摘要: |
针对雷达信号分选中常见的聚类数目难确定、数据簇形状识别、异常数据敏感等问题,提出了基于NeiMu(Neighboring Mutually)的雷达信号聚类分选算法。该算法首先以信号脉冲为点、各点间的欧氏距离为线构建距离矩阵,然后在进行干扰数据剔除的情况下选定合适k值完成聚类矩阵的构建,最后采取遍历聚类矩阵的方法输出聚类结果,在删除无效的聚类后实现了雷达信号的聚类分选。通过仿真可知该算法在选取合适k值的情况下具有极高的正确率,证明了其有效性和可靠性。 |
关键词: 雷达信号分选 NeiMu聚类 干扰脉冲 |
DOI: |
|
基金项目:四川省科技计划项目(2018GZ0072,2018GZ0509);四川省科技计划省院省校合作项目(2018JZ0065) |
|
Clustering and Sorting of Radar Signals Based on NeiMu |
PENG Gang,DONG Jian,YUAN Xiao,WANG Xujiao |
(1.School of Electronic Information,Sichuan University,Chengdu 610064,China;3.Unit 77618 of PLA,Lhasa 850100,China;2.Department of Unmanned Aerial Vehicle,Army Engineering University Shijiazhuang Campus,Shijiazhuang 050003,China) |
Abstract: |
For the common problems in radar signal sorting,such as difficult to determine the number of clusters,shape recognition of data clusters,and sensitivity to abnormal data,a clustering sorting algorithm based on Neighboring Mutually(NeiMu) is proposed.Firstly,the distance matrix is constructed by taking the signal pulse as the point and the Euclidean distance between the points as the line.Then,the appropriate k value is selected to complete the construction of the clustering matrix under the condition of eliminating the interference data.Finally,the clustering result is output by traversing the clustering matrix.After eliminating the invalid clustering,the clustering of radar signals is realized.The simulation results show that the algorithm has a very high accuracy rate when the appropriate k value is selected,and prove its effectiveness and reliability. |
Key words: radar signal sorting NeiMu clustering interference pulse |