基于深度学习的特定辐射源识别方法研究综述  

A review of specific emitter identification methods based on deep learning

作　　者：刘馥源 郑瑾[3] 张小林[2] 刘瑞丽 LIU Fuyuan;ZHENG Jin;ZHANG Xiaolin;LIU Ruili(Department of Electronic Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;No.36 Research Institute of CETC,Jiaxing 314033,Zhejiang,China;Unit 63921 of PLA,Beijing 100094,China)

机构地区：[1]上海交通大学电子系,上海200240 [2]中国电子科技集团公司第三十六研究所,浙江嘉兴314033 [3]中国人民解放军63921部队,北京100094

出　　处：《航天电子对抗》2025年第1期8-13,共6页Aerospace Electronic Warfare

摘　　要：近年来,深度学习在特定辐射源识别中获得了远超传统方法的识别准确度,在国防和民用信息安全领域中得到了广泛应用。首先阐述了特定辐射源的识别原理,根据是否需要对信号进行特征提取总结了2种基于深度学习的特定辐射源识别方案,并举例介绍了这2种方案采用的特征提取方法和神经网络架构。然后讨论了特定辐射源识别场景中面临的问题并归纳了相应的深度学习方法。最后讨论了目前特定辐射源识别课题中存在的一些问题和发展方向。In recent years,Deep Learning(DL)has achieved recognition accuracy far beyond tra-ditional 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 re-quired are summarized.The feature extraction methods and neural network architectures used in these approaches are introduced.Then the challenges encountered in SEI scenarios and relevant DL meth-ods are discussed.Finally,some of the current issues and future directions in the research on SEI are discussed.

关 键 词：特定辐射源识别 深度学习 度量学习 迁移学习 对抗生成网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TN97[自动化与计算机技术—控制科学与工程]