Using Feature Distribution Methods in Ensemble Systems Combined by Fusion and Selection-Based Methods

Authors:
Laura E. Santana;Anne M. Canuto;João C. Xavier, Jr.
Affiliations:
Informatics and Applied Mathematics Department, Federal University of RN Natal, Brazil 59072-970;Informatics and Applied Mathematics Department, Federal University of RN Natal, Brazil 59072-970;Informatics and Applied Mathematics Department, Federal University of RN Natal, Brazil 59072-970
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 6
Cited 0

The Random Subspace Method for Constructing Decision Forests

IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature selection for ensembles

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
Classi.cation of Examples by Multiple Agents with Private Features

IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Rotation Forest: A New Classifier Ensemble Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Investigating the influence of the choice of the ensemble members in accuracy and diversity of selection-based and fusion-based methods for ensembles

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

The main prerequisite for the efficient use of ensemble systems is that the base classifiers should be diverse among themselves. One way of increasing diversity is through the use of feature distribution methods in ensemble systems. In this paper, an investigation of the use of feature distribution methods among the classifiers of ensemble systems will be performed. In this investigation, five different methods of data distribution will be used. These ensemble systems will use six existing combination methods, in which four of them are fusion-based methods and the remaining two are selection-based methods. As a result, it is aimed to detect which ensemble systems are more suitable to use feature distribution among the classifier.