A novel hybrid intelligent system: Genetic algorithm and rough set incorporated neural fuzzy inference system
Dongdong Wang, Geok See Ng, Chai Hiok Quek · 2008
This paper proposes a novel hybrid intelligent system denoted as genetic algorithm and rough set incorporated neural fuzzy inference system (GARSINFIS). Its network structure dynamically changes along with the evolving genetic algorithm based rough set clustering (GARSC) technique. When input data set is applied, only the most essential information is retained in the clustering result, as knowledge reduction is done using rough set approximations and the most optimal solution is selected by genetic algorithm. The system not only obtains promising accuracy but also possesses a great level of interpretability to meet the increasing need of understanding the inference process. In terms of TSK type of fuzzy inference system, better structural interpretability is typically manifested as employing less number of input features, less number of rules, less number of fuzzy membership functions in each feature, and less complex rules in both antecedent and consequent parts. Extensive simulations on various data sets were conducted, and the performance of GARSINFIS was benchmarked against other well established neural and neural-fuzzy systems. Experimental results have shown that GARSINFIS performs well in both accuracy and interpretability.