Incremental feature selection approach to interval-valued fuzzy decision information systems based on 1-fuzzy similarity self-information

The relative decision self-information is a crucial evaluation function of feature selection in information system. It encapsulates classification information in upper and lower approx-imations and pays attention to the boundary region of samples. Nevertheless, with the fre-quent replacement of data, the static feature selection neglects the previous information of samples, which diminishes the computational efficiency. With the purpose of adapting to the evolution of the era, incremental learning is widely exerted in the field of data mining. In combination with incremental technique, it is not cumbersome to update the reduct in time. Enlightened by this, our work focuses on the mechanism of incremental feature selec-tion due to the variation of objects in IvFDIS. Firstly, we construct 1-fuzzy similarity rela-tion and introduce 1-fuzzy similarity self-information into IvFDIS based on relative decision self-information. Besides, with the assistance of matrix operation, we recommend static feature selection according to 1-fuzzy similarity self-information. Furthermore, two relevant incremental algorithms involving the insertion and removal of objects in IvFDIS are made a research. Finally, some comparative experiments are conducted on twelve pub -lic data sets to certify the validity of our incremental algorithms. Experimental results show that comparable to three tested algorithms, the proposed incremental algorithms les -sen the computation time greatly, and they select fewer features in most instances without decreasing classification accuracy in IvFDIS.(c) 2023 Elsevier Inc. All rights reserved.