A survey of commonly used ensemble-based classification techniques

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

The combination of multiple classifiers, commonly referred to as a classifier ensemble, has previously demonstrated the ability to improve classification accuracy in many application domains. As a result this area has attracted significant amount of research in recent years. The aim of this paper has therefore been to provide a state of the art review of the most well-known ensemble techniques with the main focus on bagging, boosting and stacking and to trace the recent attempts which have been made to improve their performance. Within this paper we present and compare an updated view on the different modifications of these techniques which have specifically aimed to address some of the drawbacks of these methods namely the low diversity problem in bagging or the over-fitting problem in boosting. In addition we provide a review of different ensemble selection methods based on both static and dynamic approach. We present some new directions which have been adopted in the area of classifier ensembles from a range of recently published studies. In order to provide better understanding on how the ensembles work some existing theoretical studies have been reviewed in the paper.
LanguageEnglish
Pages551-581
JournalThe Knowledge Engineering Review
Volume29
Issue number5
DOIs
Publication statusPublished - Nov 2014

Fingerprint

Classifiers

Cite this

@article{aefa732c8d1c4b5eab4ef38acbafe648,
title = "A survey of commonly used ensemble-based classification techniques",
abstract = "The combination of multiple classifiers, commonly referred to as a classifier ensemble, has previously demonstrated the ability to improve classification accuracy in many application domains. As a result this area has attracted significant amount of research in recent years. The aim of this paper has therefore been to provide a state of the art review of the most well-known ensemble techniques with the main focus on bagging, boosting and stacking and to trace the recent attempts which have been made to improve their performance. Within this paper we present and compare an updated view on the different modifications of these techniques which have specifically aimed to address some of the drawbacks of these methods namely the low diversity problem in bagging or the over-fitting problem in boosting. In addition we provide a review of different ensemble selection methods based on both static and dynamic approach. We present some new directions which have been adopted in the area of classifier ensembles from a range of recently published studies. In order to provide better understanding on how the ensembles work some existing theoretical studies have been reviewed in the paper.",
author = "Anna Jurek and Yaxin Bi and Shengli Wu and Chris Nugent",
year = "2014",
month = "11",
doi = "10.1017/S0269888913000155",
language = "English",
volume = "29",
pages = "551--581",
journal = "Knowledge Engineering Review",
issn = "0269-8889",
publisher = "Cambridge University Press",
number = "5",

}

A survey of commonly used ensemble-based classification techniques. / Jurek, Anna; Bi, Yaxin; Wu, Shengli; Nugent, Chris.

In: The Knowledge Engineering Review, Vol. 29, No. 5, 11.2014, p. 551-581.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A survey of commonly used ensemble-based classification techniques

AU - Jurek, Anna

AU - Bi, Yaxin

AU - Wu, Shengli

AU - Nugent, Chris

PY - 2014/11

Y1 - 2014/11

N2 - The combination of multiple classifiers, commonly referred to as a classifier ensemble, has previously demonstrated the ability to improve classification accuracy in many application domains. As a result this area has attracted significant amount of research in recent years. The aim of this paper has therefore been to provide a state of the art review of the most well-known ensemble techniques with the main focus on bagging, boosting and stacking and to trace the recent attempts which have been made to improve their performance. Within this paper we present and compare an updated view on the different modifications of these techniques which have specifically aimed to address some of the drawbacks of these methods namely the low diversity problem in bagging or the over-fitting problem in boosting. In addition we provide a review of different ensemble selection methods based on both static and dynamic approach. We present some new directions which have been adopted in the area of classifier ensembles from a range of recently published studies. In order to provide better understanding on how the ensembles work some existing theoretical studies have been reviewed in the paper.

AB - The combination of multiple classifiers, commonly referred to as a classifier ensemble, has previously demonstrated the ability to improve classification accuracy in many application domains. As a result this area has attracted significant amount of research in recent years. The aim of this paper has therefore been to provide a state of the art review of the most well-known ensemble techniques with the main focus on bagging, boosting and stacking and to trace the recent attempts which have been made to improve their performance. Within this paper we present and compare an updated view on the different modifications of these techniques which have specifically aimed to address some of the drawbacks of these methods namely the low diversity problem in bagging or the over-fitting problem in boosting. In addition we provide a review of different ensemble selection methods based on both static and dynamic approach. We present some new directions which have been adopted in the area of classifier ensembles from a range of recently published studies. In order to provide better understanding on how the ensembles work some existing theoretical studies have been reviewed in the paper.

U2 - 10.1017/S0269888913000155

DO - 10.1017/S0269888913000155

M3 - Article

VL - 29

SP - 551

EP - 581

JO - Knowledge Engineering Review

T2 - Knowledge Engineering Review

JF - Knowledge Engineering Review

SN - 0269-8889

IS - 5

ER -