On the Performance Indices of ICA and Blind Source Separation



: Nordhausen K, Ollila E, Oja H

: IEEE

: IEEE International Workshop on Signal Processing Advances in Wireless Communications

: New York, NY

: 2011

: IEEE International Workshop on Signal Processing Advances in Wireless Communications

: 2011 IEEE 12th International Workshop on Signal Processing Advances in Wireless Communications

: SPAWC 2011: 2011 IEEE 12TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS

: 486

: 490

: 5

: 978-1-4244-9332-6

DOI: https://doi.org/10.1109/SPAWC.2011.5990458(external)


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.



Last updated on 2024-26-11 at 15:24