In a Quest for Suitable Similarity Measures to Compare Experience-Based Evaluations

被引:2
|
作者
Loor, Marcelo [1 ,2 ]
De Tre, Guy [1 ]
机构
[1] Univ Ghent, Dept Telecommun & Informat Proc, Sint Pietersnieuwstr 41, B-9000 Ghent, Belgium
[2] ESPOL Univ, Dept Elect & Comp Engn, Campus Gustavo Galindo 5,Km 30-5 Via Perimetral, Guayaquil, Ecuador
来源
COMPUTATIONAL INTELLIGENCE, IJCCI 2015 | 2017年 / 669卷
关键词
Experience-based evaluations; Similarity Measures; Intuitionistic fuzzy sets;
D O I
10.1007/978-3-319-48506-5_15
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
After representing experience-based evaluations as intuitionistic fuzzy sets (IFSs), one might expect that all of the existing similarity measures for IFSs could be used to compare them. However, only some of those measures seem to be suitable to do so according to a psychological perspective which indicates that similarity measures assuming symmetry and transitivity could not reflect properly the perceived similarity. Consequently, to determine empirically their suitability for such comparisons, several similarity measures for IFSs were tested on simulated experience-based evaluations. This paper presents our findings about how each of them reflected the perceived similarity among the simulated experience-based evaluation sets.
引用
收藏
页码:291 / 314
页数:24
相关论文
共 50 条