Author/Authors :
Fei, L Institute of Fundamental and Frontier Science - University of Electronic Science and Technology of China, Chengdu, 610054, China , Wang, H School of Computer and Information Sciences - Southwest University, Chongqing 400715, China , Chen, L School of Computer and Information Sciences - Southwest University, Chongqing 400715, China , Deng, Y Institute of Fundamental and Frontier Science - University of Electronic Science and Technology of China, Chengdu, 610054, China
Abstract :
Plenty of researches have been carried out, focusing on the measures of distance, similarity, and correlation between
intuitionistic fuzzy sets (IFSs). However, most of them are single-valued measures and lack of potential for eciency
validation. In this paper, a new vector valued similarity measure for IFSs is proposed based on OWA operators. The
vector is dened as a two-tuple consisting of the similarity measure and uncertainty measure, in which the latter is the
uncertainty of the former. OWA operators have the ability to aggregate all values in the universe of discourse of IFSs,
and to determine the weights according to specic applications. A framework is built to measure similarity between
IFSs. A series of denitions and theorems are given and proved to satisfy the corresponding axioms dened for IFSs.
In order to illustrate the eectiveness of the proposed vector valued similarity measure, a classication problem is used
as an application.
Keywords :
Classification , OWA operator , Intuitionistic fuzzy set , Uncertainty measure , Similarity measure
