Fuzzy modeling and identification, using afreli and fuzion algorithms
Jairo Jose Espinosa · 1998
This papers presents an algorithm to extract rules relating input-output data. The rules are created under the environment of fuzzy systems. The trade-off between linguistic integrity and accuracy is discussed and used as a framework to propose an algorithm for rule extraction (AFRELI). The algorithm is complemented with the use of the FuZion algorithm created to merge consecutive membership functions and guarantees the distinguishability between the fuzzy sets on each domain.