Radar interference semi-supervised open set identification system based on generative adversarial network

Abstract

The invention provides a radar interference semi-supervised open set recognition system based on a generative adversarial network. The radar interference semi-supervised open set recognition system comprises a generator formed by the generative adversarial network GAN and a discriminator formed by an adaptive pseudo label-convolutional neural network. The generator is used for generating pseudo samples from random noise; the discriminator is used for discriminating whether the input sample is true or false. In the training process, the generator inputs the generated pseudo samples and a small number of marked samples of K classes into a discriminator for training, the pseudo samples generated by the generator are judged to be the (K + 1) th class, and the real samples are judged to be the first K classes; and after the training is completed, inputting the radar interference data to be identified into the trained discriminator, and outputting an interference identification result by the discriminator. The generative adversarial network is introduced, and radar interference semi-supervised open set recognition under a small number of marked samples is realized through the recognition capability of a game adversarial enhancement model of a generator and a discriminator and the discrimination capability of unknown classes in an iteration process.

Description

technical field [0001] The invention relates to a radar jamming recognition technology, in particular to a radar jamming semi-supervised recognition technology based on a generating confrontation network. Background technique [0002] Radar interference "closed set" recognition training and test samples meet the independent and identical distribution conditions, but in the actual environment, the model may encounter "unknown" interference other than the training set, so it is necessary to enhance the rejection ability of the model to achieve radar interference The open set recognition of . The radar jamming recognition model is a "closed set" recognition, that is, the number of training sample categories is the same as the number of test sample categories, and a better recognition effect is obtained. Considering the actual electromagnetic environment, for a model or system, it is not only required to be able to accurately identify the trained samples, but also to have the a...

AI Technical Summary

Problems solved by technology

When using the method of closed-set identification of interference, if there are untrained samples in the test process, due to the structural setting of the neural network model, the network only has the ability to extract the characteristics of the training samples, while for unknown samples, the network is still It will be judged as one of the training samples with a high degree of confidence; when the unknown sample is judged to be a certain type of interference, the subsequent anti-interference measures are only for this type of interference, and cannot suppress the unknown interference. Will pose a certain degree of threat to radar work

Images