系统工程与电子技术 ›› 2019, Vol. 41 ›› Issue (2): 244-248.

• 电子技术 • 上一篇    下一篇

基于模糊C类均值聚类的信源数估计方法

刘赞, 陈西宏, 刘进, 刘强   

  1. 空军工程大学防空反导学院, 陕西 西安 710051
  • 出版日期:2019-01-25 发布日期:2019-01-24

Source number estimation method based on fuzzy C-means clustering

LIU Zan, CHEN Xihong, LIU Jin, LIU Qiang   

  1. Air and Missile Defense College, Air Force Engineering University, Xi’an 710051, China

  • Online:2019-01-25 Published:2019-01-24

摘要: 信源数估计的性能直接影响着高分辨测向的精度。为提高估计方法的性能,提出一种基于模糊C类均值(fuzzy Cmeans, FCM)聚类的信源数估计方法。在此方法中,信号的协方差阵的特征值及其差值,对协方差阵酉变换得到的盖氏圆半径及其差值作为FCM聚类过程中的样本指标。最终判断样本归属时,引入容错概率的概念。在接受一定程度容错的前提下,提高了算法的性能。在不同噪声类型下进行仿真的结果表明,所提出的信源数估计方法性能较好。

Abstract: Source number estimation directly affects the performance of high resolution direction of arrival. To improve the performance, this paper proposes a method based on fuzzy C-means(FCM) clustering. Eigenvalues of covariance matrix and the difference of them are utilized as the indices of targets. As well, radii of Gerschgorin disk based on unitary transform and the difference of them are also employed. To improve the performance of the proposed method, probability of fault tolerant is introduced. The simulations with different styles of noises indicate that it has a good performance on estimating source number.