Super learner machine-learning algorithms for compressive strength prediction of high performance concrete

Basit Öğe Kaydı
dc.authoridArmağan Karamanlı / 0000-0003-3990-6515en_US
dc.authorscopusidArmağan Karamanlı / 55659970400en_US
dc.authorwosidArmağan Karamanlı / AGG-2487-2022
dc.contributor.authorLee, Seunghye
dc.contributor.authorNguyen, Ngoc-Hien
dc.contributor.authorKaramanlı, Armağan
dc.contributor.authorLee, Jaehong
dc.contributor.authorVo, Thuc P.
dc.date.accessioned2022-07-19T11:51:37Z
dc.date.available2022-07-19T11:51:37Z
dc.date.issued2022en_US
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Makine Mühendisliği Bölümüen_US
dc.description.abstractBecause the proportion between the compressive strength of high-performance concrete (HPC) and its composition is highly nonlinear, more advanced regression methods are demanded to obtain better results. Super learner models, which are based on several ensemble methods including random forest regression (RFR), an adaptive boosting (AdaBoost), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical gradient Boosting (CatBoost), are used to solve this complicated problem. A grid search method is employed to determine the best set of hyper-parameters of each ensemble algorithm. Two super learner models, which combine all six models or select the top three effective ones as the base learners, are then proposed to develop an accurate approach to estimate the compressive strength of HPC. The results on four popular datasets show significant improvement of the proposed super learner models in terms of prediction accuracy. It also reveals that their trained models always perform better than other methods since their errors (MAE, MSE, RMSE) are always much lower and values of R2 are higher than those of the previous studies. The proposed super learner models can be used to provide a reliable tool for mixture design optimization of the HPC. © 2022 The Authors. Structural Concrete published by John Wiley & Sons Ltd on behalf of International Federation for Structural Concrete.en_US
dc.identifier.citationLee, S., Nguyen, N. H., Karamanli, A., Lee, J., & Vo, T. P. (2022). Super learner machine‐learning algorithms for compressive strength prediction of high performance concrete. Structural Concrete.en_US
dc.identifier.doi10.1002/suco.202200424en_US
dc.identifier.issn1464-4177en_US
dc.identifier.scopus2-s2.0-85133499292en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1002/suco.202200424
dc.identifier.urihttps://hdl.handle.net/20.500.12713/3019
dc.identifier.wosWOS:000821519000001en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.institutionauthorKaramanlı, Armağan
dc.language.isoenen_US
dc.publisherJohn Wiley and Sons Incen_US
dc.relation.ispartofStructural Concreteen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectCompressive Strengthen_US
dc.subjectEnsemble Learning Algorithmsen_US
dc.subjectHigh-Performance Concrete (HPC)en_US
dc.subjectMachine Learningen_US
dc.subjectSuper Learneren_US
dc.titleSuper learner machine-learning algorithms for compressive strength prediction of high performance concreteen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Structural Concrete - 2022 - Lee - Super learner machine‐learning algorithms for compressive strength prediction of high.pdf
Boyut:
27.65 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu