基于Fisher判别字典学习的辐射源调制特征识别

doi:10.3969/j.issn.1000-1093.2018.03.017

兵工学报 ›› 2018, Vol. 39 ›› Issue (3): 553-559.doi: 10.3969/j.issn.1000-1093.2018.03.017

基于Fisher判别字典学习的辐射源调制特征识别

吴笑天¹，王星¹，王志鹏²，周一鹏¹，陈游¹

（1.空军工程大学航空航天工程学院，陕西西安 710038； 2.94895部队，福建漳州 363000）

收稿日期:2017-06-07 修回日期:2017-06-07 上线日期:2018-05-07
作者简介:吴笑天（1993—），男，硕士研究生。 E-mail： celeswu@sina.com
基金资助:
航空科学基金项目（20152096019）

Emitter Signal Modulation Feature Recognition Based on Fisher Discrimination Dictionary Learning

WU Xiao-tian¹, WANG Xing¹， WANG Zhi-peng²， ZHOU Yi-peng¹, CHEN You¹

（1.Aeronautics and Astronautics Engineering College, Air Force Engineering University, Xi'an 710038, Shaanxi, China; 2.Unit 94895 of PLA, Zhangzhou 363000, Fujian, China）

Received:2017-06-07 Revised:2017-06-07 Online:2018-05-07

摘要/Abstract

摘要： 针对基于字典的信号调制类型识别方法中解析字典原子形态单一、无法与复杂辐射源信号最优匹配的问题，提出一种基于Fisher判别准则的字典学习方法。对辐射源信号进行时频分析，借鉴图像处理的方法提取信号时频特征列向量，在字典训练过程中加入信号调制类型信息，根据Fisher准则训练字典，使字典原子类间距离最大同时类内距离最小，以增强字典的识别性能；通过仿真分析Fisher判别字典的识别性能以及原子个数对字典性能的影响。研究结果表明：该方法相比于解析字典法和无监督字典法，具有更好的识别性能，在低信噪比时识别性能突出、抗噪声干扰性能好；综合考虑识别性能和计算量，当字典原子数取20时该方法性能最优。

关键词: 辐射源信号, 调制特征, Fisher判别, 字典学习, 时频分析

Abstract: The limited forms of atoms in analytical dictionary lead to sub-optimal matching of atoms and complex emitter signal, resulting in low recognition rate of signal modulation. A dictionary learning method based on Fisher discrimination criterion is proposed to improve the recognition efficiency. The time-frequency transformation of emitter signal is made. The feature vectors are extracted from time-frequency graph using image processing method, which are added class labels. In the dictionary training, the Fisher criterion with small within-class scatter and big between-class scatter is introduced, by which the dictionary not only represents signal more suitably, but also owns better classification performance. The simulated result proves that, compared to analytical dictionary and non-supervision dictionary, the proposed method can obtain a better recognition rate, especially under low SNR. For the atom number N_s=20, Fisher discrimination dictionary can achieve a pretty good balance in recognition rate and calculation amount. Key

Key words: emittersignal, modulationfeature, Fisherdiscrimination, dictionarylearning, time-frequencyanalysis

中图分类号:

TN911.72

吴笑天，王星，王志鹏，周一鹏，陈游. 基于Fisher判别字典学习的辐射源调制特征识别[J]. 兵工学报, 2018, 39(3): 553-559.

WU Xiao-tian, WANG Xing， WANG Zhi-peng， ZHOU Yi-peng, CHEN You. Emitter Signal Modulation Feature Recognition Based on Fisher Discrimination Dictionary Learning[J]. Acta Armamentarii, 2018, 39(3): 553-559.

参考文献

［1］王星, 叶志铨, 徐忠伟. 航空电子对抗原理［M］. 北京:国防工业出版社, 2008： 159-161.
WANG Xing, YE Zhi-quan, XU Zhong-wei. Airborne electronic countermeasures theory［M］. Beijing: National Defense Industry Press, 2008: 159-161. (in Chinese)

［2］ Pienie, z·ny A, Konatowski S. Intrapulse analysis of radar signal［J］. WIT Transactions on Modelling and Simulation, 2009, 48: 259-270.
［3］ Genol K. A set of features for classification of intrapulse modulations［C］∥Proceedings of Signal Processing and Communication Application Conference. Washington, DC, US: IEEE Computer Society, 2016: 2113-2116.
［4］朱明, 普运伟, 金炜东, 等. 基于时频原子方法的雷达辐射源信号特征提取［J］. 电波科学学报, 2007, 22(3): 458-462.
ZHU Ming, PU Yun-wei, JIN Wei-dong, et al. Feature extraction of radar emitter signals based on time-frequency atom［J］. Chinese Journal of Radio Science, 2007, 22(3): 458-462. (in Chinese)
［5］朱明, 金炜东, 普运伟, 等. 基于Chirplet原子的雷达辐射源信号特征提取［J］. 红外与毫米波学报, 2007, 26(4): 302-306.
ZHU Ming, JIN Wei-dong, PU Yun-wei, et al. Feature extraction of radar emitter signals based on Gaussian Chirplet atoms［J］. Journal of Infrared and Millimeter Waves, 2007, 26(4): 302-306. (in Chinese)
［6］王星, 周一鹏, 田元荣, 等. 基于改进遗传算法和Sin-Chirplet原子的调频雷达信号稀疏分解［J］. 上海交通大学学报, 2017, 51(7): 16-23.
WANG Xing, ZHOU Yi-peng, TIAN Yuan-rong, et al. Sparse decomposition for FM radar signal based on advanced genetic algorithm and Sin-Chirplet atoms［J］. Journal of Shanghai Jiao Tong University, 2017, 51(7): 16-23. (in Chinese)
［7］ Tosic I, Frossard P. Dictionary learning［J］. IEEE Signal Processing Magazine, 2011, 28(2): 27-38.
［8］练秋生, 石保顺, 陈书贞. 字典学习模型、算法及其应用研究进展［J］. 自动化学报, 2015, 41(2): 240-260.
LIAN Qiu-sheng, SHI Bao-shun, CHEN Shu-zhen. Research advances on dictionary learning models, algorithms and applications［J］. Acta Automatica Sinica, 2015, 41(2): 240-260. (in Chinese)
［9］ Zhang Q, Li B X. Discriminative K-SVD for dictionary learning in face recognition［C］∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC, US: IEEE Computer Society, 2010: 2691-2698.

