基于深度学习的特定辐射源识别方法研究综述

打开文本图片集

中图分类号：TP18;TN97 文献标志码：A

A review of specific emitter identification methods based on deep learning

LIU Fuyuan1²，ZHENG Jin，ZHANG Xiaolin²，LIU Ruilil （1.Department of Electronic Engineering， Shanghai Jiao Tong University， Shanghai 2OO24O，China; 2.No.36 Research Institute of CETC，Jiaxing 314O33，Zhejiang，China; 3.Unit 63921 of PLA，Beijing 100094，China）

Abstract： In recent years，Deep Learming （DL）has achieved recognition accuracy far beyond traditional methods in the identification of specific radiation sources，and has been widely used in the field of national defense and civil information security.The principle of specific emitter identification（SEI） is expounded，and two approaches for SEI based on whether feature extraction from the signal is required are summarized.The feature extraction methods and neural network architectures used in these approaches are introduced. Then the challnges encountered in SEI scenarios and relevant DL methods are discussed.Finally，some of the current issues and future directions in the research on SEI are discussed.

Key words：SEI; DL；metric learning； transfer learning；generative adversarial networ

0 引言

特定辐射源识别（SEI是利用信号的发射机硬件差异来识别辐射源类别或者个体的过程。（剩余8716字）