TY - GEN

T1 - On an adaptive ICA method with application to biomedical image analysis

AU - Hong, B. M.

AU - Calhoun, V. D.

PY - 2004/12/27

Y1 - 2004/12/27

N2 - Conventional ICA algorithms typically model the probability density functions of the underlying sources as highly kurtotic or symmetric. However, when source data violate the assumptions (e.g., low kuitosis), the conventional ICA methods might not work well. Adaptive modeling of the underlying sources thus becomes an important issue for ICA applications. This paper proposes the Log Weibull model to represent skewed distributed sources within the Infomax framework and further introduces an adaptive ICA method. The central idea is to use a two-stage separation process: 1) Conventional ICA used for all channel sources to obtain initial independent source estimates; 2) source density estimate-based nonlinearities adaptively used for the "refitting" separation to all channel sources. The ICA algorithm is based on flexible nonlinearities of density matched candidates. Our simulations demonstrate the effectiveness of this approach.

AB - Conventional ICA algorithms typically model the probability density functions of the underlying sources as highly kurtotic or symmetric. However, when source data violate the assumptions (e.g., low kuitosis), the conventional ICA methods might not work well. Adaptive modeling of the underlying sources thus becomes an important issue for ICA applications. This paper proposes the Log Weibull model to represent skewed distributed sources within the Infomax framework and further introduces an adaptive ICA method. The central idea is to use a two-stage separation process: 1) Conventional ICA used for all channel sources to obtain initial independent source estimates; 2) source density estimate-based nonlinearities adaptively used for the "refitting" separation to all channel sources. The ICA algorithm is based on flexible nonlinearities of density matched candidates. Our simulations demonstrate the effectiveness of this approach.

UR - http://www.scopus.com/inward/record.url?scp=10444275325&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10444275325&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:10444275325

SN - 0780384075

T3 - 2004 7th International Conference on Signal Processing Proceedings, ICSP

SP - 2247

EP - 2250

BT - 2004 7th International Conference on Signal Processing Proceedings, ICSP

T2 - 2004 7th International Conference on Signal Processing Proceedings, ICSP

Y2 - 31 August 2004 through 4 September 2004

ER -