基于半监督矩形网络的通信电台个体识别

doi:10.3969/j.issn.0372-2112.2019.01.001

电子学报 ›› 2019, Vol. 47 ›› Issue (1): 1-8.DOI: 10.3969/j.issn.0372-2112.2019.01.001

• 学术论文 • 下一篇

基于半监督矩形网络的通信电台个体识别

黄健航, 雷迎科

国防科技大学电子对抗学院, 安徽合肥 230037

收稿日期:2017-07-03 修回日期:2018-02-16 出版日期:2019-01-25
- 作者简介:
- 黄健航 男,1994年2月出生于广东深圳.国防科技大学电子对抗学院硕士研究生,研究方向为通信信号处理;雷迎科 男,1975年2月出生于安徽安庆.国防科技大学电子对抗学院指挥与控制系副教授,研究方向为通信信号处理、模式识别.
- 基金资助:
- 国家自然科学基金 (No.61272333）; 国防科技重点实验室基金 (No.9140C130502140C13068）; 总装预研项目基金 (No.9140A33030114JB39470）

Communication Radio Individual Recognition Based on Semi-Supervised Rectangular Network

HUANG Jian-hang, LEI Ying-ke

Electronic Countermeasures Institution of National University of Defense Technology, Hefei, Anhui 230037, China

Received:2017-07-03 Revised:2018-02-16 Online:2019-01-25 Published:2019-01-25
- Supported by:
- National Natural Science Foundation of China (No.61272333); Key Laboratory of national defense science and Technology Foundation (No.9140C130502140C13068); Pre-research Program Fund of the General Armaments Department (No.9140A33030114JB39470)

摘要/Abstract

摘要： 通信电台信号的小样本条件造成了电台个体识别准确性欠佳的问题，本文首次提出基于半监督矩形网络进行通信电台个体识别，克服小样本条件对电台个体识别效果的影响.首先提取电台信号的矩形积分双谱特征，人为注入噪声构成污染样本，在半监督矩形网络编码器中有监督训练，其训练结果通过网络径向连接传给解码器，解码器再无监督学习，重构未污染的原始样本，从网络顶层提取电台个体特征，输入softmax分类器实现分类识别.在实际采集的电台数据集上的实验结果说明，本算法在小样本条件下相比现有算法能更准确识别同型号的电台个体.

关键词: 小样本条件, 电台个体识别, 半监督学习, 矩形积分双谱, 自编码器

Abstract: Small sample condition of communication radio signal caused poor individual recognition on radios.To solve this problem,a method about communication radio individual recognition based on semi-supervised rectangular network was proposed innovatively.Firstly,the square integral bispectrum feature was extracted from radio signal and then was corrupted by Gaussian noise.The corrupted sample was passed to the encoder of semi-supervised rectangular network for supervised training.The trained parameterization was then mirrored to decoder through the lateral connection across the model.And the output was forced by decoder through unsupervised learning to be close to the clean input.Then the essential feature extracted was referred as the individual feature of radio signals.Individual recognition was finally accomplished by a softmax classifier.The experiment results on several radio datasets collected in actual environment indicated that the method had superior performance on identifying radio individuals with the same types under small sample condition.

Key words: small sample condition, radio individual recognition, semi-supervised learning, square integral bispectra, auto-encoder

中图分类号:

黄健航, 雷迎科. 基于半监督矩形网络的通信电台个体识别[J]. 电子学报, 2019, 47(1): 1-8.

HUANG Jian-hang, LEI Ying-ke . Communication Radio Individual Recognition Based on Semi-Supervised Rectangular Network[J]. Acta Electronica Sinica, 2019, 47(1): 1-8.

