欠定盲源分离混合矩阵估计的张量分解方法  

Estimation of underdetermined mixture matrix in blind source separation based on tensor decomposition

作　　者：张延良[1,2] 楼顺天[1,3] 张伟涛[1] 

机构地区：[1]西安电子科技大学电子工程学院,陕西西安710071 [2]河南理工大学计算机科学与技术学院,河南焦作454001 [3]超高速电路设计与电磁兼容教育部重点实验室,陕西西安710071

出　　处：《系统工程与电子技术》2011年第8期1703-1706,共4页Systems Engineering and Electronics

基　　金：国家自然科学基金(61074102);河南理工大学青年基金重点项目(Q2011-50)资助课题

摘　　要：欠定盲源分离混合矩阵的估计可以转化为三阶张量的标准分解问题。为解决现有标准分解算法运算复杂度高、所需时间长的缺点,引入塔克分解先把张量压缩为较低维的核张量,塔克分解因子可通过原张量mode-3矩阵的左奇异向量求得。然后运用交替最小二乘对该核张量进行标准分解,即可得到混合矩阵的估计。仿真结果表明,所提方法不仅可以达到与现有算法同样好的估计精度,而且具有更低的运算复杂度,运算时间较现有算法降低46.44%~76.28%。The underdetermined mixture matrix in blind source separation can be obtained by canonical decomposition of the three-order tensor.In order to overcome the flaw of high computational complexity and long running time of existing canonical decomposition algorithm,the tensor is compressed as lower order core one using tucker decomposition.The factor of tucker decomposition can be obtained by left singular value of the original tensor＇s mode-3 matrix.The mixture matrix can be estimated by the alternating least square based canonical decomposition of the core tensor.Simulation results show that the proposed algorithm has much lower computational complexity with no performance loss and its operation time reduces 46.44%~76.28% compared with the existing algorithm.

关 键 词：盲信源分离 欠定混合 张量 标准分解 塔克分解 

分 类 号：TN911.7[电子电信—通信与信息系统]