基于小波包变换和特征选择的雷达辐射源信号识别  

Radar emitter signal recognition based on wavelet packet transform and feature selection

作　　者：张葛祥[1] 荣海娜[1] 金炜东[1] 

机构地区：[1]西南交通大学电气工程学院,四川成都610031

出　　处：《电路与系统学报》2006年第6期45-49,55,共6页Journal of Circuits and Systems

基　　金：国家自然科学基金项目(60572143);西南交大基金项目(2005A13);国防科技重点实验室基金项目(NEWL51435QT220401)

摘　　要：为了提高雷达辐射源信号的正确识别率以满足现代电子对抗的需要,提出一种基于小波包变换和特征选择的雷达辐射源信号识别新方法。先采用小波包变换进行特征提取,再采用基于量子遗传算法的相像系数特征选择法来挑选出小波包特征中分辨能力强的特征。仿真实验结果显示,该方法用较少的特征能获得较高的正确识别率,具有一定的参考价值。To enhance accurate recognition rates of radar emitter signals to meet the requirements of modern electronic warfare, a novel method based on wavelet packet transform and feature selection is proposed to recognize different radar emitter signals. Wavelet packet transform is used to extract features from radar emitter signals. Resemblance coefficient feature selection approach based on quantum genetic algorithm is applied to select the most discriminatory features from a large number of wavelet packet transform features. Simulation experiment results show that the introduced method achieves good accurate recognition rate in terms of a little features as reference.

关 键 词：信号处理 特征选择 相像系数 小波包变换 雷达辐射源 

分 类 号：TN957[电子电信—信号与信息处理] O235[电子电信—信息与通信工程]