Integration of bagging and boosting with a new reweighting technique

Yoshiaki Yasumura, Naho Kitani, Kuniaki Uehara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We propose a novel ensemble learning method, IBB (Integration of Boosting and Bagging). This method creates initial classifiers by bagging, and then builds base classifiers by boosting using the previously created classifiers. IBB has two new techniques, a reweighting technique and data adaptation. The reweighting technique increases a weight of a sample which is misclassified by both the ensemble classifier and previously created base classifier. The data adaptation is realized by controlling the number of iteration in boosting. Experimental results using the datasets of UCI machine learning repository show that IBB resulted better accuracy than the other ensemble learning methods on several datasets and on average.

Original languageEnglish
Title of host publicationProceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet
Pages338-343
Number of pages6
Volume1
Publication statusPublished - 2005
Externally publishedYes
EventInternational Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005 - Vienna
Duration: 2005 Nov 282005 Nov 30

Other

OtherInternational Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005
CityVienna
Period05/11/2805/11/30

Fingerprint

Classifiers
Learning systems

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yasumura, Y., Kitani, N., & Uehara, K. (2005). Integration of bagging and boosting with a new reweighting technique. In Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet (Vol. 1, pp. 338-343). [1631289]

Integration of bagging and boosting with a new reweighting technique. / Yasumura, Yoshiaki; Kitani, Naho; Uehara, Kuniaki.

Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. Vol. 1 2005. p. 338-343 1631289.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yasumura, Y, Kitani, N & Uehara, K 2005, Integration of bagging and boosting with a new reweighting technique. in Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. vol. 1, 1631289, pp. 338-343, International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005, Vienna, 05/11/28.
Yasumura Y, Kitani N, Uehara K. Integration of bagging and boosting with a new reweighting technique. In Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. Vol. 1. 2005. p. 338-343. 1631289
Yasumura, Yoshiaki ; Kitani, Naho ; Uehara, Kuniaki. / Integration of bagging and boosting with a new reweighting technique. Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. Vol. 1 2005. pp. 338-343
@inproceedings{2b6797e82c6445338a5e3dc67b7811e1,
title = "Integration of bagging and boosting with a new reweighting technique",
abstract = "We propose a novel ensemble learning method, IBB (Integration of Boosting and Bagging). This method creates initial classifiers by bagging, and then builds base classifiers by boosting using the previously created classifiers. IBB has two new techniques, a reweighting technique and data adaptation. The reweighting technique increases a weight of a sample which is misclassified by both the ensemble classifier and previously created base classifier. The data adaptation is realized by controlling the number of iteration in boosting. Experimental results using the datasets of UCI machine learning repository show that IBB resulted better accuracy than the other ensemble learning methods on several datasets and on average.",
author = "Yoshiaki Yasumura and Naho Kitani and Kuniaki Uehara",
year = "2005",
language = "English",
isbn = "0769525040",
volume = "1",
pages = "338--343",
booktitle = "Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet",

}

TY - GEN

T1 - Integration of bagging and boosting with a new reweighting technique

AU - Yasumura, Yoshiaki

AU - Kitani, Naho

AU - Uehara, Kuniaki

PY - 2005

Y1 - 2005

N2 - We propose a novel ensemble learning method, IBB (Integration of Boosting and Bagging). This method creates initial classifiers by bagging, and then builds base classifiers by boosting using the previously created classifiers. IBB has two new techniques, a reweighting technique and data adaptation. The reweighting technique increases a weight of a sample which is misclassified by both the ensemble classifier and previously created base classifier. The data adaptation is realized by controlling the number of iteration in boosting. Experimental results using the datasets of UCI machine learning repository show that IBB resulted better accuracy than the other ensemble learning methods on several datasets and on average.

AB - We propose a novel ensemble learning method, IBB (Integration of Boosting and Bagging). This method creates initial classifiers by bagging, and then builds base classifiers by boosting using the previously created classifiers. IBB has two new techniques, a reweighting technique and data adaptation. The reweighting technique increases a weight of a sample which is misclassified by both the ensemble classifier and previously created base classifier. The data adaptation is realized by controlling the number of iteration in boosting. Experimental results using the datasets of UCI machine learning repository show that IBB resulted better accuracy than the other ensemble learning methods on several datasets and on average.

UR - http://www.scopus.com/inward/record.url?scp=33847204682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847204682&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0769525040

SN - 9780769525044

VL - 1

SP - 338

EP - 343

BT - Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet

ER -