［10］ Jiang Z L, Lin Z, Davis L S. Label consistent K-SVD: learning a discriminative dictionary for recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11): 2651-2664.
［11］ Yang M, Zhang L, Feng X C. Sparse representation based fisher discrimination dictionary learning for image classification［J］. International Journal of Computer Vision, 2014, 109(3): 209-232.
［12］王伟, 韩纪庆, 郑铁然, 等. 基于Fisher判别字典学习的说话人识别［J］. 电子与信息学报, 2016, 38(2): 367-372.
WANG Wei, HAN Ji-qing, ZHENG Tie-ran, et al. Speaker recognition based on fisher discrimination dictionary learning［J］. Journal of Electronic and Information Technology, 2016, 38(2): 367-372. (in Chinese)
［13］ Laska J, Kirolos S, Massoud Y, et al. Random sampling for analog-to-information conversion of wideband signals［C］∥Proceedings of IEEE Dallas Workshop on Design, Applications Integration and Software. Washington, DC, US: IEEE Computer Society, 2006: 119-122.
［14］ Wang J, Kwon S, Shim B. Generalized orthogonal matching pursuit［J］. IEEE Transactions on Signal Processing,2012, 60(12): 6202-6216.
［15］ Yang A Y, Sastry S S, Ganesh A, et al. Fast l1-minimization algorithms and an application in robμst face recognition: a review［C］∥Proceedings of IEEE International Conference on Image Processing. Washington, DC, US: IEEE Computer Society, 2010: 1849-1852.
［16］王希勤, 刘婧瑶, 孟华东, 等. 一种基于时频原子特征的雷达辐射源信号识别方法［J］. 红外与毫米波学报, 2011, 30(6): 566-570.
WANG Xi-qin, LIU Jing-yao, MENG Hua-dong, et al. A method for radar emitter signal recognition based on time-frequency atom features［J］. Journal of Infrared and Millimeter Waves, 2011, 30(6): 566-570. (in Chinese)

第39卷
第3期2018 年3月兵工学报ACTA
ARMAMENTARIIVol.39No.3Mar.2018

[1]	闫晓鹏, 张锦玉, 郝新红, 李剑锋, 代健. 基于多项式Chirplet变换的线性调频引信干扰波形设计方法[J]. 兵工学报, 2024, 45(2): 504-515.
[2]	普运伟，刘涛涛，郭江，吴海潇. 基于卷积神经网络和模糊函数主脊坐标变换的雷达辐射源信号识别[J]. 兵工学报, 2021, 42(8): 1680-1689.
[3]	李东瑾，杨瑞娟，董睿杰. 基于联合投影字典学习的辐射源调制识别[J]. 兵工学报, 2020, 41(7): 1464-1472.
[4]	李东瑾，杨瑞娟，李晓柏，朱晟坤，费太勇. 基于栈式降维与字典学习的辐射源调制识别[J]. 兵工学报, 2020, 41(10): 2023-2032.
[5]	呙鹏程，吴礼洋. 融合卷积特征与判别字典学习的低截获概率雷达信号识别[J]. 兵工学报, 2019, 40(9): 1881-1889.
[6]	郑权，李宝星，翁春生，白桥栋. 双波对撞模态下的液态燃料旋转爆轰发动机推力测试研究[J]. 兵工学报, 2017, 38(4): 679-689.
[7]	计宏磊，杨清文，秦晓燕. 基于分层模型和鲁棒字典学习的背景差分炸点检测[J]. 兵工学报, 2016, 37(4): 705-711.
[8]	徐舟，张浩，程水英. 未知包络多分量线性调频脉冲信号参数估计[J]. 兵工学报, 2016, 37(3): 462-470.
[9]	李湘平，鲁军勇，李玉，武晓康. 基于解析法的电磁发射弹丸内膛磁场分布特性分析[J]. 兵工学报, 2016, 37(12): 2205-2211.

基于Fisher判别字典学习的辐射源调制特征识别

Emitter Signal Modulation Feature Recognition Based on Fisher Discrimination Dictionary Learning

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价