DocumentCode :
2841381
Title :
On the performance indices of ICA and blind source separation
Author :
Nordhausen, Klaus ; Ollila, Esa ; Oja, Hannu
Author_Institution :
Sch. of Health Sci., Univ. of Tampere, Tampere, Finland
fYear :
2011
fDate :
26-29 June 2011
Firstpage :
486
Lastpage :
490
Abstract :
For assessing the separation performance (quality and accuracy) of ICA estimators, several performance indices have been introduced in the literature. The purpose of this note is to outline, review and study the properties of performance indices as well as propose some new ones. Special emphasis is put on the properties that such performance indices ought to satisfy. We categorize the indices in two separate groups that differ in the approaches they deploy in measuring the closeness of the achieved source separation to the ideal case and point out some inherent relations between the indices in these categories.
Keywords :
blind source separation; estimation theory; independent component analysis; ICA estimator; blind source separation; independent component analysis estimator; performance index; Correlation; Independent component analysis; Indexes; Performance analysis; Robustness; Signal processing; Signal processing algorithms; blind source separation; correlation; independent component analysis; performance index; robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Advances in Wireless Communications (SPAWC), 2011 IEEE 12th International Workshop on
Conference_Location :
San Francisco, CA
ISSN :
1948-3244
Print_ISBN :
978-1-4244-9333-3
Electronic_ISBN :
1948-3244
Type :
conf
DOI :
10.1109/SPAWC.2011.5990458
Filename :
5990458
Link To Document :
بازگشت