Deep learning-based specific emitter identification using integral bispectrum and the slice of ambiguity function.

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 an SEI method based on deep learning (DL), which uses the phase noise feature of the received signal. Particularly, we calculate the bispectrum and ambiguity function of the signal as the feature. Then, we use integral bispectrum and slice to reduce the influence of noise and redundant information. Finally, some DL models like deep residual network (Resnet) are used to identify specific emitters by using the feature. The method proposed in this paper improves the recognition performance of SEI by extracting the characteristic information of phase noise hidden in the original signal. The effectiveness of the proposed algorithm is verified by comparison with simulation experiments. [ABSTRACT FROM AUTHOR]