Título

Synthetic Oversampling of Instances Using Clustering

Autor

Atlántida Irene Sánchez Vivar

Eduardo Francisco Morales Manzanares

Jesús Antonio González Bernal

Nivel de Acceso

Acceso Abierto

Licencia

http://creativecommons.org/licenses/by-nc-nd/4.0

Materias

Imbalanced datasets - (IMBALANCED DATASETS) Oversampling - (OVERSAMPLING) Cluster-based oversampling - (CLUSTER-BASED OVERSAMPLING) Jittering - (JITTERING) CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA - (CTI) MATEMÁTICAS - (CTI) CIENCIA DE LOS ORDENADORES - (CTI) CIENCIA DE LOS ORDENADORES - (CTI)

Resumen o descripción

Imbalanced data sets, in the class distribution, is common to many real world applications. As many classifiers tend to degrade their performance over the minority class, several approaches have been proposed to deal with this problem. In this paper, we propose two new cluster-based oversampling methods, SOI-C and SOI-CJ. The proposed methods create clusters from the minority class instances and generate synthetic instances inside those clusters. In contrast with other oversampling methods, the proposed approaches avoid creating new instances in majority class regions. They are more robust to noisy examples (the number of new instances generated per cluster is proportional to the cluster's size). The clusters are automatically generated. Our new methods do not need tuning parameters, and they can deal both with numerical and nominal attributes. The two methods were tested with twenty artificial datasets and twenty three datasets from the UCI Machine Learning repository. For our experiments, we used six classifiers and results were evaluated with TPR, precision, F-measure, and AUC measures, which are more suitable for class imbalanced datasets. We performed ANOVA and paired t-tests to show that the proposed methods are competitive and in many cases significantly better than the rest of the oversampling methods used during the comparison.

Editor

World Scientific Publishing Company

Fecha de publicación

2013

Tipo de publicación

Artículo

Versión de la publicación

Versión aceptada

Recurso de información

http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/2395

Formato

application/pdf

Idioma

Inglés

Audiencia

Estudiantes

Investigadores

Público en general

Sugerencia de citación

Sánchez, A., et al., (2013). Synthetic Oversampling of Instances Using Clustering, International Journal on Artificial Intelligence Tools, Vol. 22 (2): 1-22

Repositorio Orígen

Repositorio Institucional del INAOE

Descargas

105