空间相关噪声下信源个数的聚类检测算法  

Sources Detection Based on Clustering in Spatially Correlated Noise Fields

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,陕西西安710071 [2]西安电子科技大学电子工程学院,陕西西安710071

出　　处：《测试技术学报》2006年第5期444-450,共7页Journal of Test and Measurement Technology

基　　金：国家重点实验室基金资助项目(J14203220033)

摘　　要：针对空间相关噪声情况,利用两个独立阵列之间噪声不相关的特性,采用联合协方差矩阵的规范相关系数作为聚类特征,提出了一种基于模糊c均值聚类的信源个数检测方法.并详细分析了应用Fuzzy-c-M eans(FCM)聚类算法进行信源个数检测的3个问题:聚类的趋势、有效性和聚类中心的初始化.与经典算法相比,本文算法有较好的角度分辨力和检测性能.仿真结果证明了该方法的有效性和鲁棒性.To deal with the spatially correlated noise, a detection method based on Fuzzy-c-Means （FCM） clustering algorithm is proposed, which uses canonical correlation coefficients of the joint covariance matrix as the feature to be classified. Three crucial issues are discussed for the application of Fuzzy-c-Means method to the source-number detection. Compared with the classical methods, the presented algorithm has better performance and angular resolution. The simulation results demonstrate the effectiveness and robustness of the proposed scheme.

关 键 词：相关噪声 模糊聚类 信源个数 信源检测 阵列信号处理 

分 类 号：TN911.7[电子电信—通信与信息系统]