Adaptive Neural Architecture Search Using Meta-Heuristics: Discovering Fine-Tuned Predictive Models for Photocatalytic CO2 Reduction

Basit Öğe Kaydı
dc.contributor.authorIşıkdağ, Ümit
dc.contributor.authorBekdaş, Gebrail
dc.contributor.authorAydın, Yaren
dc.contributor.authorApak, Sudi
dc.contributor.authorHong, Junhee
dc.contributor.authorGeem, Zong Woo
dc.date.accessioned2025-03-26T16:10:01Z
dc.date.available2025-03-26T16:10:01Z
dc.date.issued2024
dc.departmentİstanbul Esenyurt Üniversitesi, Fakülteler, Mühendislik ve Mimarlık Fakültesi, Endüstri Mühendisliği Bölümü
dc.description.abstractThis study aims to contribute to the reduction of carbon dioxide and the production of hydrogen through an investigation of the photocatalytic reaction process. Machine learning algorithms can be used to predict the hydrogen yield in the photocatalytic carbon dioxide reduction process. Although regression-based approaches provide good results, the accuracy achieved with classification algorithms is not very high. In this context, this study presents a new method, Adaptive Neural Architecture Search (NAS) using metaheuristics, to improve the capacity of ANNs in estimating the hydrogen yield in the photocatalytic carbon dioxide reduction process through classification. The NAS process was carried out with a tool named HyperNetExplorer, which was developed with the aim of finding the ANN architecture providing the best prediction accuracy through changing ANN hyperparameters, such as the number of layers, number of neurons in each layer, and the activation functions of each layer. The nature of the NAS process in this study was adaptive, since the process was accomplished through optimization algorithms. The ANNs discovered with HyperNetExplorer demonstrated significantly higher prediction performance than the classical ML algorithms. The results indicated that the NAS helped to achieve better performance in the estimation of the hydrogen yield in the photocatalytic carbon dioxide reduction process. © 2024 by the authors.
dc.description.sponsorshipKorea Institute of Energy Technology Evaluation and Planning, KETEP
dc.description.sponsorshipMinistry of Trade, Industry and Energy, MOTIE, (RS-2024-00442817)
dc.description.sponsorshipMinistry of Trade, Industry and Energy, MOTIE
dc.description.sponsorshipGachon University, (GCU-202403910001)
dc.description.sponsorshipGachon University
dc.identifier.doi10.3390/su162310756
dc.identifier.issn2071-1050
dc.identifier.issue23
dc.identifier.scopus2-s2.0-85211762035
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3390/su162310756
dc.identifier.urihttps://hdl.handle.net/20.500.14704/789
dc.identifier.volume16
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.relation.ispartofSustainability (Switzerland)
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_Scopus_20250326
dc.subjectclassification
dc.subjecthydrogen
dc.subjecthyperparameter optimization
dc.subjectmachine learning
dc.subjectphotocatalytic
dc.titleAdaptive Neural Architecture Search Using Meta-Heuristics: Discovering Fine-Tuned Predictive Models for Photocatalytic CO2 Reduction
dc.typeArticle

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Mühendislik ve Mimarlık Fakültesi Koleksiyonu