Semi-overlap functions and novel fuzzy reasoning algorithms with applications

In order to get a more general result related on fuzzy implications that induced by aggregation functions, we relax the definition of general overlap functions, more precisely, removing its right-continuous, and introduce a new kind of aggregation function, which called semi-overlap function. Subseq...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences Vol. 614; pp. 104 - 122
Main Authors: Zhang, Xiaohong, Wang, Mei, Bedregal, Benjamín, Li, Mengyuan, Liang, Rong
Format: Journal Article
Language:English
Published: Elsevier Inc 01.10.2022
Subjects:
ISSN:0020-0255, 1872-6291
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to get a more general result related on fuzzy implications that induced by aggregation functions, we relax the definition of general overlap functions, more precisely, removing its right-continuous, and introduce a new kind of aggregation function, which called semi-overlap function. Subsequently, we explore some of their related algebraic properties and its corresponding residual implications. Moreover, serval scholars have provided kinds of methods for fuzzy modus ponens (FMP, for short) problems, such as Zadeh’s compositional rule of inference (CRI, for short), Wang’s triple I method (TIM, for short) and quintuple implication principle (QIP, for short). Compared with CRI and TIM, QIP has some advantages in solving FMP problems. Based on the above theory foundation of semi-overlap functions and their residual implications, we further consider the QIP for FMP problems. Finally, we propose a new classification algorithm that based on semi-overlap functions and QIP, which called SO5I-FRC algorithm. Through the comparative tests, the average accuracy of SO5I-FRC algorithm is higher than FARC–HD algorithm. The experimental results indicate that semi-overlap functions and QIP have certain advantages and a wide range of applications in classification problems.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2022.10.017