计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (7): 279-286.doi: 10.11896/jsjkx.240600073

• 计算机网络 • 上一篇    下一篇

基于渐进式自训练开集域适应的辐射源个体识别

张涛涛, 谢钧, 乔平娟   

  1. 中国人民解放军陆军工程大学指挥控制工程学院 南京 210007
  • 收稿日期:2024-06-11 修回日期:2024-09-12 发布日期:2025-07-17
  • 通讯作者: 谢钧(xiejun@aeu.edu.cn)
  • 作者简介:(ztt6691@163.com)

Specific Emitter Identification Based on Progressive Self-training Open Set Domain Adaptation

ZHANG Taotao, XIE Jun, QIAO Pingjuan   

  1. School of Command and Control Engineering, Army Engineering University of the PLA, Nanjing 210007, China
  • Received:2024-06-11 Revised:2024-09-12 Published:2025-07-17
  • About author:ZHANG Taotao,born in 1992,postgra-duate.His main research interests include wireless network and specific emitter identification.
    XIE Jun,born in 1973,Ph.D,professor,Ph.D supervisor.His main research interests include wireless networks and intelligent network management.

PDF (PC)

25

摘要： 针对闭集场景中训练的辐射源个体识别模型部署在包含有新类别的辐射源个体环境条件中时会出现已知类识别性能下降以及新类识别错误的问题,提出了一种噪声变化场景下的基于开集域适应辐射源个体识别方法。利用最大最小阈值判别已知类和未知类并通过渐进式自训练的方法训练一个目标分类器用于测试场景。目标分类器的一个未知分类要同时拟合多个未知类的特征分布,可能会导致学习到的已知未知特征分布的边界混淆。基于此,提出了一个多中心损失用于增加目标已知类和未知类内的紧凑性以及类间的可区分性,可提高目标分类器判别的准确性。同时,为了减少源域和目标域之间因为噪声造成的指纹特征偏移问题,使用了基于原型到原型的对比学习来学习域不变特征。在公开数据集上进行了6组实验,所提方法在其中5组中的HOS指标好于其他方法,甚至在10dB-8dB的任务中HOS达到了93.8%,实验结果验证了所提方法的有效性。

关键词: 辐射源个体识别, 开集域适应, 自训练, 中心损失, 对比学习

Abstract: Aiming at the problem that the specific emitter identification model trained in the closed set scene will suffer from the degradation of the known class recognition performance and the error of the new class recognition when deployed in the environmental conditions of the specific emitter identification containing the new class,this paper proposes an specific emitter identification method based on open set domain adaptation in the noise change scene.The maximum and minimum thresholds are used to distinguish the known class and the unknown class,and a target classifier is trained by a progressive self-training method for testing the scene.An unknown classification of the target classifier fit the feature distribution of multiple unknown classes at the same time may lead to the problem of boundary confusion of the learned known and unknown feature distribution.Based on this,a multi-center loss is proposed to increase the compactness within the unknown class of the target known class and the distinguish ability between classes,which can improve the accuracy of the target classifier.At the same time,in order to reduce the problem of fingerprint feature offset caused by noise between the source domain and the target domain,a prototype-to-prototype contrastive learning is used to learn domain invariant features.Six groups of experiments are carried out on the public data set.The HOS index of the proposed method in five groups is better than other methods,and the HOS reaches 93.8 % in the task of 10dB-8dB.The experimental results show the effectiveness of the proposed method.

Key words: Specific emitter identification, Open set domain adaptation, Self-training, Center loss, Contrastive learning

中图分类号: 

