基于似P范数FOCUSS的稀疏信号盲分离  

Blind Sparse Source Separation Based on P-Norm Like Diversity Measure of FOCUSS

作　　者：马艳荣[1] 马丽艳[1] 张玉洁[1] 

机构地区：[1]中国地质大学数理学院,武汉430074

出　　处：《工程地球物理学报》2007年第4期287-290,共4页Chinese Journal of Engineering Geophysics

基　　金：国家自然科学基金(60672049)资助项目;中国地质大学研究生学术创新与探索基金资助项目

摘　　要：把似P范数FOCUSS方法应用于稀疏信号盲分离中,采用k均值聚类算法来估计混合矩阵;然后利用似P范数FOCUSS方法来求解具有线性约束优化问题的稀疏源信号,从而给出了一种基于似P范数FOCUSS方法的稀疏信号盲分离算法。该算法计算量小,精度较高。仿真结果表明该算法是有效的,具有良好的分离性能。　In this paper,we propose a blind sparse source separation algorithm by using P-norm like diversity measure of FOCUSS.The proposed algorithm first estimates the mixied matrix by using the k-means clustering algorithm.Then P-norm like diversity measure of FOCUSS is applied to the linearly constrained optimization problem for recovering the sparse sources.Finally,a blind Sparse Source Separation Based on P-norm like diversity measure of FOCUSS algorithm is obtained.The presented algorithm is characterized by high accuracy and less computation.Simulation results illustrate the efficiency and the good performance of the algorithm.

关 键 词：稀疏 盲分离 似P范数FOCUSS 

分 类 号：P628[天文地球—地质矿产勘探]