自适应组合型盲源分离算法及其优化方案  

Adaptive Combination Algorithm and Its Modified Scheme for Blind Source Separation

作　　者：欧世峰[1] 高颖[1] 赵晓晖[2] 

机构地区：[1]烟台大学光电信息科学技术学院,烟台264005 [2]吉林大学通信工程学院,长春130012

出　　处：《电子与信息学报》2011年第5期1243-1247,共5页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61005021);高等学校博士学科点基金(200801830037)资助课题

摘　　要：该文通过引入滑动参数来自适应地组合两个不同步长的盲源分离系统,提出了一种自适应组合型盲源分离算法,其可在两个系统并向运行的同时,自适应地选取最优的分离系统进行在线分离。文中推导了滑动参数的自适应更新规则,并针对算法存有的问题,提出了具体优化方案。平稳和非平稳环境下的仿真实验表明了算法的优良性能。By adaptively combining two separation systems with different step sizes,an adaptive combination algorithm is proposed for blind source separation.A smoothing parameter is used to adjust the proportion of the two systems in an attempt to put together the best properties of them.The adaptive updating rule for the smoothing parameter is obtained,and in view of the insufficiency of the proposed method,a concrete modified scheme is also presented.Experimental results demonstrate the good performance of the proposed approaches in stationary and non-stationary conditions.

关 键 词：信号处理 盲源分离 步长 自适应 滑动参数 

分 类 号：TN911.7[电子电信—通信与信息系统]