An ant colony optimization approach for stacking ensemble

Yijun CHEN, Man Leung WONG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

9 Citations (Scopus)

Abstract

an ensemble in data mining is the strategy that combines a set of different classifiers together to generate an integrated classification system to classify new instances. In the early research, an ensemble outperforms any of its individual components. Stacking is one of the most influential ensemble among the proposed ensemble schemes. Stacking applies a two-level structure: the base-level classifiers output their own predictions and the meta-level classifier takes the outputs as its input to generate final decision. Most of the existing studies focus on the meta-level classifier adoption, and few on the topic about determining the configuration of both base-level classifiers and the meta-level classifier together. This work is inspired by the Ant Colony Optimization which is good at solving combinatorial optimization problems. We propose an ACO-Stacking ensemble approach and also perform some preliminary experiments to compare our approach with some well-known ensembles. The preliminary results show that the performance of the ACO-Stacking is promising.
Original languageEnglish
Title of host publicationProceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
Pages146-151
Number of pages6
DOIs
Publication statusPublished - 1 Jan 2010

Fingerprint

Ant colony optimization
Classifiers
Combinatorial optimization
Data mining
Experiments

Keywords

  • ACO
  • Data mining
  • Ensemble
  • Metaheuristic
  • Stacking

Cite this

CHEN, Y., & WONG, M. L. (2010). An ant colony optimization approach for stacking ensemble. In Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010 (pp. 146-151) https://doi.org/10.1109/NABIC.2010.5716282
CHEN, Yijun ; WONG, Man Leung. / An ant colony optimization approach for stacking ensemble. Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. pp. 146-151
@inproceedings{0238f761790b4665bbd6c9e902580d85,
title = "An ant colony optimization approach for stacking ensemble",
abstract = "an ensemble in data mining is the strategy that combines a set of different classifiers together to generate an integrated classification system to classify new instances. In the early research, an ensemble outperforms any of its individual components. Stacking is one of the most influential ensemble among the proposed ensemble schemes. Stacking applies a two-level structure: the base-level classifiers output their own predictions and the meta-level classifier takes the outputs as its input to generate final decision. Most of the existing studies focus on the meta-level classifier adoption, and few on the topic about determining the configuration of both base-level classifiers and the meta-level classifier together. This work is inspired by the Ant Colony Optimization which is good at solving combinatorial optimization problems. We propose an ACO-Stacking ensemble approach and also perform some preliminary experiments to compare our approach with some well-known ensembles. The preliminary results show that the performance of the ACO-Stacking is promising.",
keywords = "ACO, Data mining, Ensemble, Metaheuristic, Stacking",
author = "Yijun CHEN and WONG, {Man Leung}",
year = "2010",
month = "1",
day = "1",
doi = "10.1109/NABIC.2010.5716282",
language = "English",
pages = "146--151",
booktitle = "Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010",

}

CHEN, Y & WONG, ML 2010, An ant colony optimization approach for stacking ensemble. in Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. pp. 146-151. https://doi.org/10.1109/NABIC.2010.5716282

An ant colony optimization approach for stacking ensemble. / CHEN, Yijun; WONG, Man Leung.

Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. p. 146-151.

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

TY - GEN

T1 - An ant colony optimization approach for stacking ensemble

AU - CHEN, Yijun

AU - WONG, Man Leung

PY - 2010/1/1

Y1 - 2010/1/1

N2 - an ensemble in data mining is the strategy that combines a set of different classifiers together to generate an integrated classification system to classify new instances. In the early research, an ensemble outperforms any of its individual components. Stacking is one of the most influential ensemble among the proposed ensemble schemes. Stacking applies a two-level structure: the base-level classifiers output their own predictions and the meta-level classifier takes the outputs as its input to generate final decision. Most of the existing studies focus on the meta-level classifier adoption, and few on the topic about determining the configuration of both base-level classifiers and the meta-level classifier together. This work is inspired by the Ant Colony Optimization which is good at solving combinatorial optimization problems. We propose an ACO-Stacking ensemble approach and also perform some preliminary experiments to compare our approach with some well-known ensembles. The preliminary results show that the performance of the ACO-Stacking is promising.

AB - an ensemble in data mining is the strategy that combines a set of different classifiers together to generate an integrated classification system to classify new instances. In the early research, an ensemble outperforms any of its individual components. Stacking is one of the most influential ensemble among the proposed ensemble schemes. Stacking applies a two-level structure: the base-level classifiers output their own predictions and the meta-level classifier takes the outputs as its input to generate final decision. Most of the existing studies focus on the meta-level classifier adoption, and few on the topic about determining the configuration of both base-level classifiers and the meta-level classifier together. This work is inspired by the Ant Colony Optimization which is good at solving combinatorial optimization problems. We propose an ACO-Stacking ensemble approach and also perform some preliminary experiments to compare our approach with some well-known ensembles. The preliminary results show that the performance of the ACO-Stacking is promising.

KW - ACO

KW - Data mining

KW - Ensemble

KW - Metaheuristic

KW - Stacking

UR - http://commons.ln.edu.hk/sw_master/6535

U2 - 10.1109/NABIC.2010.5716282

DO - 10.1109/NABIC.2010.5716282

M3 - Conference paper (refereed)

SP - 146

EP - 151

BT - Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010

ER -

CHEN Y, WONG ML. An ant colony optimization approach for stacking ensemble. In Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. p. 146-151 https://doi.org/10.1109/NABIC.2010.5716282