%0 Journal Article
%T A Study of Identifiability for Blind Signal Separation via Nonorthogonal Joint Diagonalization<br>非正交联合对角化盲分离算法的可辨识性研究
%A Zhang Yan-liang
%A Lou Shun-tian
%A Zhang Wei-tao
%A <br>张延良
%A 楼顺天
%A 张伟涛
%J 电子与信息学报
%D 2010
%I 
%X Based on the uniqueness condition of the solution of Nonorthogonal Joint Diagonalization (NJD), the identifiability for Blind Signal Separation (BSS) is analyzed. Firstly, it is proved that the target matrices consisting of Second-Order Statistics (SOS) or higher-order cumulant are diagonalizable, so the problem of BSS can be solved by NJD. The uniqueness condition for NJD is that the vectors consisting of diagonal elements in the same position of diagonal matrix are pairwise linearly independent. From this...
%K Signal processing
%K Blind Signal Separation (BSS)
%K Joint diagonalization
%K Identifiability
%K Uniqueness condition
%K Higher-order cumulant<br>信号处理
%K 盲信源分离
%K 联合对角化
%K 可辨识性
%K 唯一存在条件
%K 高阶累积量
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=9D3707CD8479791FD212AEB5788A2236&yid=140ECF96957D60B2&vid=9971A5E270697F23&iid=94C357A881DFC066&sid=63025EFC6CC49145&eid=A50445FB05D4B1A0&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=0&reference_num=15