Novel methods in multicreria decision analysis by means of advanced signal processing techniques

• Grant number: 15/16325-1
• Support Opportunities: Regular Research Grants
• Start date: October 01, 2015
• End date: September 30, 2017
• Field of knowledge: Engineering - Production Engineering - Operational Research
• 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

A central problem in multi-criteria decision analysis is to develop quantitative methods that sort a set of alternatives by taking into account different decision criteria. These methods have been intensively applied in problems from different domains. However, despite the impressive results obtained in multi-criteria decision analysis and its central role in the area of operations research, there are still relevant issues to be investigated. In the current project, some of these points will be addressed. Most notably, we shall develop novel methods that are able to provide an efficient sorting even in the case of interacting criteria, which often arises in practical scenarios. Furthermore, we shall investigate the problem of multi-criteria decision aiding in the case of missing data. Finally, the problem of group decision will be addressed; we aim at obtaining methods that do not suffer from bias caused by the presence of a dominant sub-group people having similar point of views. A central innovative aspect of this project is related to the tools that will be considered herein. Differently from classical approaches, we shall integrate advanced signal processing techniques, such as independent component analysis, low-rank modeling and tensor-based data representation, to the existing methods. Numerical experiments and theoretical experiments will be carried out in order to assess the developed solutions vis-à-vis the classical solutions found in the area. (AU)

Scientific publications

(5)

(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)

DUARTE, LEONARDO TOMAZELI. A Novel Multicriteria Decision Aiding Method Based on Unsupervised Aggregation via the Choquet Integral. IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT, v. 65, n. 2, p. 293-302, APR 2018. (15/16325-1)

PELEGRINA, GUILHERME DEAN; ATTUX, ROMIS; DUARTE, LEONARDO TOMAZELI. Application of multi-objective optimization to blind source separation. EXPERT SYSTEMS WITH APPLICATIONS, v. 131, p. 60-70, OCT 1 2019. (14/27108-9, 15/16325-1)

VIGNERON, VINCENT; DUARTE, LEONARDO TOMAZELI; TICHAVSKY, P; BABAIEZADEH, M; MICHEL, OJJ; THIRIONMOREAU, N. Toward Rank Disaggregation: An Approach Based on Linear Programming and Latent Variable Analysis. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2017), v. 10169, p. 9-pg., 2017-01-01. (15/16325-1)

PELEGRINA, GUILHERME D.; DUARTE, LEONARDO T.. A Multi-Objective Approach for Post-Nonlinear Source Separation and Its Application to Ion-Selective Electrodes. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, v. 65, n. 12, p. 2067-2071, DEC 2018. (15/16325-1, 14/27108-9)

PEREIRA-FERRERO, VANESSA HELENA; LEWIS, THEODORE GYLE; PEREIRA FERRERO, LUCIANE GRAZIELE; DUARTE, LEONARDO TOMAZELI. Complex Networks Models and Spectral Decomposition in the Analysis of Swimming Athletes' Performance at Olympic Games. FRONTIERS IN PHYSIOLOGY, v. 10, SEP 3 2019. (15/16325-1)