Prototype Selection Using Self-Organizing-Maps and Entropy for Overlapped Classes and Imbalanced Data

Tipo
Artigo de evento
Data de publicação
2018
Periódico
Proceedings of the International Joint Conference on Neural Networks
Citações (Scopus)
2
Autores
Rubbo M.
Silva L.A.
Orientador
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
© 2018 IEEE.The k nearest neighbor kNN is a traditional supervised classifier used in data mining tasks. However, when used in real applications, mainly in a dataset with class imbalance or class overlap, kNN suffers with problems in accuracy performance. In this paper, we propose three prototype selection methods using self-organizing maps (SOM) and information entropy to increase the effectiveness of the kNN classifier in datasets with these conditions. The methods, named SOMEntropyKnn, were able to increase the effectiveness of the kNN classifier in all the 14 datasets used in the experiment, increasing the accuracy performance from datasets with imbalance or overlap problems.
Descrição
Palavras-chave
Assuntos Scopus
class overlap , Data mining tasks , Imbalanced data , Information entropy , K-nearest neighbors , Prototype selection , Real applications , Supervised classifiers
Citação
DOI (Texto completo)