Sistemas de apoio à decisão em grupo multicritério : uma abordagem baseada em regras fuzzy

• Ano de defesa: 2009
• Autor(a) principal: Santos, Fábio José Justo dos
• Orientador(a): Camargo, Heloisa de Arruda
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos; Câmpus São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação - PPGCC
• Palavras-chave em Português: Inteligência artificial; Sistemas baseados em regras fuzzy; Sistemas de suporte de decisão; Processo decisório
• Palavras-chave em Inglês: Fuzzy Rules-Based System; Multi-criteria Decision Support Systems; Group Decision Making
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO
• Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/7064

The use of fuzzy logic and fuzzy sets theory applied to decision making process was initially proposed by Bellman and Zadeh (1970). Since then, the arisen of unstructured problems associated with multi-criteria characteristics and group decision making changed the way of dealing with these problems. The evolution of Decision Support Systems (DSS) allowed them, not only to provide data and information, but also to propose solutions to these problems. The goal of this work is to present a framework for the development of DSS that deal with Multi-Criteria Group Decision Making (MCGDM) problems through fuzzy rules. In this approach, we propose a method capable of automatically generating a Fuzzy Rule Base with multi-criteria characteristics for group decision making, that is, different influence degrees for each decider and different importance degrees assigned to each variable are considered in the model. This framework also contains a structural model of a Fuzzy System for Group Decision Support aiming at adding DSS characteristics found in literature to Fuzzy Systems. These characteristics include user/system interactivity and Model Management Subsystem (MMS) described in this work. Finally, a case study designed to validate the model is presented.