An improved arithmetic optimization algorithm for training feedforward neural networks under dynamic environments

Basit Öğe Kaydı
dc.authoridGolcuk, Ilker/0000-0002-8430-7952
dc.authorwosidGolcuk, Ilker/B-2116-2015
dc.contributor.authorGölcük, İlker
dc.contributor.authorÖzsoydan, Fehmi Burçin
dc.contributor.authorDurmaz, Esra Duygu
dc.date.accessioned2023-03-22T19:47:20Z
dc.date.available2023-03-22T19:47:20Z
dc.date.issued2023
dc.departmentBelirleneceken_US
dc.description.abstractThis paper proposes an improved Arithmetic Optimization Algorithm (AOA) to train artificial neural networks (ANNs) under dynamic environments. Despite many successful applications of metaheuristic training of ANNs, these studies assume static environments, which might not be realistic in real-world nonstationary processes. In this study, the training of ANNs is modeled as a dynamic optimization problem, and the proposed AOA is used to optimize connection weights and biases of the ANN under the presence of concept drift. The proposed method is designed to work for classification tasks. The performance of the proposed algorithm has been tested on twelve dynamic classification problems. Comparative analysis with state-of-the-art metaheuristic optimization algorithms has been provided. The superiority of the compared algorithms has been verified using nonparametric statistical tests. The results show that the improved AOA outperforms compared algorithms in training ANNs under dynamic environments. The findings demonstrate the potential of improved AOA for dynamic data-driven applications.(c) 2023 Elsevier B.V. All rights reserved.en_US
dc.description.sponsorshipIzmir Bakircay University Scientific Research Projects Coordination [KBP.2021.001]en_US
dc.description.sponsorshipThis work has been supported by Izmir Bakircay University Scientific Research Projects Coordination Unit under grant number KBP.2021.001.en_US
dc.identifier.doi10.1016/j.knosys.2023.110274
dc.identifier.issn0950-7051
dc.identifier.issn1872-7409
dc.identifier.scopus2-s2.0-85149730689en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1016/j.knosys.2023.110274
dc.identifier.urihttps://hdl.handle.net/20.500.14034/637
dc.identifier.volume263en_US
dc.identifier.wosWOS:000925673200001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.journalKnowledge-Based Systemsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectArithmetic optimization algorithmen_US
dc.subjectArtificial neural networksen_US
dc.subjectConcept driften_US
dc.subjectDynamic optimizationen_US
dc.subjectDifferential Evolution Algorithmen_US
dc.subjectDesignen_US
dc.subjectDriften_US
dc.titleAn improved arithmetic optimization algorithm for training feedforward neural networks under dynamic environmentsen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Tam metin / Full text
Boyut:
3.15 MB
Biçim:
Adobe Portable Document Format
Açıklama:
An improved arithmetic optimization algorithm
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Endüstri Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu