Distributed Genetic Tuning of Fuzzy Rule-Based Systems
Ignacio Robles, Rafael Alcalá, José M. Benítez, Francisco Herrera · European Society for Fuzzy Logic and Technology Conference · 2009
The tuning of Fuzzy Rule Base-Systems is necessary to improve their performance after the extraction of rules. This op- timization problem can become a hard one when the size of the con- sidered system in terms of the number of variables, rules and data samples is big. To alleviate this growth in complexity, we propose a distributed genetic algorithm which explotes the nowadays available parallel hardware (multicore microprocessors and clusters). The em- pirical performance in solution quality and computing time is as- sessed by comparing its results with those from a highly effective sequential tuning algorithm. Both methods are applied for the mod- eling of four well-known regression problems. Keywords— 2-tuples, Distributed Genetic Algorithms, Fuzzy Rule-based Systems Tuning, Lateral Tuning