Incremental attribute reduction with α,β-level intuitionistic fuzzy sets

Abstract

The intuitionistic fuzzy set theory is recognized as an effective approach for attribute reduction in decision information systems containing numerical or continuous data, particularly in cases of noisy data. However, this approach involves complex computations due to the participation of both the membership and non-membership functions, making it less feasible for data tables with a large number of objects. Additionally, in some practical scenarios, dynamic data tables may change in the number of objects, such as the addition or removal of objects. To overcome these challenges, we propose a novel and efficient incremental attribute reduction method based on $\alpha ,\beta$-level intuitionistic fuzzy sets. Specifically, we first utilize the key properties of $\alpha ,\beta$-level intuitionistic fuzzy sets to construct a distance measure between two $\alpha ,\beta$-level intuitionistic fuzzy partitions. This extension of the intuitionistic fuzzy set model helps reduce noise in the data and shrink the computational space. Subsequently, we define a new reduct and design an efficient algorithm to identify an attribute subset in fixed decision tables. For dynamic decision tables, we develop two incremental calculation formulas based on the distance measure between two $\alpha ,\beta$-level intuitionistic fuzzy partitions to improve processing time. Accordingly, some important properties of the distance measures are also clarified. Finally, we design two incremental attribute reduction algorithms that handle the addition and removal of objects. Experimental results have demonstrated that our method is more effective than incremental methods based on fuzzy rough set and intuitionistic fuzzy set approaches in terms of execution time and classification accuracy from the obtained reduct.