A neurofuzzy system based on rough set theory and genetic algorithms

This paper presents a hybrid soft computing modeling approach, a neurofuzzy system based on rough set theory and genetic algorithms (NFRSGA). To solve the curse of dimensionality problem of neurofuzzy system, rough set is applied to obtain the reductive fuzzy rule set. The number of rules decreases, and each rule does not need all condition attributes values. Genetic algorithm is used to obtain the optimal discretization of continuous attributes. Then the fuzzy system is represented via an equivalent artificial neural network (ANN). The convergence of the ANN training is fast, and the structure size of the ANN becomes small.