DocumentCode
2904826
Title
Correlation coefficient based on independent component analysis
Author
Falie, Dragos ; David, Livia
Author_Institution
Image Process. & Anal. Lab., Univ. Politeh. of Bucharest, Bucharest, Romania
fYear
2012
fDate
21-23 June 2012
Firstpage
59
Lastpage
62
Abstract
The proposed correlation coefficient better characterize the statistical independence of two random variables that are a linear mixture of two independent sources. This correlation coefficient can be calculated with analytical relations or with the known algorithms of independent components analysis (ICA). The value of the correlation coefficient is zero when the random variables are a statistically independent and it is one when these are fully dependent.
Keywords
independent component analysis; statistical analysis; ICA; correlation coefficient; independent component analysis; independent sources; linear mixture; random variables; statistical independence; Algorithm design and analysis; Correlation; Data structures; Gold; Independent component analysis; Random variables; USA Councils; BSS; ICA; blind separation of sources; correlation; statistical independence;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications (COMM), 2012 9th International Conference on
Conference_Location
Bucharest
Print_ISBN
978-1-4577-0057-6
Type
conf
DOI
10.1109/ICComm.2012.6262543
Filename
6262543
Link To Document