Functional Correlations in the Pursuit of Performance Assessment of Classifiers

Standard

Functional Correlations in the Pursuit of Performance Assessment of Classifiers. / Gribkova, Nadezhda; Zitikis, Ričardas.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 34, No. 13, 2051013, 15.12.2020.

Research output: Contribution to journal › Article › peer-review

Author

Gribkova, Nadezhda ; Zitikis, Ričardas. / Functional Correlations in the Pursuit of Performance Assessment of Classifiers. In: International Journal of Pattern Recognition and Artificial Intelligence. 2020 ; Vol. 34, No. 13.

BibTeX

@article{0260b1b0b281433d85f9041d5bede19c,

title = "Functional Correlations in the Pursuit of Performance Assessment of Classifiers",

abstract = "In statistical classification and machine learning, as well as in social and other sciences, a number of measures of association have been proposed for assessing and comparing individual classifiers, raters, as well as their groups. In this paper, we introduce, justify, and explore several new measures of association, which we call CO-, ANTI-, and COANTI-correlation coefficients, that we demonstrate to be powerful tools for classifying confusion matrices. We illustrate the performance of these new coefficients using a number of examples, from which we also conclude that the coefficients are new objects in the sense that they differ from those already in the literature.",

keywords = "classifier, confusion matrix, Functional correlation, rater, weighted kappa, functional correlation, classifer, rater, confusion matrix, weighted kappa",

author = "Nadezhda Gribkova and Ri{\v c}ardas Zitikis",

year = "2020",

month = dec,

day = "15",

doi = "10.1142/S0218001420510131",

language = "English",

volume = "34",

journal = "International Journal of Pattern Recognition and Artificial Intelligence",

issn = "0218-0014",

publisher = "WORLD SCIENTIFIC PUBL CO PTE LTD",

number = "13",

}

RIS

TY - JOUR

T1 - Functional Correlations in the Pursuit of Performance Assessment of Classifiers

AU - Gribkova, Nadezhda

AU - Zitikis, Ričardas

PY - 2020/12/15

Y1 - 2020/12/15

N2 - In statistical classification and machine learning, as well as in social and other sciences, a number of measures of association have been proposed for assessing and comparing individual classifiers, raters, as well as their groups. In this paper, we introduce, justify, and explore several new measures of association, which we call CO-, ANTI-, and COANTI-correlation coefficients, that we demonstrate to be powerful tools for classifying confusion matrices. We illustrate the performance of these new coefficients using a number of examples, from which we also conclude that the coefficients are new objects in the sense that they differ from those already in the literature.

AB - In statistical classification and machine learning, as well as in social and other sciences, a number of measures of association have been proposed for assessing and comparing individual classifiers, raters, as well as their groups. In this paper, we introduce, justify, and explore several new measures of association, which we call CO-, ANTI-, and COANTI-correlation coefficients, that we demonstrate to be powerful tools for classifying confusion matrices. We illustrate the performance of these new coefficients using a number of examples, from which we also conclude that the coefficients are new objects in the sense that they differ from those already in the literature.

KW - classifier

KW - confusion matrix

KW - Functional correlation

KW - rater

KW - weighted kappa

KW - functional correlation

KW - classifer

KW - rater

KW - confusion matrix

KW - weighted kappa

UR - http://www.scopus.com/inward/record.url?scp=85083799930&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/44d03347-6a9b-3371-b3a1-a5f03881d22d/

U2 - 10.1142/S0218001420510131

DO - 10.1142/S0218001420510131

M3 - Article

AN - SCOPUS:85083799930

VL - 34

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 13

M1 - 2051013

ER -

ID: 69947173