Use this url to cite publication: https://hdl.handle.net/20.500.12259/54731
Approximation of unbiased convex classification error rate estimator
Type of publication
Straipsnis Web of Science ir Scopus duomenų bazėje / Article in Web of Science and Scopus database (S1)
Author(s)
Author | Affiliation | |
---|---|---|
LT | ||
University Göttingen, Germany | DE |
Title [en]
Approximation of unbiased convex classification error rate estimator
Is part of
Informacinės technologijos ir valdymas = Information technology and control. Kaunas : Technologija, 2016, t. 45, nr. 2
Date Issued
Date |
---|
2016 |
Publisher
Kaunas : Technologija
Extent
p. 148-155
Field of Science
Abstract (en)
Convex classification error rate estimator is described as weighted combination of the low-biased estimator and the high-biased estimator. If the underlying data model is known, the coefficients (weights) can be optimized so that the bias and root-mean-square error of the estimator is minimized. However, in most situations, data model is unknown. In this paper we propose a new error estimation method, based on approximation of unbiased convex error rate estimator. Experiments with real world and synthetic data sets show that common error estimation methods, such as resubstitution, repeated 10-foldcross-validation, leave-one-out and random subsampling are outperformed (in terms of root-mean-square error) by the proposed method.
Type of document
type::text::journal::journal article::research article
Language
Anglų / English (en)
Coverage Spatial
Lietuva / Lithuania (LT)
ISSN (of the container)
1392-124X
WOS
WOS:000378875700003
Other Identifier(s)
VDU02-000020515
Access Rights
Atviroji prieiga / Open Access
Creative Commons License
Journal | IF | AIF | AIF (min) | AIF (max) | Cat | AV | Year | Quartile |
---|---|---|---|---|---|---|---|---|
Information Technology and Control | 0.475 | 2.788 | 2.345 | 3.021 | 3 | 0.177 | 2016 | Q4 |
Journal | IF | AIF | AIF (min) | AIF (max) | Cat | AV | Year | Quartile |
---|---|---|---|---|---|---|---|---|
Information Technology and Control | 0.475 | 2.788 | 2.345 | 3.021 | 3 | 0.177 | 2016 | Q4 |
Journal | Cite Score | SNIP | SJR | Year | Quartile |
---|---|---|---|---|---|
Information Technology and Control | 1.9 | 0.571 | 0.276 | 2016 | Q2 |