Title :
Nonlinear signal separation for multinonlinearity constrained mixing model
Author :
Gao, P. ; Woo, W.L. ; Dlay, S.S.
Author_Institution :
Sch. of Electr., Univ. of Newcastle upon Tyne
fDate :
5/1/2006 12:00:00 AM
Abstract :
In this letter, a new type of nonlinear mixture is derived and developed into a multinonlinearity constrained mixing model. The proposed signal separation solution integrates the Theory of Series Reversion with a polynomial neural network whereby the hidden neurons are spanned by a set of mutually reversed activation functions. Simulations have been undertaken to support the theory of the proposed scheme and the results indicate promising performance
Keywords :
neural nets; polynomials; source separation; transfer functions; hidden neurons; multinonlinearity constrained mixing model; mutually reversed activation functions; nonlinear signal separation; polynomial neural network; series reversion theory; Classification algorithms; Data mining; Face detection; Handwriting recognition; Machine learning; Neural networks; Pattern recognition; Source separation; Support vector machine classification; Support vector machines; Adaptive signal estimation; blind separation; independent component analysis (ICA); series reversion; Algorithms; Artificial Intelligence; Computer Simulation; Information Storage and Retrieval; Models, Statistical; Neural Networks (Computer); Nonlinear Dynamics; Pattern Recognition, Automated; Principal Component Analysis; Systems Theory;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2006.873288