参考文献

[1] 任春辉.通信电台个体特征分析[D].成都:电子科技大学,2006. REN Chun-hui.Individual Character Analysis of Communication Transmitter[D].Chengdu:University of Electronic Science and Technology of China,2006.(in Chinese)
[2] 许丹,柳征,姜文利,周一宇.窄带信号中的放大器"指纹"特征提取:原理分析及FM广播实测实验[J].电子学报,2008,36(5):917-932. XU Dan,LIU Zheng,JIANG Wen-li,ZHOU Yi-yu.Extraction of amplifier fingerprints from narrow band signal:principle analysis and FM broadcast experiment[J].Acta Electronica Sinica,2008,36(5):917-932.(in Chinese)
[3] 张旻,钟子发,王若冰.通信电台个体识别技术研究[J].电子学报,2009,37(10):2125-2129. ZHANG Min,ZHONG Zi-fa,WANG Ruo-bin.Research on the technique of individual communication transmitter identi-fication[J].Acta Electronica Sinica,2009,37(10):2125-2129.(in Chinese)
[4] HALL J,BARBEAU M,KRANAKIS E.Radio frequency fingerprinting for intrusion detection in wireless networks[J].IEEE Transactions on Defend-able and Secure Computing,2005(12):1-35.
[5] BERTONCINI C,RUDD K,NOUSAIN B,et al.Wavelet fingerprinting of radio-frequency identification(RFID) tags[J].IEEE Transactions on Industrial Electronics,2012,59(12):4843-4850.
[6] XU S H.Radio transmitter classification using a new method of stray features analysis combined with PCA[A].Military Communication Conference[C].Orlando,FL,USA:IEEE,2007.1-5.
[7] 唐智灵.通信辐射源非线性个体识别方法研究[D].西安:西安电子科技大学,2013. TANG Zhi-ling.A Study of Nonlinear Method for Specific Communications Emitter Identification[D].Xian:Xidian University,2013.(in Chinese)
[8] 梁江海.一种基于经验模态分解的通信辐射源个体识别方法[J].中国电子科学研究院学报,2013,8(4):393-397. LIANG Jiang-hai.A method based on empirical mode decomposition for identifying transmitter individuals[J].Journal of CAEIT,2013,8(4):393-397.(in Chinese)
[9] 韩洁,张涛,王欢欢,等.基于3D-Hibert能量谱和多尺度分形特征的通信辐射源个体识别[J].通信学报,2017,38(4):99-109. HAN Jie,ZHANG Tao,WANG Huan-huan,et al.Communication emitter individual identification based on 3D-Hibbert energy spectrum and multi-scale fractal features[J].Journal on Communications,2017,38(4):99-109.(in Chinese)
[10] 汪勇,段田东,刘瑞东,等.短时频率稳定度特征分析的FSK信号个体识别方法[J].太赫兹科学与电子信息学报,2013,(6):880-885. WANG yong,DUAN Tian-dong,LIU Rui-dong,et al.Individual identification of FSK signals based on stability of transient carrier frequency[J].Journal of Terahertz Science and Electronic Information Technology,2013,(6):880-885.(in Chinese)
[11] 顾晨辉,王伦文.基于瞬时包络特征的跳频电台个体识别方法[J].信号处理,2012,28(9):1335-1340. GU Chen-hui,WANG Lun-wen.Individual frequency hopping radio identification method based on instantaneous envelope characteristics[J].Signal Processing,2012,28(9):1335-1340.(in Chinese)
[12] 陈志伟,徐志军,王金明.一种基于循环谱切片的通信辐射源识别方法[J].数据采集与处理,2013,28(3):284-288. CHEN Zhi-wei,XU Zhi-jun,WANG Jin-ming,et al.Emitter identification method based on cyclic spectrum density slice[J].Journal of Data Acquisition and Processing,2013,28(3):284-288.(in Chinese)
[13] 唐哲,雷迎科.基于最大相关熵的通信辐射源个体识别方法[J].通信学报,2016,37(12):171-175. TANG Zhe,LEI Ying-ke.Method of individual communication transmitter identification based on maximum correntropy[J].Journal on Communications,2016,37(12):171-175.(in Chinese)
[14] 孙志军,薛磊,徐阳明.基于深度学习的边际Fisher分析特征提取算法[J].电子与信息学报,2013,35(4):805-811. SUN Zhi-jun,XUE Lei,XU Yang-ming.Marginal fisher feature extraction algorithm based on deep learning[J].Journal of Electronics and Information Technology,2013,35(4):805-811.(in Chinese)
[15] WU Z,TAKAKI S,YAMAGASHI J.Deep Denoising Auto-Encoder for Statistical Speech Synthesis[OL].https://arxiv.org/abs/1511.06430,2015.
[16] 赵飞翔,刘永祥,霍凯.基于栈式降噪稀疏自动编码器的雷达目标识别方法[J].雷达学报,2017,6(2):149-156. ZHAO Fei-xiang,LIU Yong-xiang,HUO Kai.Radar target recognition based on stacked denoising sparse autoencoder[J].Journal of Radars,2017,6(2):149-156.(in Chinese)
[17] VALPOLA H.Chapter 8-From Neural PCA to Deep Unsupervised Learning[A].Advances in Independent Component Analysis and Learning Machines[M].USA:Elsevier Ltd,2015.
[18] VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked denoising autoencoders:Learning useful representations in a deep network with a local denoising criterion[J].Journal of Machine Learning Research,2010,11(12):3371-3408.
[19] IOFFE S,SZEGEDY C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[OL].https://arxiv.org/abs/1502.03167,2015.
[20] VINCENT P,LAROCHELLE H,BENGIO Y,et al.Extracting and composing robust features with denoising auto-encoders[A].International Conference on Machine Learning[C].Helsinki,Finland:ACM,2008.1096-1103.
[21] HAGER W,ZHANG H.The limited memory conjugate gradient method[J].Siam Journal on Optimization,2013,23(4):2150-2168.
[22] PEZESHKI M,FAN L,BRAKEL P,et al.Deconstructing the Ladder Network Architecture[OL].https://arxiv.org/abs/1511.06430,2015.
[23] ZHANG X,CHEUNG W K,LI C H.Learning latent variable models from distributed and abstracted data[J].Information Sciences,2011,181(4):2964-2988.
[24] SCHMIDHUBER J.Deep learning in neural networks:An overview[J].Neural Networks the Official Journal of the International Neural Network Society,2014,61:85-117.
[25] 蔡忠伟,李建东.基于双谱的通信辐射源个体识别[J].通信学报,2007,28(2):75-79. CAI Zhong-wei,LI Jian-dong.Study of transmitter individual identification based on bispectra[J].Journal on Communications,2007,28(2):75-79.(in Chinese)
[26] 陶旺林,卢选民,刘李娟.基于局部围线双谱的通信辐射源个体识别[J].计算机工程与应用,2013,49(1):131-133. TAO Wang-lin,LU Xuan-min,LIU Li-juan.Transmitter individual identification based on local surrounding-line integral bispectrum[J].Computer Engineering and Applications,2013,49(1):131-133.(in Chinese)

