A novel approach to predictive analysis using attribute-oriented rough fuzzy sets. (15th December 2020)

• Record Type: Journal Article
• Authors: Yu, Bin; Cai, Mingjie; Dai, Jianhua; Li, Qingguo
• Is Part Of: Expert systems with applications. Volume 161(2020)
• Publication Date: 2020-12-15
• Subjects: Fuzzy information system (FIS) -- δ-Cluster -- (γ, δ)-Rough fuzzy set ((γ, δ)-RFS) -- TPELDTP -- Decision making; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2020.113644
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: With data mining's point of view, we propose a novel rough fuzzy sets of fuzzy information systems. Based on δ -clusters, ( γ, δ )-rough fuzzy sets inherit the ability that predict it with growth trend. We use ( γ, δ )-rough fuzzy set theory to predictive analysis. The randomness of the algorithm is analyzed. Abstract: In this study, a forecasting decision-making method is put forward to deal with multi-attribute decision-making problems. On the basis of rough set theory, ( γ, δ )-rough fuzzy sets are presented using δ -clusters in data mining. Furthermore, several characteristics of the upper and lower ( γ, δ )-approximations are obtained. Lastly, the difference between the fuzzy set A of the object and the upper and lower rough ( γ, δ )-approximation operators on A is analyzed. We also design a novel algorithm to forecast decision making and provide a related example illustrating the new method.