Rapid and brief communication: Controlling the diversity in classifier ensembles through a measure of agreement

Authors:
Héla Zouari;Laurent Heutte;Yves Lecourtier
Affiliations:
Laboratoire PSI-FRE CNRS 2645, Université de Rouen, 76821 Mont-Saint-Aignan, Cedex, France;Laboratoire PSI-FRE CNRS 2645, Université de Rouen, 76821 Mont-Saint-Aignan, Cedex, France;Laboratoire PSI-FRE CNRS 2645, Université de Rouen, 76821 Mont-Saint-Aignan, Cedex, France
Venue:
Pattern Recognition
Year:
2005

Citing 3
Cited 3

Generating classifier outputs of fixed accuracy and diversity

Pattern Recognition Letters
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy

Machine Learning
Simulating classifier outputs for evaluating parallel combination methods

MCS'03 Proceedings of the 4th international conference on Multiple classifier systems

Ectropy of diversity measures for populations in Euclidean space

Information Sciences: an International Journal
Credit rating using a hybrid voting ensemble

SETN'12 Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applications
Tree ensembles for predicting structured outputs

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, a simulation method is proposed to generate a set of classifier outputs with specified individual accuracies and fixed pairwise agreement. A diversity measure (kappa) is used to control the agreement among classifiers for building the classifier teams. The generated team outputs can be used to study the behaviour of class-type combination methods such as voting rules over multiple dependent classifiers.