Using integer programming to rough set based feature selection: An approach to find all reducts respectively

Document Type : Original Article

Authors
Seyed Majid Alavi
Narges Khazravi
10.22034/jcse.2023.181962
Abstract
Rough set theory (RST) is an important tool for finding feature
subset selection. One of the most critical and challenging issues in
RST is to find reducts and core. Since most applied sciences involve
high-dimensional descriptions of input features, a large amount of research has been conducted on dimensional reduction. Feature Selection refers to the process of selecting the input features leading to the most
predictable results. On the other hand, RST can be adopted to discover data dependencies and reduce the number of attributes in a data set using the data alone, requiring no extra information. Therefore, in
this paper, we proposed a straightforward approach for feature subset
selection through binary integer linear programming (BILP). Optimal
solutions to the result of this problem in reducts that lead to feature
subset selection. All reducts are obtained from the smallest cardinality to the largest cardinality, respectively. Also, to get the optimal solutions for BILP, we dealt with the Branch and Bound method and
Genetic Algorithm. The steps of our approach are illustrated by anE

Keywords