Exploring the relationships between data complexity and classification diversity in ensembles

Date

2021

Authors

Formentín Garcia, Nathan
Tiggeman, Frederico
Borges, Eduardo N.
Santos, Helida

Director

Publisher

SciTePress
Acceso abierto / Sarbide irekia
Contribución a congreso / Biltzarrerako ekarpena
Versión publicada / Argitaratu den bertsioa

Project identifier

Impacto
No disponible en Scopus

Abstract

Several classification techniques have been proposed in the last years. Each approach is best suited for a particular classification problem, i.e., a classification algorithm may not effectively or efficiently recognize some patterns in complex data. Selecting the best-tuned solution may be prohibitive. Methods for combining classifiers have also been proposed aiming at improving the generalization ability and classification results. In this paper, we analyze geometrical features of the data class distribution and the diversity of the base classifiers to understand better the performance of an ensemble approach based on stacking. The experimental evaluation was conducted using 32 real datasets, twelve data complexity measures, five diversity measures, and five heterogeneous classification algorithms. The results show that stacked generalization outperforms the best individual base classifier when there is a combination of complex and imbalanced data with diverse predictions among weak learners.

Description

Keywords

Machine learning ensembles, Complexity measures, Diversity measures

Department

Estadística, Informática y Matemáticas / Estatistika, Informatika eta Matematika

Faculty/School

Degree

Doctorate program

item.page.cita

Garcia, N.; Tiggeman, F.; Borges, E.; Lucca, G.; Santos, H. and Dimuro, G. (2021). Exploring the Relationships between Data Complexity and Classification Diversity in Ensembles. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-509-8; ISSN 2184-4992, pages 652-659. DOI: 10.5220/0010440006520659

item.page.rights

© 2021 by SCITEPRESS-Science and Technology Publications, Lda. Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

Los documentos de Academica-e están protegidos por derechos de autor con todos los derechos reservados, a no ser que se indique lo contrario.