Efficient multi-objective genetic tuning of fuzzy models for large-scale regression problems

A new algorithm for tuning fuzzy partitions with a high interpretability degree is proposed. The set of input variables, the number of linguistic terms per variable, and the type (triangular or trapezoidal) and parameters of the membership functions is tuned by an efficient process that endows the algorithm with capability to deal with large-scale regression problems. Interpretability constrains and advanced genetic operators are considered. A multi-objective optimization approach is used to generate different interpretability-accuracy tradeoffs. The algorithm is tested in a set of real-world regression problems with successful results compared to other methods.