Binary Dragonfly Algorithm for Feature Selection

Majdi M. Mafarja; Derar Eleyan; Iyad Jaber; Abdelaziz Hammouri; Seyedali Mirjalili

doi:10.1109/ICTCS.2017.43

Binary Dragonfly Algorithm for Feature Selection

Majdi M. Mafarja, Derar Eleyan, Iyad Jaber, Abdelaziz Hammouri, Seyedali Mirjalili

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

83 Citations (Scopus)

Abstract

Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.

Original language	English
Title of host publication	Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017
Editors	Arafat Awajan, Adnan Shaout
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	12-17
Number of pages	6
ISBN (Electronic)	9781538605271
DOIs	https://doi.org/10.1109/ICTCS.2017.43
Publication status	Published - 8 Jan 2018
Externally published	Yes
Event	2017 International Conference on New Trends in Computing Sciences, ICTCS 2017 - Amman, Jordan Duration: 11 Oct 2017 → 13 Oct 2017

Publication series

Name	Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017
Volume	2018-January

Conference

Conference	2017 International Conference on New Trends in Computing Sciences, ICTCS 2017
Country	Jordan
City	Amman
Period	11/10/17 → 13/10/17

Keywords

classification
Dragonfly Algorithm
Optimization
Selection

Access to Document

10.1109/ICTCS.2017.43

Fingerprint Dive into the research topics of 'Binary Dragonfly Algorithm for Feature Selection'. Together they form a unique fingerprint.

Cite this

Mafarja, M. M., Eleyan, D., Jaber, I., Hammouri, A., & Mirjalili, S. (2018). Binary Dragonfly Algorithm for Feature Selection. In A. Awajan, & A. Shaout (Eds.), Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017 (pp. 12-17). (Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICTCS.2017.43

Mafarja, Majdi M. ; Eleyan, Derar ; Jaber, Iyad ; Hammouri, Abdelaziz ; Mirjalili, Seyedali. / Binary Dragonfly Algorithm for Feature Selection. Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017. editor / Arafat Awajan ; Adnan Shaout. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 12-17 (Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017).

@inproceedings{f45337099cc0441bb71efda7cfe4255e,

title = "Binary Dragonfly Algorithm for Feature Selection",

abstract = "Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.",

keywords = "classification, Dragonfly Algorithm, Optimization, Selection",

author = "Mafarja, {Majdi M.} and Derar Eleyan and Iyad Jaber and Abdelaziz Hammouri and Seyedali Mirjalili",

year = "2018",

month = jan,

day = "8",

doi = "10.1109/ICTCS.2017.43",

language = "English",

series = "Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "12--17",

editor = "Arafat Awajan and Adnan Shaout",

booktitle = "Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017",

note = "2017 International Conference on New Trends in Computing Sciences, ICTCS 2017 ; Conference date: 11-10-2017 Through 13-10-2017",

}

Mafarja, MM, Eleyan, D, Jaber, I, Hammouri, A & Mirjalili, S 2018, Binary Dragonfly Algorithm for Feature Selection. in A Awajan & A Shaout (eds), Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017. Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 12-17, 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017, Amman, Jordan, 11/10/17. https://doi.org/10.1109/ICTCS.2017.43

Binary Dragonfly Algorithm for Feature Selection. / Mafarja, Majdi M.; Eleyan, Derar; Jaber, Iyad; Hammouri, Abdelaziz; Mirjalili, Seyedali.

Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017. ed. / Arafat Awajan; Adnan Shaout. Institute of Electrical and Electronics Engineers Inc., 2018. p. 12-17 (Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017; Vol. 2018-January).

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

TY - GEN

T1 - Binary Dragonfly Algorithm for Feature Selection

AU - Mafarja, Majdi M.

AU - Eleyan, Derar

AU - Jaber, Iyad

AU - Hammouri, Abdelaziz

AU - Mirjalili, Seyedali

PY - 2018/1/8

Y1 - 2018/1/8

N2 - Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.

AB - Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.

KW - classification

KW - Dragonfly Algorithm

KW - Optimization

KW - Selection

UR - http://www.scopus.com/inward/record.url?scp=85050194810&partnerID=8YFLogxK

U2 - 10.1109/ICTCS.2017.43

DO - 10.1109/ICTCS.2017.43

M3 - Conference contribution

T3 - Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017

SP - 12

EP - 17

BT - Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017

A2 - Awajan, Arafat

A2 - Shaout, Adnan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017

Y2 - 11 October 2017 through 13 October 2017

ER -

Mafarja MM, Eleyan D, Jaber I, Hammouri A, Mirjalili S. Binary Dragonfly Algorithm for Feature Selection. In Awajan A, Shaout A, editors, Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 12-17. (Proceedings - 2017 International Conference on New Trends in Computing Sciences, ICTCS 2017). https://doi.org/10.1109/ICTCS.2017.43

Binary Dragonfly Algorithm for Feature Selection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this