融合双注意力的小样本辐射源个体识别网络  

Small sample radiation source individual recognition network with dual attention fusion

作　　者：刘佳乐 郭志涛 王宏[1] 张森 Liu Jiale;Guo Zhitao;Wang Hong;Zhang Sen(College of Electronic Information Engineering,Hebei University of Technology,Tianjin 300130,China;Innovation Research Institute,Hebei University of Technology(Shijiazhuang),Shijiazhuang 050299,China)

机构地区：[1]河北工业大学电子信息工程学院,天津300130 [2]河北工业大学创新研究院(石家庄),石家庄050299

出　　处：《电子测量技术》2024年第19期70-78,共9页Electronic Measurement Technology

基　　金：河北工业大学创新研究院(石家庄)石家庄市科技合作专项基金(SJZZXB23005)项目资助。

摘　　要：特定辐射源识别在军事和民用领域中发挥着越来越重要的作用。随着深度学习技术的飞速发展,SEI方法的识别性能得到了显著提升。然而这些方法往往依赖于大量的辐射源样本数据,在样本数量有限的实际应用场景中表现不佳。针对这一问题,本研究提出了一种新颖的深度学习网络模型CRCPA-GCN用于实现小样本场景下的SEI。该模型在多层复数卷积神经网络中融合了CPCA和GCNet注意力模块,采用类重建和对抗训练的方法显著提升了小样本场景下的识别性能。本研究在公开数据集上进行了一系列实验验证,并与当前主流的SEI网络模型进行了比较。实验结果表明,在20 shot的学习条件下,所提出的CRCPA-GCN网络模型达到了95.81%的准确率,优于其他主流SEI网络,并且在鲁棒性方面表现出色。Specific emitter identification is playing an increasingly important role in the military and civilian sectors.With the rapid development of deep learning technology,the recognition performance of SEI method has been significantly improved.However,these methods often rely on a large number of radiation source sample data,and perform poorly in practical application scenarios with limited sample size.To solve this problem,this study proposes a novel deep learning network model CRCPA-GCN to achieve SEI in small-sample scenarios.The model integrates CPCA and GCNet attention modules in a multi-layer complex convolutional neural network,and the recognition performance in small-shot scenarios is significantly improved by using the methods of class reconstruction and adversarial training.In this study,a series of experiments were carried out on public datasets and compared with the current mainstream SEI networks.Experimental results show that the proposed CRCPA-GCN network model achieves an accuracy of 95.81%under the learning condition of 20 shot,which is better than other mainstream SEI networks and performs well in robustness.

关 键 词：特定辐射源识别 小样本学习 注意力模块 类重建 对抗训练 

分 类 号：TN975[电子电信—信号与信息处理] TN92[电子电信—信息与通信工程]