基于模糊聚类的信源个数检测新算法  

A New Source Number Detection Algorithm Based on Fuzzy Clustering

作　　者：包志强[1] 韩冰[2] 吴顺君[1] 

机构地区：[1]西安电子科技大学雷达信号处理国家重点实验室,西安710071 [2]西安电子科技大学电子工程学院,西安710071

出　　处：《电子与信息学报》2006年第10期1761-1765,共5页Journal of Electronics & Information Technology

基　　金：国家重点实验室基金(J14203220033)资助课题

摘　　要：信源个数检测方法的研究是目前阵列信号处理领域的一个研究热点和重点,它的测量精度直接影响到许多高分辨测向算法的精确度。然而现有的检测方法对于不同的噪声环境非常敏感;而且随着快拍数的减少性能迅速下降。基于以上的限制与缺陷,该文提出了一种基于模糊c均值聚类的信源个数检测方法。在两种不同噪声环境下的仿真结果表明该方法的有效性和鲁棒性。The research of source number detection is still open and challenge issue in array signal processing. The accurate estimation may be very essential to those high resolution direction finding algorithms. However, the traditional methods are sensitive to different noise fields and the performances of them are degraded in short snapshots. To overcome these drawbacks, an effective, accurate, robust detection method of the number of sources is proposed using the fuzzy-c-means clustering algorithm. The simulation results with two noise fields demonstrate the effectiveness and robustness of the proposed scheme.

关 键 词：阵列信号处理 模糊聚类 信源个数 

分 类 号：TN911.23[电子电信—通信与信息系统]