Unsupervised Attribute Reduction Algorithm for Mixed Data Based on Fuzzy Optimal Approximation Set

Haotong Wen, Shixin Zhao () and Meishe Liang
Additional contact information
Haotong Wen: Department of Mathematics and Physics, Shijiazhuang Tiedao University, Shijiazhuang 050043, China
Shixin Zhao: Department of Mathematics and Physics, Shijiazhuang Tiedao University, Shijiazhuang 050043, China
Meishe Liang: Department of Mathematics and Physics, Shijiazhuang Tiedao University, Shijiazhuang 050043, China

Mathematics, 2023, vol. 11, issue 16, 1-26

Abstract: Fuzzy rough set theory has been successfully applied to many attribute reduction methods, in which the lower approximation set plays a pivotal role. However, the definition of lower approximation used has ignored the information conveyed by the upper approximation and the boundary region. This oversight has resulted in an unreasonable relation representation of the target set. Despite the fact that scholars have proposed numerous enhancements to rough set models, such as the variable precision model, none have successfully resolved the issues inherent in the classical models. To address this limitation, this paper proposes an unsupervised attribute reduction algorithm for mixed data based on an improved optimal approximation set. Firstly, the theory of an improved optimal approximation set and its associated algorithm are proposed. Subsequently, we extend the classical theory of optimal approximation sets to fuzzy rough set theory, leading to the development of a fuzzy improved approximation set method. Finally, building on the proposed theory, we introduce a novel, fuzzy optimal approximation-set-based unsupervised attribute reduction algorithm (FOUAR). Comparative experiments conducted with all the proposed algorithms indicate the efficacy of FOUAR in selecting fewer attributes while maintaining and improving the performance of the machine learning algorithm. Furthermore, they highlight the advantage of the improved optimal approximation set algorithm, which offers higher similarity to the target set and provides a more concise expression.

Keywords: fuzzy rough set; granular computing; optimal approximation set; unsupervised attribute reduction (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/16/3452/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/16/3452/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:16:p:3452-:d:1213650

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().