Title :
Blind Source Separation Based on Chaotic Immune Genetic Algorithm with High-order Cumulate
Author :
Wang, Kun ; Zhang, Wei
Author_Institution :
Xi´´an Aerotech. Coll., Xi´´an
Abstract :
A blind source separation method based on chaotic immune genetic algorithm (CIGA) is proposed. The first step performs pretreatment of mixed signal, which mainly finishes whitening and centering by eigenvalue decomposition. The second step performs separation of sources and estimate of separate matrix. The separate matrix is updated by CIGA and high order statistics, where object function is based on the transformation of high order statistics of Kurtosis. The applicability of proposed method for blind source separation is demonstrated by simulation.
Keywords :
blind source separation; eigenvalues and eigenfunctions; genetic algorithms; matrix algebra; statistical analysis; blind source separation; chaotic immune genetic algorithm; eigenvalue decomposition; high order statistics; separate matrix; Blind source separation; Chaos; Chaotic communication; Eigenvalues and eigenfunctions; Erbium; Genetic algorithms; Signal processing; Signal processing algorithms; Source separation; Statistics; Blind source separation; Chaotic immune genetic algorithm (CIGA); Eigenvalue decomposition; Kurtosis;
Conference_Titel :
Vehicular Electronics and Safety, 2006. ICVES 2006. IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0759-1
Electronic_ISBN :
1-4244-0759-1
DOI :
10.1109/ICVES.2006.371570
