Skip to main content

Research Repository

Advanced Search

Evolving an optimal decision template for combining classifiers.

Nguyen, Tien Thanh; Luong, Anh Vu; Dang, Manh Truong; Dao, Lan Phuong; Nguyen, Thi Thu Thuy; Liew, Alan Wee-Chung; McCall, John

Authors

Anh Vu Luong

Manh Truong Dang

Lan Phuong Dao

Thi Thu Thuy Nguyen

Alan Wee-Chung Liew

Profile Image

Professor John McCall j.mccall@rgu.ac.uk
Professorial Lead (NSC) & Lead of the Computational Intelligence Research Group



Contributors

Tom Gedeon
Editor

Kok Wai Wong
Editor

Minho Lee
Editor

Abstract

In this paper, we aim to develop an effective combining algorithm for ensemble learning systems. The Decision Template method, one of the most popular combining algorithms for ensemble systems, does not perform well when working on certain datasets like those having imbalanced data. Moreover, point estimation by computing the average value on the outputs of base classifiers in the Decision Template method is sometimes not a good representation, especially for skewed datasets. Here we propose to search for an optimal decision template in the combining algorithm for a heterogeneous ensemble. To do this, we first generate the base classifier by training the pre-selected learning algorithms on the given training set. The meta-data of the training set is then generated via cross validation. Using the Artificial Bee Colony algorithm, we search for the optimal template that minimizes the empirical 0–1 loss function on the training set. The class label is assigned to the unlabeled sample based on the maximum of the similarity between the optimal decision template and the sample’s meta-data. Experiments conducted on the UCI datasets demonstrated the superiority of the proposed method over several benchmark algorithms.

Citation

NGUYEN, T.T., LUONG, A.V., DANG, M.T., DAO, L.P., NGUYEN, T.T.T., LIEW, A.W.-C. and MCCALL, J. 2019. Evolving an optimal decision template for combining classifiers. In Gedeon, T., Wong, K.W. and Lee, M. (eds.) Neural information processing: proceedings of the 26th International conference on neural information processing (ICONIP 2019), 12-15 December 2019, Sydney, Australia. Part I. Lecture notes in computer science, 11953. Cham: Springer [online], pages 608-620. Available from: https://doi.org/10.1007/978-3-030-36708-4_50

Conference Name 26th International conference on neural information processing (ICONIP 2019)
Conference Location Sydney, Australia
Start Date Dec 12, 2019
End Date Dec 15, 2019
Acceptance Date Sep 14, 2019
Online Publication Date Dec 9, 2019
Publication Date Dec 31, 2019
Deposit Date May 4, 2020
Publicly Available Date May 4, 2020
Publisher Springer Verlag
Volume Part I
Pages 608-620
Series Title Lecture notes in computer science
Series Number 11953
Series ISSN 1611-3349
Book Title Neural information processing
ISBN 9783030367077
DOI https://doi.org/10.1007/978-3-030-36708-4_50
Keywords Ensemble systems; Ensemble learning systems; Machine learning; Decision template method
Public URL https://rgu-repository.worktribe.com/output/905611

Files





You might also like



Downloadable Citations