基于随机森林的雷达信号脉内调制识别

doi:10.11959/j.issn.1000-0801.2016151

摘要/Abstract

摘要：

针对雷达信号脉内调制识别算法存在着准确率低的问题，提出一种新的雷达脉内调制类型自动识别方法，该方法首先提取雷达信号时频图像的形状特征和纹理特征构成融合特征，然后将融合特征输入随机森林分类器，实现信号的分类识别。仿真实验中对8种常见的不同调制类型的雷达信号进行识别，提出的算法在信噪比为-2 dB时识别准确率可以达到90%以上，验证了该方法的有效性。

关键词: 雷达信号识别, 时频图像, 融合特征, 随机森林

Abstract:

To solve the existing problems of low recognition rate and noise problem in radar signal recognition,the fusion feature extraction method of time-frequency image and the random forest classifier is applied to the identification of radar signals.The radar signal time-frequency image was firstly extracted the shape features and texture features to anstitute fusion characteristics,into and then input fusioncharacteristics radom forest classifier recognition of the signal classification was realized.The results of simulation experiments for eight kinds of common radar signals to recognition show that recognition accuracy of the method proposed can be achieved more than 90% in SNR -2 dB,so it also verify the effectiveness of the method.

Key words: radar signal recognition, ime-frequency image, fusion feature, random forest

刘歌,张国毅,于岩. 基于随机森林的雷达信号脉内调制识别[J]. 电信科学, 2016, 32(5): 69-78.

Ge LIU,Guoyi ZHANG,Yan YU. Intra-pulse modulation recognition of radar signal based on random forest[J]. Telecommunications Science, 2016, 32(5): 69-78.

图/表 5

图1

图2

图3

表1

图4

参考文献 17

[1]	韩俊，何明浩，朱元清等. 雷达信号脉内特征自动识别的一种新方法[J]. 弹箭与制导学报， 2007,27(2):270-272. HAN J ， HE M H ， ZHU Y Q et al. A new automatic recognition method within radar pulse characteristics[J]. Arrows and Guidance, 2007,27(2):270-272.
[2]	毕大平，董晖，姜秋喜 . 基于瞬时频率的脉内调制识别技术[J]. 电子对抗技术， 2005,20(2):6-10. BI D P ， DONG H ， JIANG Q X . Intra-pulse modulation recognition technology based on the instantaneous frequency[J]. Electronic Countermeasure Technology, 2005 20(2):6-10.
[3]	CIBLAT P , LOUBATON P , SERPEDIN E , et al. Asymptotic analysis of blind cyclic correlation-based symbol-rate estimators[J]. IEEE Transactions on Information Theory, 2002,48(7): 1922-1934
[4]	孟玲玲，李静，韩宝如 . 循环谱相关方法在调制信号参数估计中的应用[J]. 燕山大学学报， 2010,34(3):252-255. MENG L L ， LI J ， HAN B R . Cyclic spectrum correlation method in the application of the modulation signal parameter estimation[J]. Journal of Yanshan University, 2010,34(3):252-255.
[5]	白航，赵拥军，胡德秀 . 基于 Choi-Williams 时频图像特征的雷达辐射源识别[J]. 数据采集与处理， 2012,27(4):480-485. BAI H ， ZHAO Y J ， HU D X . Radar radiating source recognition based on Choi-Williams time-frequency image characteristics[J]. Data Acquisition and Processing, 2012,27(4):480-485.
[6]	白航，赵拥军，沈伟等. 基于时频分布Reyni熵特征的雷达辐射源识别[J]. 电路系统学报， 2013,18(1):437-442. BAI H ， ZHAO Y J ， SHEN W . Radar radiating source recognition based on the time-frequency distribution Renyi entropy characteristics[J]. Journal of Circuit System, 2013 18(1):437-442.
[7]	范会敏，王浩 . 模式识别方法概述[J]. 电子设计工程， 2012,20(19):48-51. FAN H M ， WANG H . An overview of the pattern recognition method[J]. Electronic Design Engineering, 2012 20(19):48-51.
[8]	王丽亚 . 图像特征提取和分类[D]. 西安：西安电子科技大学， 2006. WANG L Y . Cooperative spectrum sensing algorithms based on eigenvalue structure of the received signal[D]. Xi'an: :Xi'an University of Electronic Science and Technology, 2006.
[9]	刘康宁 . 基于时频分析的雷达信号调制方式识别技术研究[D]. 西安：西安电子科技大学， 2014. LIU K N . Radar signal modulation mode recognition technology research based on the time-frequency analysis[D]. Xi'an: Xi'an University of Electronic Science and Technology, 2014.
[10]	GONZALEZ R C , WOODS R E , EDDINS S L . Digital image processing using MATLAB. New York: Pearson Education Inc, 2007: 197-199.
[11]	刘丽，匡纲要 . 图像纹理特征提取方法综述[J]. 中国图像图形学报， 2009,14(4):622-635. LIU L ， KUANG G Y . Image texture feature extraction methods review[J]. Chinese Journal of Image and Graphics, 2009 14(4):622-635.
[12]	付玮，曾接贤 . 基于形状特征的图像检索技术研究[J]. 计算机技术与发展， 2007,17(11):228-232. FU W ， ZENG J X ， ZENG J X . Image retrieval technology research based on shape feature[J]. Computer Technology and Development, 2007 17(11):228-232.
[13]	张跃 . 模糊数学方法及其应用[M]. 北京：煤炭工业出版社， 1992. ZHANG Y . Fuzzy mathematics method and application[M]. Beijing: Coal Industry Press， 1992.
[14]	FERN NDEZ-DELGADO M , CERNADAS E , BARRO S . Do we need hundreds of classifiers to solve real world classification problems. Journal of Machine Learning Research, 2014(15): 3133-3181
[15]	李贞贵 . 随机森林改进的若干研究[D]. 厦门：厦门大学， 2014. LI Z G . Random forests improved several research[D]. Xiamen： Xiamen University, 2014.
[16]	李欣海 . 随机森林模型在分类与回归分析中的应用[J]. 应用昆虫学报， 2013,50(4):1190-1197. LI X H . Random forests model application in the classification and regression analysis[J]. Journal of Application Insects, 2013 50(4):1190-1197.
[17]	蔡曲林 . 基于概率神经网络的模式识别[D]. 长沙：国防科技大学， 2005. CAI Q L . Pattern recognition based on probabilistic neural network[D]. Changsha: National University of Defense Technology, 2005.

分类器	识别准确率
分类器	-10 dB	-8 dB	-6 dB	-4 dB	-2 dB	0 dB	2 dB	4 dB	6 dB	8 dB	10 dB
SVM	0.52	0.63	0.72	0.82	0.89	0.92	0.96	0.98	0.99	1.0	1.0
PNN	0.62	0.68	0.76	0.81	0.87	0.93	0.99	1.0	1.0	1.0	1.0
RF	0.60	0.69	0.82	0.87	0.93	0.98	0.99	1.0	1.0	1.0	1.0