Rough fuzzy model based feature discretization in intelligent data preprocess

Abstract Feature discretization is an important preprocessing technology for massive data in industrial control. It improves the efficiency of edge-cloud computing by transforming continuous features into discrete ones, so as to meet requirements high-quality cloud services. Compared with other methods, based on rough set has achieved good results many applications because it can make full use known knowledge base without any prior information. However, equivalence class ordinary set, which difficult describe fuzzy components data, and accuracy low some complex types big environment. Therefore, we propose a model algorithm (RFMD). Firstly, c -means clustering get membership each sample category. Then, fuzzify obtained membership, establish fitness function genetic select optimal breakpoints features. Finally, compare proposed method information entropy, chi-square test remote sensing datasets. The experimental verify effectiveness our method.