Vous êtes ici : GIPSA-lab > Animation > Soutenances

Blind Source Separation in Nonlinear Mixtures

Soutenance de la thèse de Bahram EHSANDOUST le 30/04/2018 à 11:30:00

Lieu :Kahroba - EE Department, Sharif University of Technology, Tehran, Iran

Ecole Doctorale :Electronique, electrotechnique, automatique, traitement du signal (eeats)
Structure de rattachement :
Directeur de thèse : Christian JUTTEN


Financement(s) :


Date d'entrée en thèse: 01/11/2014
Date de soutenance: 30/04/2018

Composition du jury :M. Farrokh Marvasti, Professeur, Universiteì de Technologie de Sharif
M. Yannick Deville, Professeur, Universiteì Paul Sabatier Toulouse 3
M. Reza Sameni, HDR, Universiteì de Shiraz
M. Mohammad Bagher Shamsollahi, Professeur, Universiteì de Technologie de Sharif
M. Hamid Soltanian-Zadeh, Professeur, Universiteì de Teìheìran

Résumé:In this study, nonlinear BSS problem is tackled using a novel approach utilizing temporal information of the signals. The original idea followed in this purpose is to study a linear time-varying source separation problem deduced from the initial nonlinear problem by derivations. It is shown that already-proposed counter-examples showing inefficiency of Independent Component Analysis (ICA) for nonlinear mixtures, loose their validity, considering independence in the sense of stochastic processes instead of simple random variables. Based on this approach, both nice theoretical results and algorithmic developments are provided. Even though these achievements are not claimed to be a mathematical proof for the separability of nonlinear mixtures, it is shown that given a few assumptions, which are satisfied in most practical applications, they are separable. Moreover, nonlinear BSS for two useful sets of source signals is also addressed: (1) spatially sparse sources and (2) Gaussian processes. Distinct BSS methods are proposed for these two cases, each of which has been widely studied in the literature and has been shown to be quite beneficial in modeling many practical applications.

GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - 33 (0)4 76 82 71 31