Genetic tuning of fuzzy rule deep structures preserving interpretability and its interaction with fuzzy rule set reduction
- 14 February 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 13 (1), 13-29
- https://doi.org/10.1109/tfuzz.2004.839670
Abstract
Tuning fuzzy rule-based systems for linguistic fuzzy modeling is an interesting and widely developed task. It involves adjusting some of the components of the knowledge base without completely redefining it. This contribution introduces a genetic tuning process for jointly fitting the fuzzy rule symbolic representations and the meaning of the involved membership functions. To adjust the former component, we propose the use of linguistic hedges to perform slight modifications keeping a good interpretability. To alter the latter component, two different approaches changing their basic parameters and using nonlinear scaling factors are proposed. As the accomplished experimental study shows, the good performance of our proposal mainly lies in the consideration of this tuning approach performed at two different levels of significance. The paper also analyzes the interaction of the proposed tuning method with a fuzzy rule set reduction process. A good interpretability-accuracy tradeoff is obtained combining both processes with a sequential scheme: first reducing the rule set and subsequently tuning the model.Keywords
This publication has 48 references indexed in Scilit:
- Takagi-Sugeno fuzzy modeling incorporating input variables selectionIEEE Transactions on Fuzzy Systems, 2002
- Compact and transparent fuzzy models and classifiers through iterative complexity reductionIEEE Transactions on Fuzzy Systems, 2001
- Model construction, rule reduction, and robust compensation for generalized form of Takagi-Sugeno fuzzy systemsIEEE Transactions on Fuzzy Systems, 2001
- A constrained Takagi–Sugeno fuzzy system that allows for better interpretation and analysisFuzzy Sets and Systems, 2001
- GA-fuzzy modeling and classification: complexity and performanceIEEE Transactions on Fuzzy Systems, 2000
- Simplifying fuzzy rule-based models using orthogonal transformation methodsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999
- A highly interpretable form of Sugeno inference systemsIEEE Transactions on Fuzzy Systems, 1999
- Improving the interpretability of TSK fuzzy models by combining global learning and local learningIEEE Transactions on Fuzzy Systems, 1998
- Similarity measures in fuzzy rule base simplificationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1998
- Fuzzy connectives based crossover operators to model genetic algorithms population diversityFuzzy Sets and Systems, 1997