Dynamic Butterfly Optimization Algorithm for Feature Selection
Feature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce the number of these features and maximise the classifier...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9239279/ |
id |
doaj-8425d50d899c44fb8b8fdfd129efeb61 |
---|---|
record_format |
Article |
spelling |
doaj-8425d50d899c44fb8b8fdfd129efeb612021-03-30T04:28:03ZengIEEEIEEE Access2169-35362020-01-01819430319431410.1109/ACCESS.2020.30337579239279Dynamic Butterfly Optimization Algorithm for Feature SelectionMohammad Tubishat0https://orcid.org/0000-0003-1464-8345Mohammed Alswaitti1https://orcid.org/0000-0003-0580-6954Seyedali Mirjalili2https://orcid.org/0000-0002-1443-9458Mohammed Ali Al-Garadi3Ma'en Tayseer Alrashdan4Toqir A. Rana5https://orcid.org/0000-0003-4353-7150School of Technology and Computing, Asia Pacific University of Technology and Innovation, Kuala Lumpur, MalaysiaSchool of Electrical and Computer Engineering (ICT), Xiamen University Malaysia, Bandar Sunsuria, MalaysiaCentre for Artificial Intelligence Research and Optimization, Torrens University Australia, Fortitude Valley, QLD, AustraliaDepartment of Radiology, University of California at San Diego, La Jolla, CA, USASchool of Technology and Computing, Asia Pacific University of Technology and Innovation, Kuala Lumpur, MalaysiaDepartment of Computer Science and IT, The University of Lahore, Lahore, PakistanFeature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce the number of these features and maximise the classifier accuracy. This paper proposes a Dynamic Butterfly Optimization Algorithm (DBOA) as an improved variant to Butterfly Optimization Algorithm (BOA) for feature selection problems. BOA represents one of the most recently proposed optimization algorithms. BOA has demonstrated its ability to solve different types of problems with competitive results compared to other optimization algorithms. However, the original BOA algorithm has problems when optimising high-dimensional problems. Such issues include stagnation into local optima and lacking solutions diversity during the optimization process. To alleviate these weaknesses of the original BOA, two significant improvements are introduced in the original BOA: the development of a Local Search Algorithm Based on Mutation (LSAM) operator to avoid local optima problem and the use of LSAM to improve BOA solutions diversity. To demonstrate the efficiency and superiority of the proposed DBOA algorithm, 20 benchmark datasets from the UCI repository are employed. The classification accuracy, the fitness values, the number of selected features, the statistical results, and convergence curves are reported for DBOA and its competing algorithms. These results demonstrate that DBOA significantly outperforms the comparative algorithms on the majority of the used performance metrics.https://ieeexplore.ieee.org/document/9239279/Butterfly optimization algorithmfeature selectionlocal search algorithm based on mutation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mohammad Tubishat Mohammed Alswaitti Seyedali Mirjalili Mohammed Ali Al-Garadi Ma'en Tayseer Alrashdan Toqir A. Rana |
spellingShingle |
Mohammad Tubishat Mohammed Alswaitti Seyedali Mirjalili Mohammed Ali Al-Garadi Ma'en Tayseer Alrashdan Toqir A. Rana Dynamic Butterfly Optimization Algorithm for Feature Selection IEEE Access Butterfly optimization algorithm feature selection local search algorithm based on mutation |
author_facet |
Mohammad Tubishat Mohammed Alswaitti Seyedali Mirjalili Mohammed Ali Al-Garadi Ma'en Tayseer Alrashdan Toqir A. Rana |
author_sort |
Mohammad Tubishat |
title |
Dynamic Butterfly Optimization Algorithm for Feature Selection |
title_short |
Dynamic Butterfly Optimization Algorithm for Feature Selection |
title_full |
Dynamic Butterfly Optimization Algorithm for Feature Selection |
title_fullStr |
Dynamic Butterfly Optimization Algorithm for Feature Selection |
title_full_unstemmed |
Dynamic Butterfly Optimization Algorithm for Feature Selection |
title_sort |
dynamic butterfly optimization algorithm for feature selection |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Feature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce the number of these features and maximise the classifier accuracy. This paper proposes a Dynamic Butterfly Optimization Algorithm (DBOA) as an improved variant to Butterfly Optimization Algorithm (BOA) for feature selection problems. BOA represents one of the most recently proposed optimization algorithms. BOA has demonstrated its ability to solve different types of problems with competitive results compared to other optimization algorithms. However, the original BOA algorithm has problems when optimising high-dimensional problems. Such issues include stagnation into local optima and lacking solutions diversity during the optimization process. To alleviate these weaknesses of the original BOA, two significant improvements are introduced in the original BOA: the development of a Local Search Algorithm Based on Mutation (LSAM) operator to avoid local optima problem and the use of LSAM to improve BOA solutions diversity. To demonstrate the efficiency and superiority of the proposed DBOA algorithm, 20 benchmark datasets from the UCI repository are employed. The classification accuracy, the fitness values, the number of selected features, the statistical results, and convergence curves are reported for DBOA and its competing algorithms. These results demonstrate that DBOA significantly outperforms the comparative algorithms on the majority of the used performance metrics. |
topic |
Butterfly optimization algorithm feature selection local search algorithm based on mutation |
url |
https://ieeexplore.ieee.org/document/9239279/ |
work_keys_str_mv |
AT mohammadtubishat dynamicbutterflyoptimizationalgorithmforfeatureselection AT mohammedalswaitti dynamicbutterflyoptimizationalgorithmforfeatureselection AT seyedalimirjalili dynamicbutterflyoptimizationalgorithmforfeatureselection AT mohammedalialgaradi dynamicbutterflyoptimizationalgorithmforfeatureselection AT maentayseeralrashdan dynamicbutterflyoptimizationalgorithmforfeatureselection AT toqirarana dynamicbutterflyoptimizationalgorithmforfeatureselection |
_version_ |
1724181783762698240 |