Title :
Constraint Setting in Constrained ICA
Author :
Guangyun Wang ; Langbo Qiu ; Gang Wang ; Zhengzhi Wang
Author_Institution :
Coll. of Mechatronics Eng. & Autom., Nat. Univ. of Defense Technol., Changsha
Abstract :
Constraint setting is a crucial part in constrained independent component analysis (CICA) and directly affects the result of CICA´s application in blind source separation (BSS), etc.. In this paper, constraints are sorted into three types. Based on numerical optimistic algorithms, the corresponding formula and the setting method for each type are presented, and the adjustable parameter in the formula of constraints is emphasized. Experimental results show that constraints in CICA can be set reasonably and effectively by the proposed methods
Keywords :
blind source separation; independent component analysis; BSS; blind source separation; constrained ICA; constrained independent component analysis; setting method; Automation; Blind source separation; Constraint optimization; Educational institutions; Feature extraction; Independent component analysis; Mechatronics; Source separation; Speech; Vectors;
Conference_Titel :
Signal Processing, 2006 8th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9736-3
Electronic_ISBN :
0-7803-9736-3
DOI :
10.1109/ICOSP.2006.345751
