基于多域判别核典型相关分析的辐射源指纹特征融合方法  

Radio frequency fingerprinting feature fusion based on multi-domain discriminant kernel canonical correlation analysis

作　　者：孙丽婷 王翔 黄知涛[1] Liting SUN;Xiang WANG;Zhitao HUANG(Department of Electronic Science,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学电子科学学院,长沙410073

出　　处：《中国科学：信息科学》2023年第1期146-163,共18页Scientia Sinica(Informationis)

基　　金：湖南省创新群体研究项目(批准号:2019JJ10004);国防科技大学青年创新奖(批准号:18/19-QNCXJ)资助项目。

摘　　要：辐射源个体识别(specific emitter identification,SEI)是指通过提取信号中蕴含的有关其发射来源的硬件指纹信息,来实现对特定信号辐射源的精确识别.SEI技术的关键在于指纹特征的提取.相关研究大多侧重于定义和提取新的指纹特征,较少关注对已有特征的综合利用问题.鉴于不同分析域的特征对辐射源指纹的描述存在互补性,本文提出一种基于多域判別核典型相关分析(multi-domain discriminant kernel canonical correlation analysis,MDKCCA)的辐射源指纹多域特征融合方法,充分利用特征的标签信息以及特征间的互补性,在高维空间完成多域特征的降维与融合.以4个特征分析域8种常见指纹特征为依托,在4种不同类型的实测数据集上验证了算法的性能.结果证明,该方法无需人工特征寻优环节,可大幅降低融合特征的维度,对4类目标的准确识别率均达到95%以上,优于最优单一特征,同时优于基于直接级联或基于PCA(principal component analysis)降维变换的简单特征综合方法、基于神经网络的特征综合方法,以及基于判别相关分析(discriminant canonical correlation,DCA)等方法的特征融合方法.Specific emitter identification(SEI)refers to the precise identification of a specific transmitter through the extraction of hardware fingerprint information from the received signal.The majority of related research focuses on the definition and extraction of new fingerprint features,with less emphasis on the comprehensive use of existing features.Because the characteristics of different analysis domains are complementary to the description of the radio frequency fingerprint,this paper proposes a multi-domain feature fusion strategy for SEI based on multi-domain discriminant kernel canonical correlation analysis(MDKCCA),which fully exploits the complementarity between the features of different domains and combines feature tag information.MDKCCA affords multi-domain feature dimensionality reduction and fusion in a high-dimensional space.The algorithm’s performance is validated on four different types of real-world data sets using eight common fingerprint features in four feature analysis domains.The results show that this method eliminates the need for manual feature optimization and can significantly reduce the dimensionality of fusion features.The recognition rate on various targets exceeds 95%,which is higher than the best single feature.It is also superior to the simple feature synthesis method based on direct cascade or PCA dimensionality reduction transformation,the neural network-based feature synthesis method,and the feature fusion method based on discriminant canonical correlation methods.

关 键 词：辐射源个体识别 特征融合 多域辐射源指纹特征 典型相关分析 特征提取 

分 类 号：TN911.7[电子电信—通信与信息系统]