Application of Support Vector Machine to Radar Emitter Signal Recognition
-
摘要: 为了提高电子对抗设备的信号识别能力,采用相像系数法提取雷达辐射源信号特征,并引入支持向量机完成信号自动分类识别.相像系数法在大信噪比范围内稳定性好、分辨能力强.支持向量机分类器结构简单、可获得全局最优、泛化能力强.实验结果表明,基于相像系数和支持向量机的辐射源信号识别方法在大信噪比(5~20 dB)范围内,错误识别率最低可达2.68%,优于传统识别方法.Abstract: To enhance the ability of electronic warfare equipment to recognize signals,resemblance coefficient method was proposed to extract features from radar emitter signals,and support vector machine(SVM) was introduced to identify different signals automatically.Resemblance coefficient features have good stability and discriminability.SVM has good characteristics of simple structure,global optimum and strong generalization ability.Experimental results show that the introduced approach for recognizing radar emitter signals using resemblance coefficient and SVM is superior to the conventional ones.It works effectively in a large range of noise to signal ratio(5 to 20 dB) with the recognition error rate being as low as 2.68%.
-
黄知涛,周一宇,姜文利.基于相对无模糊相位重构的自动脉内调制特性分析[J].通信学报,2003,24(4):153-160.H uang Z T,Zhou Y Y,Jiang W L.The automatic analysis of intrapulse modulation characteristics based on the relatively non-ambiguity phase restoral[J].Journal of China Institute of Communications,2003,24(4):153-160.[2] Willson G B.Radar classification using a neural network [A].Applications of Artificial Neural Networks (1294) [C].Bellingham:SPIE,1990.200 210.[3] Shieh C S,Lin C T.A vector network for emitter identification[J].IEEE Transaction on antennas and propagation,2002,50(8):1 120-1 127.[4] ZhangG P.Neural networks for classification:a survey[J].IEEE Trans on System,Man,and Cybernetics-Part C:Application and Reviews,2000,30 (4):451-462.[5] 王守觉,王柏南.人工神经网络的多维空间几何分析及其理论[J].电子学报,2002,30(1):1-4.Wang S J,Wang B N.Analysis and theory of high-dimension space geometry for artificial neural networks [J].ACTA Electronica Sinica,2002,30(1):1-4.[6] 边肇祺,张学工.模式识别(第2版)[M].北京:清华大学出版社,2000.284-304.[7] Vapnik V.The nature of statistical learning theory[M].New York:Springer Verlag,1998.[8] Foody G M,Mathur A.A relative evaluation of multiclass image classification by support vector machines [J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(6):1 335-1 343.[9] Hsu C W,Lin C J.A comparison of methods for multiclass support vector machines [J].IEEE Transactions on Neural Networks,2002,13(2):415-425.[10] Rifkin R M.Everything old is new again:a fresh look at historical approaches in machine learning[D].Boston:Massachusettes Institute of Technology,2002.[11] Platt J C,Cristianini N,Shawe-Taylor J.Large margin DAG's for multiclass classification[J].Advances in Neural Information Processing Systems,2000,12:547-553.[12] Cheong S M,Oh S H,Lee S Y.Support vector machines with binary tree architecture for multi-class classification[J].Neural Information Processing-Letters and Reviews,2004,2 (3):47-51.[13] 张葛祥,金炜东,胡来招.基于粗集理论的雷达辐射源信号识别[J].西安交通大学学报,2005,39(8):871-875.Zhang G X,Jin W D,Hu L Z.Radar emitter signal recognition based on rough set theory [J].Journal of Xi'an Jiaotong University,2005,39(8):871-875.[14] Zhang G X,Jin W D,Hu L Z.Resemblance coefficient based intrapulse feature extraction approach for radar emitter signals [J].Chinese Journal of Electronics,2005,14(2):337-341.[15] 周荣星,祝向荣,王金金.高等数学(上册)[M].西安:西安电子科技大学出版社,1993.113.
点击查看大图
计量
- 文章访问数: 1474
- HTML全文浏览量: 79
- PDF下载量: 378
- 被引次数: 0