectrum to reduce the influence of noise. Finally, CNN is used to identify specific emitters by using the surrounding-line bispectrum. This method basically extracts the overall feature information hidden in the original signal. This can be used to improve recognition performance. The simulation results verify our conclusion that the proposed method is better than other existing solutions in the literature.