A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification

Imbalanced data classification is one of the most important tasks in the field of machine learning because abnormality, which is usually of our interest, appears less frequently than normality in real-world systems. Learning classifiers from imbalanced data can be troublesome due to no absolute stan...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yeontark Park, Jong-Seok Lee
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Classification class imbalance sphere covering learning objective area under ROC curve Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/f94a5f2921364ab09353bf9e527dd376
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f94a5f2921364ab09353bf9e527dd376
record_format	dspace
spelling	oai:doaj.org-article:f94a5f2921364ab09353bf9e527dd3762021-12-03T00:00:23ZA Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification2169-353610.1109/ACCESS.2021.3130272https://doaj.org/article/f94a5f2921364ab09353bf9e527dd3762021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9625925/https://doaj.org/toc/2169-3536Imbalanced data classification is one of the most important tasks in the field of machine learning because abnormality, which is usually of our interest, appears less frequently than normality in real-world systems. Learning classifiers from imbalanced data can be troublesome due to no absolute standard as to how much imbalance can be said to be imbalanced or balanced. To address this issue, this research proposes a new sphere-based classification method named LOCS (learning objective controllable sphere-based classifier), which is designed to maximize AUC (area under ROC curve). The AUC learning objective was adopted from the fact that it approximates the accuracy as class distribution becomes balanced. Therefore, the proposed method properly performs a classification task for both imbalanced and balanced data. It constructs a classification model by a single training, whereas existing cost-sensitive learning and resampling methods usually attempt different parameter settings. In addition, the learning objective can be easily modified within LOCS for each of application domains by setting different importance levels for positive and negative classes, respectively. Numerical experiments based on 25 real datasets with several investigational settings showed the effectiveness and the intended strengths of the proposed method.Yeontark ParkJong-Seok LeeIEEEarticleClassificationclass imbalancesphere coveringlearning objectivearea under ROC curveElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 158010-158026 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Classification class imbalance sphere covering learning objective area under ROC curve Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Classification class imbalance sphere covering learning objective area under ROC curve Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yeontark Park Jong-Seok Lee A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
description	Imbalanced data classification is one of the most important tasks in the field of machine learning because abnormality, which is usually of our interest, appears less frequently than normality in real-world systems. Learning classifiers from imbalanced data can be troublesome due to no absolute standard as to how much imbalance can be said to be imbalanced or balanced. To address this issue, this research proposes a new sphere-based classification method named LOCS (learning objective controllable sphere-based classifier), which is designed to maximize AUC (area under ROC curve). The AUC learning objective was adopted from the fact that it approximates the accuracy as class distribution becomes balanced. Therefore, the proposed method properly performs a classification task for both imbalanced and balanced data. It constructs a classification model by a single training, whereas existing cost-sensitive learning and resampling methods usually attempt different parameter settings. In addition, the learning objective can be easily modified within LOCS for each of application domains by setting different importance levels for positive and negative classes, respectively. Numerical experiments based on 25 real datasets with several investigational settings showed the effectiveness and the intended strengths of the proposed method.
format	article
author	Yeontark Park Jong-Seok Lee
author_facet	Yeontark Park Jong-Seok Lee
author_sort	Yeontark Park
title	A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
title_short	A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
title_full	A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
title_fullStr	A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
title_full_unstemmed	A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
title_sort	learning objective controllable sphere-based method for balanced and imbalanced data classification
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/f94a5f2921364ab09353bf9e527dd376
work_keys_str_mv	AT yeontarkpark alearningobjectivecontrollablespherebasedmethodforbalancedandimbalanceddataclassification AT jongseoklee alearningobjectivecontrollablespherebasedmethodforbalancedandimbalanceddataclassification AT yeontarkpark learningobjectivecontrollablespherebasedmethodforbalancedandimbalanceddataclassification AT jongseoklee learningobjectivecontrollablespherebasedmethodforbalancedandimbalanceddataclassification
_version_	1718374026934484992

A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification

Ejemplares similares