Communication radiation source individual recognition method based on related entropy sparse representation

Abstract

The invention discloses a communication radiation source individual recognition method based on related entropy sparse representation. The method comprises the following steps: receiving communicationradiation source signals, extracting rectangular integration bispectrum feature vectors of I / Q two-path digital zero intermediate frequency signals, dividing the rectangular integration bispectrum feature vectors of all the received communication radiation source signals into training sample sets and testing sample sets, forming a rectangular integration bispectrum feature dictionary from the training sample sets, respectively performing related entropy sparse representation on each testing sample in the testing sample sets on the rectangular integration bispectrum feature dictionary, obtaining a representation coefficient vector of each testing sample, obtaining representation residuals of different categories of training sample sub-sets to the testing samples according to the representation coefficient vector, and taking the categories corresponding to the minimum representation residual as categories of communication radiation source individuals. The problems existing in the conventional method that the method cannot be used for recognizing communication radiation sources of the same manufacturer and the same model, the same signal source cannot be recognized in different noiseenvironments and the like are solved.

Description

technical field [0001] The invention belongs to the technical field of communication signal identification, in particular to a communication radiation source individual identification method based on correlation entropy sparse representation. Background technique [0002] The individual identification of communication radiation sources refers to the unique subtle features of the signals radiated by different manufacturers and different batches of communication radiation equipment, and adopts various means to identify the subtle features in these signals. The industry mainly uses transient signal characteristics or steady-state signal characteristics to realize the individual identification of communication radiation sources. Typical methods include methods based on instantaneous characteristic analysis of radiation sources, methods based on spurious characteristics, methods based on modulation parameters and methods based on high-order statistical methods, but there are stil...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a communication radiation source individual identification method based on correlation entropy sparse representation, to solve the problems existing in existing methods that cannot be used to identify communication radiation sources of the same manufacturer and model, and the same signal source in different noise environments to further improve the ability and level of individual identification of communication radiation sources

Images