基于特征加权与SVM的雷达有源干扰分类技术  

A Radar Active Jamming Sorting Based on Feature Weighted and Support Vector Machine

作　　者：唐翥[1] 张兵[1] 李广强[1] 沈浩浩[1] 

机构地区：[1]空军预警学院,武汉430019

出　　处：《火力与指挥控制》2014年第5期114-116,共3页Fire Control & Command Control

摘　　要：为了有效提高雷达有源干扰分类正确率,提出一种基于特征加权与支持向量机的分类方法。针对分类过程中各信号特征参数对信号分类的重要度不同,引入特征加权的概念。利用灰色关联分析方法求取各特征权重,避免一些弱特征对分类结果产生较大影响。最后利用支持向量机分类器,对雷达有源干扰信号进行了分类识别。通过仿真实验证明,该方法可以有效提高雷达有源干扰信号类型的识别率,具有很好的通用性。In order to improve the the active jamming sorting accuracy effectively,a sorting method based on feature weighted and support vector machine is proposed. The feature weighting concept according to the different importance degree of each signal feature parameters to signal classification in the process is introduced. Using the gray relational analysis to obtain the weight of each feature,and some weak characteristics for the huge impact on the classification results are avoided. Finally,using support vector machine classifier,the active radar interference signal is classified and identified. Simulation experiments show that this method can improve the recognition rate of the radar active interference signal type effectively.

关 键 词：向量机 特征加权 有源干扰 分类 

分 类 号：TJ95[兵器科学与技术—武器系统与运用工程]