A Comparison of MCC and CEN Error Measures in Multi-Class Prediction

被引：227

作者：

Jurman, Giuseppe ^{[1
]}

Riccadonna, Samantha ^{[1
]}

Furlanello, Cesare ^{[1
]}

机构：

[1] Fdn Bruno Kessler, Trento, Italy

来源：

PLOS ONE | 2012年 / 7卷 / 08期

关键词：

ROC CURVE; STATISTICAL COMPARISONS; AREA; PERFORMANCE; CLASSIFIERS; CLASSIFICATION; ACCURACY; AUC;

D O I：

10.1371/journal.pone.0041882

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

We show that the Confusion Entropy, a measure of performance in multiclass problems has a strong (monotone) relation with the multiclass generalization of a classical metric, the Matthews Correlation Coefficient. Analytical results are provided for the limit cases of general no-information (n-face dice rolling) of the binary classification. Computational evidence supports the claim in the general case.

引用

页数：8

共 35 条

[1]

[Anonymous], P INT JOINT C NEUR N

[2]

[Anonymous], INFORM PROCESS UNPUB

[3]

[Anonymous], STUDIES COMPUTATIONA

[4]

[Anonymous], IFA P

[5]