A classification using mixture of concordance measures
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F25%3A00640703" target="_blank" >RIV/67985556:_____/25:00640703 - isvavai.cz</a>
Result on the web
<a href="https://ijfs.usb.ac.ir/article_9284.html" target="_blank" >https://ijfs.usb.ac.ir/article_9284.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.22111/ijfs.2025.51019.9017" target="_blank" >10.22111/ijfs.2025.51019.9017</a>
Alternative languages
Result language
angličtina
Original language name
A classification using mixture of concordance measures
Original language description
In the realm of classification studies, existing literature indicates that, when the relationships among exploratory variables extend beyond linear functions, nonlinear classifiers tend to outperform their linear counterparts. This study employs concordance measures to attain optimal outcomes in a classification task. In this regard, we examine the connection copula among the exploratory variables, as well as the copula linking the exploratory attributes to the target attribute are taken into consideration. As a major novelty, our classification approach utilizes a convex combination of the pairwise Spearman's rank correlation coefficient rho and the pairwise Kendall's association tau. Through a simulation analysis, we assess the performance of our algorithm, which demonstrates its superiority over alternatives, including copula-based classification methods as well as machine learning classification models. We also, provide an application of our method to the classification of COVID-19 dataset for more illustration.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10103 - Statistics and probability
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Iranian Journal of Fuzzy Systems
ISSN
1735-0654
e-ISSN
2676-4334
Volume of the periodical
22
Issue of the periodical within the volume
3
Country of publishing house
IR - IRAN, ISLAMIC REPUBLIC OF
Number of pages
11
Pages from-to
139-149
UT code for WoS article
001528199400006
EID of the result in the Scopus database
2-s2.0-105010739860