Supervised methods for regrouping attributes in fuzzy rule-based classification systems

摘要: This paper focuses on ensemble methods for Fuzzy Rule-Based Classification Systems (FRBCS) where the decisions of different classifiers are combined in order to form final classification model. The proposed reduce FRBCS complexity and generated rules number. We interested particular which cluster attributes into subgroups treat each subgroup separately. Our work is an extension a previous method called SIFRA. uses frequent itemsets mining concept deduce groups related by analyzing their simultaneous appearances databases. drawback this that it forms searching dependencies between independently from class information. Besides, since we deal with supervised learning problems, would be very interesting consider attribute when forming subgroups. In paper, two new regrouping take account not only but also information about labels. results obtained various benchmark datasets show good accuracy built