基于半监督矩形网络的通信电台个体识别

Communication Radio Individual Recognition Based on Semi-Supervised Rectangular Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	江兵兵, 何文达, 吴兴宇, 项俊浩, 洪立斌, 盛伟国. 基于自适应图学习的半监督特征选择[J]. 电子学报, 2022, 50(7): 1643-1652.
[2]	王雪松, 张翰林, 程玉虎. 基于自编码器和超图的半监督宽度学习系统[J]. 电子学报, 2022, 50(3): 533-539.
[3]	孙新, 盖晨, 申长虹, 张颖捷. 基于短语向量和主题加权的关键词抽取方法[J]. 电子学报, 2021, 49(9): 1682-1690.
[4]	席亮, 刘涵, 樊好义, 张凤斌. 基于深度对抗学习潜在表示分布的异常检测模型[J]. 电子学报, 2021, 49(7): 1257-1265.
[5]	余游, 冯林, 王格格, 徐其凤. 一种基于伪标签的半监督少样本学习模型[J]. 电子学报, 2019, 47(11): 2284-2291.
[6]	付晓, 沈远彤, 付丽华, 杨迪威. 基于特征聚类的稀疏自编码快速算法[J]. 电子学报, 2018, 46(5): 1041-1046.
[7]	盛凯, 刘忠, 周德超, 魏启航, 冯成旭. 一种基于证据理论的多类半监督分类算法[J]. 电子学报, 2018, 46(11): 2642-2649.
[8]	周孟, 朱福喜. 基于情感标签的极性分类[J]. 电子学报, 2017, 45(4): 1018-1024.
[9]	罗畅, 王洁, 王鹏飞, 肖军, 肖红. 卷积自编码器中粗粒度池化特征提取研究[J]. 电子学报, 2017, 45(10): 2390-2401.
[10]	刘金平, 陈青, 张进, 唐朝晖. 基于集成学习的交互式图像分割[J]. 电子学报, 2016, 44(7): 1649-1655.
[11]	周炫余, 刘娟, 邵鹏, 卢笑, 罗飞. 基于测度优化Laplacian SVM的中文指代消解方法[J]. 电子学报, 2016, 44(12): 3064-3072.
[12]	陶剑文, 姚奇富. 稀疏特征空间嵌入正则化:鲁棒的半监督学习框架[J]. 电子学报, 2014, 42(11): 2198-2204.
[13]	万建武, 杨明, 陈银娟. 代价敏感的半监督Laplacian支持向量机[J]. 电子学报, 2012, 40(7): 1410-1415.
[14]	赵莹;张健沛;杨静;王冠军. 一种改进的分枝定界半监督支持向量机学习算法[J]. 电子学报, 2010, 38(2): 449-454.
[15]	王娇, 罗四维, 曾宪华. 基于随机子空间的半监督协同训练算法[J]. 电子学报, 2008, 36(S1): 60-65.