Title :
A New Algorithm Estimating the Mixing Matrix for the Sparse Component Analysis
Author :
Zhang, Suxian ; Liu, Hailin ; Wen, Jiechang ; Chen, Weili
Author_Institution :
Fac. of Inf. Eng., Guangdong Univ. of Technol., Guangzhou, China
Abstract :
For the problem of Underdetermined Blind Source Separation (UBSS) under nonstrictly sparse condition, we propose a new algorithm to estimate mixing matrix. Firstly, a clustering prototype of orthogonal complement space is introduced; Secondly, a fuzzy EVD clustering method which combines fuzzy clustering and Eigenvalue Decomposition (EVD) is presented. Based on these two methods, the algorithm proposed in this paper is robust against noise without losing convergence speed.
Keywords :
blind source separation; eigenvalues and eigenfunctions; estimation theory; eigenvalue decomposition; fuzzy EVD clustering; mixing matrix estimation; nonstrictly sparse condition; sparse component analysis; underdetermined blind source separation; Algorithm design and analysis; Blind source separation; Clustering algorithms; Clustering methods; Convergence; Eigenvalues and eigenfunctions; Matrix decomposition; Noise robustness; Prototypes; Sparse matrices; Blind source separation; eigenvalue decomposition; fuzzy clustering; sparse component analysis;
Conference_Titel :
Computational Intelligence and Security, 2009. CIS '09. International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-5411-2
DOI :
10.1109/CIS.2009.251