  • TP391
[1]GU C M,CAO J J,WANG B W,et al.Individual identification of radiation sources based on hybrid feature selection[J].Compu-ter Science,2024,51(5):267-276.
[2]WANG B,GAO N,WANG F.Specific Emitter Identificationbased on CNN and Transformer[C]//2023 5th International Academic Exchange Conference on Science and Technology Innovation.IEEE,2023:571-575.
[3]SU J,LIU H,YANG L.Specific Emitter Identification Based on CNN via Variational Mode Decomposition and Bimodal Feature Fusion[C]//2023 IEEE 3rd International Conference on Power,Electronics and Computer Applications.IEEE,2023:539-543.
[4]YAN G,CAI Z,LIU Y,et al.Intelligent Specific Emitter IdentificationUsing Complex-Valued Convolutional Neural Network[C]//2023 IEEE 23rd International Conference on Communication Technology.IEEE,2023:1259-1263.
[5]ZHANGY,ZHANG Q,ZHAO H,et al.Multisource Heterogeneous Specific Emitter Identification Using Attention Mechanism-Based RFF Fusion Method[J].IEEE Transactions on Information Forensics and Security,2024,19:2639-2650.
[6]YIN L,FU X,SHI S,et al.Few-Shot Domain Adaption-Based Specific Emitter Identification Under Varying Modulation[C]//2023 IEEE 23rd International Conference on Communication Technology.IEEE,2023:1439-1443.
[7]XU C,ZHOU M,GE T,et al.Unsupervised domain adaption with pixel-level discriminator for image-aware layout generation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2023:10114-10123.
[8]LIU Y,ZHOU Z,SUN B.Cot:Unsupervised domain adaptation with clustering and optimal transport[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2023:19998-20007.
[9]ZHA X,LI T,QIU Z,et al.Cross-receiver radio frequency fingerprint identification based on contrastive learning and subdomain adaptation[J].IEEE Signal Processing Letters,2023,30:70-74.
[10]ZHANG X,LI T,GONG P,et al.Variable-modulation specific emitter identification with domain adaptation[J].IEEE Transactions on Information Forensics and Security,2022,18:380-395.
[11]WANG M,LIN Y,JIANG H,et al.TESPDA-SEI:Tensor embedding substructure preserving domain adaptation for specific emitter identification[J].Physical Communication,2023,57:101973.
[12]LI D,YAO B,SUN P,et al.Specific emitter identification based on ensemble domain adversarial neural network in multi-domain environments[J].EURASIP Journal on Advances in Signal Processing,2024,2024(1):42.
[13]SAITO K,YAMAMOTO S,USHIKU Y,et al.Open set domain adaptation by backpropagation[C]//Proceedings of the European Conference on Computer Vision.Springer,2018:153-168.
[14]JANG J H,NA B,SHIN D H,et al.Unknown-aware domain ad-versarial learning for open-set domain adaptation[J].Advances in Neural Information Processing Systems,2022,35:16755-16767.
[15]LI W,LIU J,HAN B,et al.Adjustment and alignment for unbiased open set domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2023:24110-24119.
[16]YUQ,IRIE G,AIZAWA K.Self-labeling framework for open-set domain adaptation with few labeled samples[J].IEEE Transactions on Multimedia,2023,26:1474-1487.
[17]ZHU Y,ZHUANG F,WANG J,et al.Deep subdomain adaptation network for image classification[J].IEEE Transactions on Neural Networks and Learning Systems,2020,32(4):1713-1722.
[18]GANIN Y,USTINOVA E,AJAKAN H,et al.Domain-adversarial training of neural networks[J].Journal of Machine Lear-ning Research,2016,17(59):1-35.
[19]QIN J.Individual identification of communication emitters based on deep learning[D].Beijing:Beijing University of Posts and Telecommunications,2019.
[20]WANG C,DAN B,ZHANG C S.A channel adaptive unsupervised training and recognition method for radiation sources[J].Journal of Ordnance and Equipment Engineering,2023,44(4):211-216.
[21]GAO Y,MA A J,GAO Y,et al.Adversarial open set domain adaptation via progressive selection of transferable target samples[J].Neurocomputing,2020,410:174-184.
[22]JANG J H,NA B,SHIN D H,et al.Unknown-aware domain adversarial learning for open-set domain adaptation[J].Advances in Neural Information Processing Systems,2022,35:16755-16767.
[23]WEN Y,ZHANG K,LI Z,et al.A discriminative feature lear-ning approach for deep face recognition[C]//European Confe-rence on Computer Vision.Cham:Springer,2016:499-515.
[24]LI J,XIE H,LI J,et al.Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Springer,2021:6458-6467.
[25]AMINI M R,FEOFANOV V,PAULETTO L,et al.Self-training:A survey[J].arXiv:2202.12040,2022.
[26]CHEN T,KORNBLITH S,NOROUZI M,et al.A simpleframework for contrastive learning of visual representations[C]//International Conference on Machine Learning.ACM,2020:1597-1607.
[27]YUE X,ZHENG Z,ZHANG S,et al.Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2021:13834-13844.
[28]SANKHE K,BELGIOVINE M,ZHOU F,et al.ORACLE:Optimized radio classification through convolutional neural networks[C]//IEEE INFOCOM 2019-IEEE Conference on Computer Communications.IEEE,2019:370-378.
[29]WONG L J,MCPHERSON S,MICHAELS A J.Assessing the value of transfer learning metrics for RF domain adaptation[J].arXiv:2206.08329,2022.
[30]SHEN G,ZHANG J.Exploration of transferable deep learning-aided radio frequency fingerprint identification systems[J].Security and Safety,2024,3:2023019.
[31]LI W,LIU J,HAN B,et al.Adjustment and alignment for unbiased open set domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2023:24110-24119.
[32]GAOF,PI D,CHEN J.Balanced and robust unsupervised Open Set Domain Adaptation via joint adversarial alignment and unknown class isolation[J].Expert Systems with Applications,2024,238:122127.
[33]HE K,ZHANG X,REN S,et al.Deep residual learning for imagerecognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:770-778.
[34]WANG Y,HUANG H,RUDIN C,et al.Understanding how dimension reduction tools work:an empirical approach to deciphering t-SNE,UMAP,TriMAP,and PaCMAP for data visualization[J].Journal of Machine Learning Research,2021,22(201):1-73.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发