Truncated exponential nonlinearities for independent component analysis

Muhammad Tufail, Masahide Abe, Masayuki Kawamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes exponential type nonlinearities in order to blindly separate instantaneous mixtures of signals with mixed kurtosis signs. These nonlinear functions are applied only in a certain range around zero in order to ensure that the relative gradient algorithm remains locally stable. The proposed truncated nonlinearities neutralize the effect of outliers while the higher order terms inherently present in the exponential function result in fast convergence especially for signals with bounded support. By varying the truncation threshold, signals with both sub-Gaussian and super-Gaussian probability distributions can be separated. Furthermore, when the sources consist of signals with mixed kurtosis signs we propose to estimate the characteristic function online in order to classify the signals as sub-Gaussian or super-Gaussian and consequently choose an adequate value of the truncation threshold. Some computer simulations are presented to demonstrate the effectiveness of the proposed idea.

Original languageEnglish
Title of host publicationProceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005
PublisherIEEE Computer Society
Pages381-384
Number of pages4
ISBN (Print)0780392663, 9780780392663
DOIs
Publication statusPublished - 2005 Jan 1
Event2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 - Hong Kong, China
Duration: 2005 Dec 132005 Dec 16

Publication series

NameProceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005
Volume2005

Other

Other2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005
CountryChina
CityHong Kong
Period05/12/1305/12/16

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Truncated exponential nonlinearities for independent component analysis'. Together they form a unique fingerprint.

  • Cite this

    Tufail, M., Abe, M., & Kawamata, M. (2005). Truncated exponential nonlinearities for independent component analysis. In Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 (pp. 381-384). [1595426] (Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005; Vol. 2005). IEEE Computer Society. https://doi.org/10.1109/ispacs.2005.1595426