Feature selection for classification using an ant colony system

Nadia Abd-Alsabour; Marcus Randall

doi:10.1109/eScienceW.2010.23

Feature selection for classification using an ant colony system

Nadia Abd-Alsabour^*, Marcus Randall

^*Corresponding author for this work

Bond Business School

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

20 Citations (Scopus)

Abstract

Many applications such as pattern recognition require selecting a subset of the input features in order to represent the whole set of features. The aim of feature selection is to remove irrelevant or redundant features while keeping the most informative ones. In this paper, an ant colony system approach for solving feature selection for classification is presented. The proposed algorithm was tested using artificial and real-world datasets. The results are promising in terms of the accuracy of the classifier and the number of selected features in all the used datasets. The results of the proposed algorithm have been compared with other results available in the literature and found to be favorable.

Original language	English
Title of host publication	Proceedings - 6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010
Pages	86-91
Number of pages	6
DOIs	https://doi.org/10.1109/eScienceW.2010.23
Publication status	Published - 2010
Event	6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010 - Brisbane, QLD, Australia Duration: 7 Dec 2010 → 10 Dec 2010

Conference

Conference	6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010
Country/Territory	Australia
City	Brisbane, QLD
Period	7/12/10 → 10/12/10

Access to Document

10.1109/eScienceW.2010.23

Cite this

@inproceedings{fa1e20ef11114705a5cdf97b41d4050c,

title = "Feature selection for classification using an ant colony system",

abstract = "Many applications such as pattern recognition require selecting a subset of the input features in order to represent the whole set of features. The aim of feature selection is to remove irrelevant or redundant features while keeping the most informative ones. In this paper, an ant colony system approach for solving feature selection for classification is presented. The proposed algorithm was tested using artificial and real-world datasets. The results are promising in terms of the accuracy of the classifier and the number of selected features in all the used datasets. The results of the proposed algorithm have been compared with other results available in the literature and found to be favorable.",

author = "Nadia Abd-Alsabour and Marcus Randall",

year = "2010",

doi = "10.1109/eScienceW.2010.23",

language = "English",

isbn = "9780769542959",

pages = "86--91",

booktitle = "Proceedings - 6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010",

note = "6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010 ; Conference date: 07-12-2010 Through 10-12-2010",

}

TY - GEN

T1 - Feature selection for classification using an ant colony system

AU - Abd-Alsabour, Nadia

AU - Randall, Marcus

PY - 2010

Y1 - 2010

N2 - Many applications such as pattern recognition require selecting a subset of the input features in order to represent the whole set of features. The aim of feature selection is to remove irrelevant or redundant features while keeping the most informative ones. In this paper, an ant colony system approach for solving feature selection for classification is presented. The proposed algorithm was tested using artificial and real-world datasets. The results are promising in terms of the accuracy of the classifier and the number of selected features in all the used datasets. The results of the proposed algorithm have been compared with other results available in the literature and found to be favorable.

AB - Many applications such as pattern recognition require selecting a subset of the input features in order to represent the whole set of features. The aim of feature selection is to remove irrelevant or redundant features while keeping the most informative ones. In this paper, an ant colony system approach for solving feature selection for classification is presented. The proposed algorithm was tested using artificial and real-world datasets. The results are promising in terms of the accuracy of the classifier and the number of selected features in all the used datasets. The results of the proposed algorithm have been compared with other results available in the literature and found to be favorable.

UR - http://www.scopus.com/inward/record.url?scp=79951815086&partnerID=8YFLogxK

U2 - 10.1109/eScienceW.2010.23

DO - 10.1109/eScienceW.2010.23

M3 - Conference contribution

AN - SCOPUS:79951815086

SN - 9780769542959

SP - 86

EP - 91

BT - Proceedings - 6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010

T2 - 6th IEEE International Conference on e-Science Workshops, e-ScienceW 2010

Y2 - 7 December 2010 through 10 December 2010

ER -

Feature selection for classification using an ant colony system

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this