Unsupervised signal separation: a study on the applicability of Generative Adversarial Networks and on nonlinear models based on the Choquet Integral

• Grant number: 20/01089-9
• Support Opportunities: Regular Research Grants
• Start date: August 01, 2020
• End date: July 31, 2022
• Field of knowledge: Engineering - Electrical Engineering - Telecommunications
• Principal Investigator: Leonardo Tomazeli Duarte
• Grantee: Leonardo Tomazeli Duarte
• Host Institution: Faculdade de Ciências Aplicadas (FCA). Universidade Estadual de Campinas (UNICAMP). Limeira , SP, Brazil

Abstract

Blind source separation (BSS) refers to the task of recovering a set of source signals in an unsupervised fashion, that is, by only considering a set of mixtures of these sources. This field, which has been extensively studied in signal processing and fields related to data analysis, encompasses a wide range of applications, from the separation of biomedical signals to feature extraction in the context of machine learning. In this project, we address a challenging problem in BSS: the case of nonlinear mixtures. Our main aim is to develop BSS methods for novel mixing models. In a first moment, we shall investigate mixing models based on the Choquet integral. Our motivation comes from the fact that the parameters of the Choquet integral allow one to quantify the contributions of each attribute individually as well as of coalitions of them; such a feature has been pursued in the search for interpretable nonlinear models. In a second moment, we shall study the applicability of generative adversarial networks (GAN) in BSS. These networks have been applied in the context of unsupervised learning and provide a high degree of flexibility, which can be useful in BSS problems. We will assess the proposed methods by considering real applications in two different domains: separation of chemical signals and image separation. Moreover, we shall apply our proposal in the problem of searching disentangled representations of data, an emerging topic in the field of machine learning. (AU)

Scientific publications

(10)

(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)

PELISSARI, RENATA; ABACKERLI, ALVARO JOSE; DUARTE, LEONARDO TOMAZELI. Choquet capacity identification for multiple criteria sorting problems: A novel proposal based on Stochastic Acceptability Multicriteria Analysis. APPLIED SOFT COMPUTING, v. 120, p. 18-pg., 2022-05-01. (20/01089-9, 20/09838-0)

MORAES, CAROLINE P. A.; SALDANHA, JULIANA; NEVES, ALINE; FANTINATO, DENIS G.; ATTUX, ROMIS; DUARTE, LEONARDO TOMAZELI; IEEE. An SOS-Based Algorithm for Source Separation in Nonlinear Mixtures. 2021 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), v. N/A, p. 5-pg., 2021-01-01. (20/01089-9)

PELISSARI, RENATA; DUARTE, LEONARDO TOMAZELI. SMAA-Choquet-FlowSort: A novel user-preference-driven Choquet classifier applied to supplier evaluation. EXPERT SYSTEMS WITH APPLICATIONS, v. 207, p. 15-pg., 2022-07-08. (20/01089-9, 18/23447-4)

CAMPELLO, BETANIA SILVA CARNEIRO; DUARTE, LEONARDO TOMAZELI; ROMANO, JOAO MARCOS TRAVASSOS. Exploiting temporal features in multicriteria decision analysis by means of a tensorial formulation of the TOPSIS method. COMPUTERS & INDUSTRIAL ENGINEERING, v. 175, p. 10-pg., 2022-12-21. (20/01089-9)

DE OLIVEIRA, HENRIQUE EVANGELISTA; DUARTE, LEONARDO TOMAZELI; TRAVASSOS ROMANO, JOAO MARCOS. Identification of the Choquet integral parameters in the interaction index domain by means of sparse modeling. EXPERT SYSTEMS WITH APPLICATIONS, v. 187, JAN 2022. (20/01089-9)

PELISSARI, RENATA; ALENCAR, PAULO S.; BEN AMOR, SARAH; DUARTE, LEONARDO TOMAZELI; XAVIER-JUNIOR, JC; RIOS, RA. The Use of Multiple Criteria Decision Aiding Methods in Recommender Systems: A Literature Review. INTELLIGENT SYSTEMS, PT I, v. 13653, p. 15-pg., 2022-01-01. (20/01089-9, 20/09838-0)

ABACKERLI, ALVARO JOSE; PELISSARI, RENATA; DUARTE, LEONARDO TOMAZELI. Validation of a Maturity Model for Applied R & D: Adding Value to Business. IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT, v. N/A, p. 17-pg., 2023-06-09. (20/01089-9, 20/09838-0)

PELEGRINA, GUILHERME DEAN; DUARTE, LEONARDO TOMAZELI; GRABISCH, MICHEL; ROMANO, JOAO MARCOS TRAVASSOS. Dealing with redundancies among criteria in multicriteria decision making through independent component analysis. COMPUTERS & INDUSTRIAL ENGINEERING, v. 169, p. 19-pg., 2022-04-26. (20/01089-9, 17/23879-9, 20/09838-0, 16/21571-4)

PELEGRINA, GUILHERME D.; BROTTO, RENAN D. B.; DUARTE, LEONARDO T.; ATTUX, ROMIS; ROMANO, JOAO M. T.; IEEE. Analysis of Trade-offs in Fair Principal Component Analysis Based on Multi-objective Optimization. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), v. N/A, p. 8-pg., 2022-01-01. (20/09838-0, 19/20899-4, 20/01089-9, 20/10572-5, 21/11086-0)

CAMPELLO, BETANIA SILVA CARNEIRO; DUARTE, LEONARDO TOMAZELI; ROMANO, JOAO MARCOS TRAVASSOS. Dealing with multi-criteria decision analysis in time-evolving approach using a probabilistic prediction method. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, v. 116, p. 11-pg., 2022-10-06. (20/01089-9, 20/09838-0)