Genetic generation of fuzzy knowledge bases: new perspectives

• Grant number: 07/05390-0
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: November 01, 2007
• End date: March 31, 2012
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Maria Carolina Monard
• Grantee: Marcos Evandro Cintra
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The automatic generation of fuzzy knowledge bases has become, in the last years, a topic of great interest for researchers of the areas that integrate the global theme of artificial intelligence. The methodologies based on fuzzy logic, which provide the mathematical apparatus for the representation and processing of knowledge in fuzzy systems offer flexible mechanisms for the treatment of the imprecision inherent to various domains of knowledge. The automatic design or optimization of such systems, or part of them, usually uses complementary methodologies equipped with resources for machine learning, such as clustering methods, neural networks and genetic algorithms, among others. This project focuses particularly on the articulation of the methodologies of fuzzy systems and genetic algorithms, which originated the area referred to as fuzzy genetic systems. The results presented in the several proposals found in the literature evidence the fact that this is a promising combination for the design of fuzzy systems. Among the biggest challenges found nowadays are the questions of dimensionality and balancing between precision and interpretability of the knowledge base. The project here proposed aims at investigating methods for the construction and optimization of fuzzy knowledge bases from data sets, emphasizing the articulation of theses methods with techniques directed to the treatment of the open questions here nominated.

Scientific publications

(4)

(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)

CINTRA, MARCOS E.; CAMARGO, HELOISA A.; MARTIN, TREVOR; CARVALHO, JP; KAYMAK, DU; SOUSA, JMC. Optimising the Fuzzy Granulation of Attribute Domains. PROCEEDINGS OF THE JOINT 2009 INTERNATIONAL FUZZY SYSTEMS ASSOCIATION WORLD CONGRESS AND 2009 EUROPEAN SOCIETY OF FUZZY LOGIC AND TECHNOLOGY CONFERENCE, v. N/A, p. 6-pg., 2009-01-01. (07/05390-0)

CINTRA, MARCOS EVANDRO; MARTIN, TREVOR P.; MONARD, MARIA CAROLINA; CAMARGO, HELOISA DE ARRUDA; TANG, YC; LAWRY, J; HUYNH, VN. Feature Subset Selection Using a Fuzzy Method. 2009 INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS, VOL 2, PROCEEDINGS, v. N/A, p. 2-pg., 2009-01-01. (07/05390-0)

CINTRA, M. E.; CAMARGO, H. A.; MONARD, M. C.. Genetic generation of fuzzy systems with rule extraction using formal concept analysis. INFORMATION SCIENCES, v. 349, p. 199-215, JUL 1 2016. (07/05390-0)

CINTRA, MARCOS E.; CAMARGO, HELOISA A.; HULLERMEIR, E; KRUSE, R; HOFFMANN, F. Feature Subset Selection for Fuzzy Classification Methods. ENGINEERING APPLICATIONS OF NEURAL NETWORKS, v. 80, p. 3-pg., 2010-01-01. (07/05390-0)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

CINTRA, Marcos Evandro. Genetic generation of fuzzy knowledge bases: new perspectives. 2012. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.