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

A radar jamming and recognition system technology, applied in biological neural network models, character and pattern recognition, instruments, etc., can solve problems such as the inability to realize unknown interference suppression, radar work threats, etc., achieve generalization performance enhancement, and reduce misidentification Effect

Pending Publication Date: 2022-03-25
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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 b

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Radar interference semi-supervised open set identification system based on generative adversarial network
  • Radar interference semi-supervised open set identification system based on generative adversarial network
  • Radar interference semi-supervised open set identification system based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0027] The present invention is to achieve a radar interference collected identifier under a small amount of marking sample, and adaptive PL-CNN is used as a generator to form a GaN-PL-CNN model. Through the generator and the discriminator, the radar interference semi-supervision collation recognition is realized, and the basic block diagram of the model is shown in 3.

[0028] In the GAN-PL-CNN model, the generator G is like Figure 4As shown, the random noise z is refactored to a 256 * 1 dimensional vector, and the dimension is converted to 2 * 2 * 64, and the depth of the output vector is becoming more and more shallower and changing through the dimension. The process is: 256 → 256 → 128 → 128 → 64 → 1, that is, the black-white image of the last output image channel is 1, the output pixel size varies to: 4 * 4 → 8 * 8 → 16 * 16 → 32 * 32 → 64 * 64 → 128 * 128, then the dimension of the output image is 128 * 128 * 1.

[0029] Judgment Figure 5 Show. When training, consulate the c...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06V10/774G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/045G06F18/214Y02T10/40
Inventor 张伟康慧陈翾宇曹建蜀
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap