Optimal deep neural network architecture design with improved generalization for data-driven cooling load estimation problem

Basit Öğe Kaydı
dc.contributor.authorAlagoz, Baris Baykant
dc.contributor.authorKeles, Cemal
dc.contributor.authorAtes, Abdullah
dc.contributor.authorÖzdemir, Edanur
dc.contributor.authorAlkhulaifi, Nasser
dc.date.accessioned2026-04-04T13:18:53Z
dc.date.available2026-04-04T13:18:53Z
dc.date.issued2025
dc.departmentİnönü Üniversitesi
dc.description.abstractDecision of the model complexity is a significant challenge in contemporary data-driven modeling applications. Designing neural architecture involves the process of determining the optimal model complexity for deep neural networks (DNNs) models in order to uncover relationships in real-world data patterns. Consequently, optimizing DNN architectures is crucial for enhancing the practical approximation performance of DNN models to real-world data. This study implements a data-driven neuroevolution scheme for the optimal neural architecture search (NAS) and demonstrates a data-driven engineering application for cooling load estimation. The proposed neuroevolution scheme aims at evolving to the best generalizing DNN model that well suits the modeling complexity requirements of the dataset. To this end, the objective function for the neural architecture optimization process is simplified to the mean square error of the test dataset, which enables to reduce the risk of insufficient generalization during NAS. By employing this objective function for evolution field optimization (EFO), the proposed neuroevolution process can automatically achieve the optimal model complexity, preventing overfitting and underfitting cases, and thereby attaining almost the best generalization for the dataset. For this purpose, this approach combines parametric learning with the backpropagation algorithm and structural learning with EFO-based neural architecture search to address data-driven, optimal complexity DNN model generation problems. Effectiveness of the method is demonstrated in the cooling load estimation problem of residential buildings, and performances of the optimal DNN models with four objective functions are analyzed. The design of objective function for the best generalizing model is also elaborated. © The Author(s) 2025.
dc.description.sponsorshipTürkiye Bilimsel ve Teknolojik Araştırma Kurumu, TUBITAK; TÜBİTAK; Scientific and Technological Research Council of Türkiye; Inönü Üniversitesi, (FBA-2024-3436); Inönü Üniversitesi
dc.identifier.doi10.1007/s00521-025-11212-7
dc.identifier.endpage13616
dc.identifier.issn0941-0643
dc.identifier.issue19
dc.identifier.scopus2-s2.0-105004031810
dc.identifier.scopusqualityQ1
dc.identifier.startpage13597
dc.identifier.urihttps://doi.org/10.1007/s00521-025-11212-7
dc.identifier.urihttps://hdl.handle.net/11616/107986
dc.identifier.volume37
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer Science and Business Media Deutschland GmbH
dc.relation.ispartofNeural Computing and Applications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_Scopus_20250329
dc.subjectArtificial neural network
dc.subjectAutomated machine learning
dc.subjectEnergy load estimation
dc.subjectNeural architecture search
dc.subjectNeuroevolution
dc.titleOptimal deep neural network architecture design with improved generalization for data-driven cooling load estimation problem
dc.typeArticle

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu