基于边际Fisher深度自编码器的电台指纹特征提取<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201711008

Abstract
Figure/Table
References
Related Citation (1)

Download: PDF (1173 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming at the difficulty in radio fingerprint extraction caused by insufficient traditional training methods with small labeled samples, a deep autoencoder regularized by marginal Fisher analysis algorithm for radio fingerprint extraction is proposed. Based on deep autoencoder, the training procedure is divided into two parts, unsupervised pre-training and supervised finetuning based on marginal Fisher analysis. Firstly, the radio individual class information contained in the large amount of unlabeled samples is extracted. And the information is sent to the deep autoencoder for parameters optimization. Then, the trainable parameters are analyzed on the basis of marginal Fisher method with the assistant of labeled samples to improve the discriminant capability of fingerprint feature between radio individuals of the same model. The classification experiment is conducted on several communication radio signal datasets. The results show that the difference of radio individuals of the same model can be represented effectively by the proposed algorithm.

Key words： Small Sample Radio Fingerprint Autoencoder Marginal Fisher Analysis

Received: 12 June 2017

ZTFLH:

TN 911.7

Fund:Supported by National Natural Science Foundation of China(No.61272333), National Defense Technology Key Laboratory Fund(No.9140C130502140C13068), General Equipment Department Pre-Developed Project Fund(No.9140A33030114JB39470)

About author:: 黄健航(通讯作者),男,1994年生,硕士研究生,主要研究方向为通信对抗侦察.E-mail:rafael211@163.com.
雷迎科,男,1975年生,博士,副教授,主要研究方向为通信信号处理.E-mail:leiyingke@163.com.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HUANG Jianhang
	LEI Yingke

Cite this article:

HUANG Jianhang,LEI Yingke. Radio Fingerprint Extraction Based on Marginal Fisher Deep Autoencoder[J]. , 2017, 30(11): 1030-1038.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201711008 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2017/V30/I11/1030

[1] 柳征.辐射源调制分类与个体识别技术研究.博士学位论文.长沙:国防科学技术大学, 2005.
(LIU Z. Research on Modulation Classification and Individual Identification of Emitters. Ph.D Dissertation. Changsha, China: National University of Defense Technology, 2005.)
[2] 蔡忠伟,李建东.基于双谱的通信辐射源个体识别.通信学报, 2007, 28(2): 75-79.
(CAI Z W, LI J D. Study of Transmitter Individual Identification Based on Bispectra. Journal of Communications, 2006, 28(2): 75-79.)
[3] 唐哲,雷迎科.通信辐射源个体识别中基于l₂正则化的最大相关熵算法.模式识别与人工智能, 2016, 29(6): 527-533.
(TANG Z, LEI Y K. Algorithm of Maximum Correntropy Based on l₂-Regularization in Individual Communication Transmitter Identification. Pattern Recognition and Artificial Intelligence, 2016, 29(6): 527-533.)
[4] 黄欣,郭汉伟.一种稳健的通信辐射源个体识别方法.电讯技术, 2015, 55(3): 321-327.
(HUANG X, GUO H W. A Robust Specific Communication Emitter Identification Method. Telecommunication Engineering, 2015, 55(3): 321-327.)
[5] 唐智灵.通信辐射源非线性个体识别方法研究.博士学位论文.西安: 电子科技大学, 2013.
(TANG Z L. A Study of Nonlinear Method for Specific Communications Emitter Identifications. Ph.D. Dissertation. Xi′an, China: Xidian University, 2013)
[6] 桂云川,杨俊安,吕季杰.基于固有时间尺度分解模型的通信辐射源特征提取算法.计算机应用研究, 2017, 34(4): 1172-1175.
(GUI Y C, YANG J A, L J J. Feature Extraction Algorithm Based on Intrinsic Time-Scale Decomposition Model for Communication Transmitter. Application Research of Computers, 2017, 34(4): 1172-1175.)
[7] 陈志伟,徐志军,王金明, 等.一种基于循环谱切片的通信辐射源识别方法.数据采集与处理, 2013, 28(3): 284-288. (CHEN Z W, XU Z J, WANG J M, et al. Emitter Identification Method Based on Cyclic Spectrum Density Slice. Journal of Data Acquisition and Processing, 2013, 28(3): 284-288.)
[8] LECUN Y, BENGIO Y, HINTON G. Deep Learning. Nature, 2015, 521(7553): 436-444.
[9] 马勇,鲍长春.基于稀疏神经网络的说话人分割.北京工业大学学报, 2015, 41(5): 662-667.
(MA Y, BAO C C. Speaker Segmentation Based on Sparse Neural Network. Journal of Beijing University of Technology, 2015, 41(5): 662-667.)
[10] CHEN M M, WEINBERGER K, SHA F, et al. Marginalized Denoising Auto-Encoders for Nonlinear Representations // Proc of the 31th International Conference on Machine Learning. New York, USA: ACM, 2014: 1476-1484.
[11] 张彦,彭华.基于深度自编码器的单样本人脸识别.模式识别与人工智能, 2017, 30(4): 343-352.
(ZHANG Y, PENG H. One Sample per Person Face Recognition Based on Deep Autoencoder. Pattern Recognition and Artificial Intelligence, 2017, 30(4): 343-352.)
[12] 孙志军,薛磊,许阳明.基于深度学习的边际Fisher分析特征提取算法.电子与信息学报, 2013, 35(4): 805-811.
(SUN Z J, XUE L, XU Y M. Marginal Fisher Feature Extraction Algorithm Based on Deep Learning. Journal of Electronics and Information Technology, 2013, 35(4): 805-811.)
[13] NOCEDAL J. Updating Quasi-Newton Matrices with Limited Sto-rage. Mathematics of Computation, 1980, 35(151): 773-782.
[14] BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy Layer-Wise Training of Deep Networks[C/OL]. [2017-05-20]. http://papers.nips.cc/paper/3048-greedy-layer-wise-training-of-deep-networks.pdf.
[15] HINTON G. Reducing the Dimensionality of Data with Neural Network. Science, 2006, 313(5786): 504-507.
[16] YANG S C, XU B Y, ZHANG H J, et al. Graph Embedding and Extensions: A General Framework for Dimensionality Reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51.
[17] 徐书华,黄本雄,徐丽娜.基于SIB/PCA的通信辐射源个体识别.华中科技大学学报(自然科学版), 2008, 36(7): 14-17.
(XU S H, HUANG B X, XU L N. Identification of Individual Radio Transmitters Using SIB/PCA. Journal of Huazhong University of Science and Technology(Natural Science Edition), 2008, 36(7): 14-17.)
[18] XU S H, XU L N, XU Z G, et al. Individual Radio Transmitter Identification Based on Spurious Modulation Characteristic of Signal
Envelop // Proc of the IEEE Military Communications Conference. Washington, USA: IEEE, 2008. DOI: 10.1109/MILCOM.2008.4753446.
[19] WU Z Z, TAKAKI S, YAMAGISHI J. Deep Denoising Auto-Encoder for Statistical Speech Synthesis[J/OL]. [2017-05-20]. https://arxiv.org/pdf/1506.05268.pdf.