摘要
随着电磁辐射源个体之间差异的减小,传统的模板比对法已经难以完成对辐射源的个体识别任务。为了更好的识别个体之间的微小差异,提高复杂电磁环境中辐射源个体识别的成功率,从工程应用角度出发,提出先使用Fisher判别率进行特征预选,再使用主成份分析进行降维,最后使用支持向量机进行训练识别的辐射源个体识别方法,构建了可以识别辐射源威胁差异的分类器。仿真结果表明:该方法可以兼顾工程应用中识别正确率和识别速度的要求,对辐射源个体识别具有较好的应用价值。
The template contrast method is abated because of that the difference between different radiant points trails off.From the point of view of engineering application,this paper presents a specific emitter identification method.In order to identify the difference between different radiant points,first the Fisher＇s discriminate ratio is employed to select the effective features,and then the principle component analysis is done to reduce the feature dimension.Finally,the support vector machine is used to perform the identification.The simulation result shows that the method can give attention to both accuracy and speed of identification simultaneously,and is of better application value in the identification of different radiant points.
出处
《空军工程大学学报（自然科学版）》
CSCD
北大核心
2012年第1期28-32,共5页
Journal of Air Force Engineering University(Natural Science Edition)
基金
陕西省信息系统综合集成重点实验室基金资助项目(2011103)
关键词
辐射源个体识别
Fisher判别率
主成份分析
支持向量机
specific emitter identification
Fisher＇s discriminate ratio
principle component analysis
support vector machine
