一种基于近类点和模糊点的未知雷达信号分选算法

摘要

Aiming at the problem that the algorithm of density-based spatial clustering of applications with noise（DBSCAN） can not find the radar signal density distribution is not even,this paper presents a new clustering algorithm based on close-category and fuzzy points.This method performs clustering by means of the distribution characteristics of data in the same radar,through confirming close-category points and fuzzy points,it can sort the radar signals of different density distribution,which is adapted to sort unknown radar signals.The algorithm test shows that the proposed method is not sensitive to noise and can find the clustering with arbitrary shapes,size and densities.%针对基于密度聚类（DBSCAN）算法不能发现雷达信号密度分布不均匀的缺陷,提出了一种基于近类点和模糊点的聚类方法。该方法利用同一部雷达数据的分布特性进行聚类,通过确定近类点和模糊点以达到分选不同密度分布的雷达信号,适用于未知雷达信号的分选。算法测试表明,该方法对噪声不敏感,能够发现任意形状、大小和密度的聚类。