Incremental feature selection approach to interval-valued fuzzy decision information systems based on λ-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 approximations and pays attention to the boundary region of samples. Nevertheless, with the frequent replacement of data,...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences 2023-05, Vol.625, p.593-619
Main Authors: Zhang, Xiaoyan, Li, Jirong
Format: Article
Language:English
Subjects:
Dynamic object set
Fuzzy similarity relation
Incremental feature selection
Interval-valued fuzzy rough set
Self-information
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The relative decision self-information is a crucial evaluation function of feature selection in information system. It encapsulates classification information in upper and lower approximations and pays attention to the boundary region of samples. Nevertheless, with the frequent 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 selection due to the variation of objects in IvFDIS. Firstly, we construct λ-fuzzy similarity relation and introduce λ-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 λ-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 public data sets to certify the validity of our incremental algorithms. Experimental results show that comparable to three tested algorithms, the proposed incremental algorithms lessen the computation time greatly, and they select fewer features in most instances without decreasing classification accuracy in IvFDIS.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2023.01.058