Nonlinear Blind Source Separation for Statistically Dependent Sources

• Grant number: 15/23424-6
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: February 15, 2016
• End date: July 14, 2016
• Field of knowledge: Engineering - Electrical Engineering - Telecommunications
• Principal Investigator: Romis Ribeiro de Faissol Attux
• Grantee: Denis Gustavo Fantinato
• Supervisor: Christian Jutten
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Institution abroad: Université de Grenoble, France
• Associated to the scholarship: 13/14185-2 - New Methods for Adaptive Equalization Based on Information Theoretic Learning, BP.DR

Abstract

The nonlinear blind source separation (BSS) problem is a challenging research topic and, differently from the linear case, its development has not reached a general separation framework. Among the reported nonlinear models, we highlight two instances that are crucial for the present project: (i) post-nonlinear (PNL) mixtures and (ii) contexts of separation of colored sources using signal derivatives. In the former case, the assumption of mutual independence among sources can be suitable for solving the PNL problem, but the employment of criteria solely based on independence constrains the nonlinearities to be bijective. Hence, there emerges as an interesting possibility the use of other statistics, such as spatial and/or temporal dependencies, for the adoption of a larger set of nonlinear separation functions. For the second approach, if temporally colored sources are assumed, by computing derivatives of the mixtures, the nonlinear mixing process becomes linear and instantaneous, but time-varying. In that sense, by modeling the probability density function of the derivatives of the sources, a more robust criterion based on the matching of distributions can be applied. The project is intended to be developed at GIPSA-Lab, Grenoble, France, under the supervision of Prof. Christian Jutten, a pioneer in the linear and nonlinear BSS problems.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

FANTINATO, DENIS G.; DUARTE, LEONARDO T.; RIVET, BERTRAND; EHSANDOUST, BAHRAM; ATTUX, ROMIS; JUTTEN, CHRISTIAN; TICHAVSKY, P; BABAIEZADEH, M; MICHEL, OJJ; THIRIONMOREAU, N. Gaussian Processes for Source Separation in Overdetermined Bilinear Mixtures. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2017), v. 10169, p. 10-pg., 2017-01-01. (15/23424-6, 13/14185-2)

FANTINATO, DENIS G.; DUARTE, LEONARDO T.; ZANINI, PAOLO; RIVET, BERTRAND; ATTUX, ROMIS; JUTTEN, CHRISTIAN; TICHAVSKY, P; BABAIEZADEH, M; MICHEL, OJJ; THIRIONMOREAU, N. A Joint Second-Order Statistics and Density Matching-Based Approach for Separation of Post-Nonlinear Mixtures. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2017), v. 10169, p. 10-pg., 2017-01-01. (15/23424-6, 13/14185-2)

FANTINATO, DENIS G.; DUARTE, LEONARDO T.; DEVILLE, YANNICK; ATTUX, ROMIS; JUTTEN, CHRISTIAN; NEVES, ALINE. A second-order statistics method for blind source separation in post-nonlinear mixtures. Signal Processing, v. 155, p. 63-72, FEB 2019. (17/11488-5, 15/23424-6)