摘要
针对传统雷达辐射源识别算法在当前高密度信号环境下进行识别时,存在实时性差、识别准确率低、鲁棒性不强的问题,提出了一种基于AdaBoost和决策树的辐射源识别算法。首先通过信息增益构建单层决策树;然后利用AdaBoost算法对弱分类器进行训练,得到强分类器;最后通过强分类器对测试数据进行识别,得到识别结果。仿真结果表明,利用该方法识别参数误差10%的测试数据,识别准确率能够达到93.78%,时间消耗低于1.5s,具备良好的识别效果。
Aiming at the problem of poor real-time performance,low recognition accuracy and poor robustness when the traditional radar emitter recognition algorithm is used in the current high density signal environment,a radar source recognition algorithm based on AdaBoost and Decision Tree is proposed. First,the decision tree is constructed by the information gain. Then the weak classifier is trained by using the AdaBoost algorithm,and the strong classifier is obtained. Finally,the strong classifier is used to identify the test data,and the final recognition result is obtained. Simulation results show that using this method to identify the test data with parameter error of 10%,the recognition accuracy can reach 93.78% and the time consumption is less than 1.5 s,with good recognition effect.
作者
唐晓婧
陈维高
席龙飞
慈言海
TANG Xiao-jing;CHEN Wei-gao;XI Long-fei;CI Yan-hai(Space Engineering University,Beijing 101416,China;Unit 78092 of PLA,Chengdu 610036,China;Shenyang Aircraft Company Military Representative Office of PLA,Shenyang 011034,China)
出处
《电子信息对抗技术》
2018年第4期16-20,58,共6页
Electronic Information Warfare Technology
