Separated and reconstructed individual radiation source identification method

Abstract

The separated and reconstructed individual radiation source identification method disclosed by the invention can effectively improve the individual identification accuracy of the radiation source. According to the technical scheme, the method comprises the following steps: collecting individual radiation source signals to establish a SepNet deep learning model; performing supervised training on the radiation source signal training set, separating individual features in radiation source signals, inputting original signals into a common feature extraction module to extract common features, and extracting high-dimensional feature vectors of training data; adopting a signal reconstruction module to reconstruct feature data from an individual feature extraction module and a content feature extraction module, reconstructing a feature map of an input signal, and calculating mean square error loss with an original signal; adopting the classification module to accurately classify the signals and judge the radiation source individuals to which the signals belong according to the obtained category probability values; and finally, using a joint optimization network model to update a convolution kernel weight, and measuring the recognition capability of the SepNet deep learning model by using a real number mapped to 0-1 through input.

Description

technical field [0001] The invention belongs to the technical field of signal identification, in particular to an individual radiation source identification (specific emitter identification, SEI) method based on feature separation and reconstruction of radiation sources. Background technique [0002] With the substantial increase of air radiation source equipment, it is necessary to judge whether the air target radiation source is working normally and the attributes of abnormal air targets, and these judgments need to be based on the individual identification of the air radiation source. Radiation source individual identification SEI is also called radiation source fingerprint identification or specific radiation source identification. Radiation source individual identification refers to the identification of the target individual by extracting one or more modulation characteristics of the received signal, because these characteristics are universal, Measurability, stability...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problem of low accuracy rate of radiation source individual identification under the traditional method, the present invention provides a radiation source individual identification, short training time, higher accuracy rate, simple classification, easy training, fast convergence speed, and effective Improve the accuracy of individual radiation source identification, with strong robustness, an individual radiation source identification method based on feature separation and reconstruction

Images