Nested ensemble selection: An effective hybrid feature selection method

It has been shown that while feature selection algorithms are able to distinguish between relevant and irrelevant features, they fail to differentiate between relevant and redundant and correlated features. To address this issue, we propose a highly effective approach, called Nested Ensemble Selecti...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Kamalov, Firuz (author)
مؤلفون آخرون: Sulieman, Hana (author), Moussa, Sherif (author), Reyes, Jorge Avante (author), Safaraliev, Murodbek (author)
التنسيق: article
منشور في: 2023
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/11073/32531
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513442478555136
author Kamalov, Firuz
author2 Sulieman, Hana
Moussa, Sherif
Reyes, Jorge Avante
Safaraliev, Murodbek
author2_role author
author
author
author
author_facet Kamalov, Firuz
Sulieman, Hana
Moussa, Sherif
Reyes, Jorge Avante
Safaraliev, Murodbek
author_role author
dc.creator.none.fl_str_mv Kamalov, Firuz
Sulieman, Hana
Moussa, Sherif
Reyes, Jorge Avante
Safaraliev, Murodbek
dc.date.none.fl_str_mv 2023
2025-12-08T07:21:35Z
2025-12-08T07:21:35Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Firuz Kamalov, Hana Sulieman, Sherif Moussa, Jorge Avante Reyes, Murodbek Safaraliev, Nested ensemble selection: An effective hybrid feature selection method, Heliyon, Volume 9, Issue 9, 2023, e19686, ISSN 2405-8440, https://doi.org/10.1016/j.heliyon.2023.e19686.
2405-8440
https://hdl.handle.net/11073/32531
10.1016/j.heliyon.2023.e19686
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv ScienceDirect
dc.relation.none.fl_str_mv https://doi.org/10.1016/j.heliyon.2023.e19686
dc.subject.none.fl_str_mv Feature selection
Ensemble selection
Random forest
Synthetic data
Machine learning
Filter method
Wrapper method
dc.title.none.fl_str_mv Nested ensemble selection: An effective hybrid feature selection method
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description It has been shown that while feature selection algorithms are able to distinguish between relevant and irrelevant features, they fail to differentiate between relevant and redundant and correlated features. To address this issue, we propose a highly effective approach, called Nested Ensemble Selection (NES), that is based on a combination of filter and wrapper methods. The proposed feature selection algorithm differs from the existing filter-wrapper hybrid methods in its simplicity and efficiency as well as precision. The new algorithm is able to separate the relevant variables from the irrelevant as well as the redundant and correlated features. Furthermore, we provide a robust heuristic for identifying the optimal number of selected features which remains one of the greatest challenges in feature selection. Numerical experiments on synthetic and real-life data demonstrate the effectiveness of the proposed method. The NES algorithm achieves perfect precision on the synthetic data and near optimal accuracy on the real-life data. The proposed method is compared against several popular algorithms including mRMR, Boruta, genetic, recursive feature elimination, Lasso, and Elastic Net. The results show that NES significantly outperforms the benchmarks algorithms especially on multi-class datasets.
format article
id aus_bba83eb3c2e261c7756c0a40a099a57b
identifier_str_mv Firuz Kamalov, Hana Sulieman, Sherif Moussa, Jorge Avante Reyes, Murodbek Safaraliev, Nested ensemble selection: An effective hybrid feature selection method, Heliyon, Volume 9, Issue 9, 2023, e19686, ISSN 2405-8440, https://doi.org/10.1016/j.heliyon.2023.e19686.
2405-8440
10.1016/j.heliyon.2023.e19686
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/32531
publishDate 2023
publisher.none.fl_str_mv ScienceDirect
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Nested ensemble selection: An effective hybrid feature selection methodKamalov, FiruzSulieman, HanaMoussa, SherifReyes, Jorge AvanteSafaraliev, MurodbekFeature selectionEnsemble selectionRandom forestSynthetic dataMachine learningFilter methodWrapper methodIt has been shown that while feature selection algorithms are able to distinguish between relevant and irrelevant features, they fail to differentiate between relevant and redundant and correlated features. To address this issue, we propose a highly effective approach, called Nested Ensemble Selection (NES), that is based on a combination of filter and wrapper methods. The proposed feature selection algorithm differs from the existing filter-wrapper hybrid methods in its simplicity and efficiency as well as precision. The new algorithm is able to separate the relevant variables from the irrelevant as well as the redundant and correlated features. Furthermore, we provide a robust heuristic for identifying the optimal number of selected features which remains one of the greatest challenges in feature selection. Numerical experiments on synthetic and real-life data demonstrate the effectiveness of the proposed method. The NES algorithm achieves perfect precision on the synthetic data and near optimal accuracy on the real-life data. The proposed method is compared against several popular algorithms including mRMR, Boruta, genetic, recursive feature elimination, Lasso, and Elastic Net. The results show that NES significantly outperforms the benchmarks algorithms especially on multi-class datasets.American University of SharjahScienceDirect2025-12-08T07:21:35Z2025-12-08T07:21:35Z2023Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfFiruz Kamalov, Hana Sulieman, Sherif Moussa, Jorge Avante Reyes, Murodbek Safaraliev, Nested ensemble selection: An effective hybrid feature selection method, Heliyon, Volume 9, Issue 9, 2023, e19686, ISSN 2405-8440, https://doi.org/10.1016/j.heliyon.2023.e19686.2405-8440https://hdl.handle.net/11073/3253110.1016/j.heliyon.2023.e19686en_UShttps://doi.org/10.1016/j.heliyon.2023.e19686oai:repository.aus.edu:11073/325312025-12-08T11:41:47Z
spellingShingle Nested ensemble selection: An effective hybrid feature selection method
Kamalov, Firuz
Feature selection
Ensemble selection
Random forest
Synthetic data
Machine learning
Filter method
Wrapper method
status_str publishedVersion
title Nested ensemble selection: An effective hybrid feature selection method
title_full Nested ensemble selection: An effective hybrid feature selection method
title_fullStr Nested ensemble selection: An effective hybrid feature selection method
title_full_unstemmed Nested ensemble selection: An effective hybrid feature selection method
title_short Nested ensemble selection: An effective hybrid feature selection method
title_sort Nested ensemble selection: An effective hybrid feature selection method
topic Feature selection
Ensemble selection
Random forest
Synthetic data
Machine learning
Filter method
Wrapper method
url https://hdl.handle.net/11073/32531