On the blind source separation of nonlinear mixtures

Alexandre Miccheleti Lucena, Kenji Nose Filho, Ricardo Suyama

DOI: 10.14209/sbrt.2024.1571036896

Evento: XLII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2024)

Keywords: blind source separation nonlinear mixtures independent component analysis nonlinear regression

Abstract

In this paper we analyze the method proposed by Ehsandoust et. al for the blind source separation of nonlinear mixtures. Interestingly, the initially proposed method based on deriving the observed signals, performing an adaptive linear blind source separation, smooth the coefficients of the separation matrices and integrate the solution can be reduced, in some cases, by simply performing an adaptive linear blind source separation and smooth the coefficients of the separation matrices. Also, we extend the results for different sets of signals such as autoregressive signals and propose an alternative method, based on a General Regression Neural Network, for the smoothing of the Jacobian matrix.

Download