DocumentCode :
3593413
Title :
Improved algorithm for independent component analysis
Author :
Ce, Ji ; Yang, Yu ; Peng, Yu
Author_Institution :
Dept. of Inf. Sci. & Eng., Northeast Univ., Shenyang, China
Volume :
2
fYear :
2010
Abstract :
Firstly, this paper introduces the basic theory of Independent Component Analysis (ICA) and the FastICA algorithm. In order to increase the algorithm convergence rate and reduce the running time, the paper amends the Newton´s iteration method and gives an improved algorithm of independent component analysis-the Newton´s iteration method with fifth-order convergence. The simulation result of the image signal separation shows that the improved algorithm have the same separate effect as conventional FastICA algorithm and can reduce the times of iterations and the running time significantly. Furthermore, the improved algorithm can also increase the convergence rate and operation efficiency.
Keywords :
Newton method; blind source separation; convergence of numerical methods; independent component analysis; FastICA algorithm; Newton iteration method; convergence rate; image signal separation; independent component analysis; Algorithm design and analysis; Convergence; Independent component analysis; Information science; Random variables; Signal analysis; Source separation; Statistics; Fixed-point algorithm; Independent component analysis; Negentropy; Newton´s iteration method;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Future Computer and Communication (ICFCC), 2010 2nd International Conference on
Print_ISBN :
978-1-4244-5821-9
Type :
conf
DOI :
10.1109/ICFCC.2010.5497485
Filename :
5497485
Link To Document :
بازگشت