CAJ | 학술논문

空中目标旋转部件对雷达回波有调制作用。将回波时域幅度调制信息的幅度偏差系数作为调制特征，首先利用仿真数据分析了固定翼飞机目标和直升机飞机目标的差异，随后提出了一种最近邻分类器的设计方法，最后利用实测数据对目标进行分类，取得了较高的识别率。与支持向量机的算法相比，该分类器算法复杂度低，计算量小，识别率高，在工程上可以选用这种方法对两类目标进行分类识别。
공중목표선전부건대뢰체회파유조제작용。장회파시역폭도조제신식적폭도편차계수작위조제특정，수선이용방진수거분석료고정익비궤목표화직승궤비궤목표적차이，수후제출료일충최근린분류기적설계방법，최후이용실측수거대목표진행분류，취득료교고적식별솔。여지지향량궤적산법상비，해분류기산법복잡도저，계산량소，식별솔고，재공정상가이선용저충방법대량류목표진행분류식별。
The rotating components of aerial target can have modulation effect on radar echo. Taking the rate deviation coefficient as a modulation characteristic,the differences between fixed-wing aircrafts and helicopter aircrafts are analyzed with simulation data. A nearest neighbor classifier method is proposed. The targets are classified by using the measured data,and a higher recognition rate is obtained. In contrast with the support vector machine algorithm,the proposed method bears low complexity,less computation and high recognition rate. It can be used to classify two types of targets in engineering project.