基于高斯-牛顿迭代的非正交联合对角化算法  

Improved fast non-orthogonal joint diagonalization algorithm based on Gauss-Newton iteration

作　　者：艾朝霞[1] 

机构地区：[1]榆林学院能源工程学院,陕西榆林719000

出　　处：《纺织高校基础科学学报》2014年第2期271-273,共3页Basic Sciences Journal of Textile Universities

基　　金：榆林学院青年科技基金项目(12YK31)

摘　　要：针对传统的分离算法因迭代次数过多而不能满足通信信号分离时对信号实时处理的要求,将最佳权矩阵引入到联合对角化准则中,提出了一种改进的基于"高斯-牛顿"迭代法的非正交联合对角化算法(WEDGE),提高了算法的分离性能和收敛速度.仿真结果验证了算法的有效性.Excessive iteration in traditional separation algorithms can not satisfy the real-time processing in communication signals separation. In order to solve this problem, optimum weight matrix is applied to joint diagonalization criterion, an improved non-orthogonal joint diagonalization algorithm based on Gauss-Newton iteration method is put forward, separation performance and the rate of convergence of the algorithm are improved. The simulation results demonstrate the effectiveness of the algorithm.

关 键 词：盲源分离 二阶统计量 联合对角化 高斯-牛顿迭代 最佳权矩阵 

分 类 号：TN911.23[电子电信—通信与信息系统]