Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism

In the current research, a newly developed ensemble intelligent predictive model called Bagging Regression (BGR) is proposed to predict the compressive strength of a hollow concrete masonry prism (fp). A matrix of input combinations is constructed based on several predictive variables, including mor...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ahmad Sharafati, Seyed Babak Haji Seyed Asadollah, Nadhir Al-Ansari
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Hollow concrete block masonry prisms Bagging regression model Compressive strength prediction Data division Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/64843f78f4834b028aad1ee593b10856
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:64843f78f4834b028aad1ee593b10856
record_format	dspace
spelling	oai:doaj.org-article:64843f78f4834b028aad1ee593b108562021-11-22T04:22:35ZApplication of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism2090-447910.1016/j.asej.2021.03.028https://doaj.org/article/64843f78f4834b028aad1ee593b108562021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2090447921002070https://doaj.org/toc/2090-4479In the current research, a newly developed ensemble intelligent predictive model called Bagging Regression (BGR) is proposed to predict the compressive strength of a hollow concrete masonry prism (fp). A matrix of input combinations is constructed based on several predictive variables, including mortar compressive strength (fm), concrete block compressive strength (fb), and height to thickness ratio (h/t). Three modeling scenarios based on the different data divisions (i.e., 80–20%, 75–25%, and 70–30%) for training-testing phases are evaluated. The proposed model is validated against classical support vector regression (SVR) and decision tree regression (DTR) models using statistical indicators and graphical presentations. Results indicate the superiority of the BGR over the other models. In quantitative terms, BGR attains minimum root mean square error (RMSE = 1.51 MPa) using the data division scenario of 80–20% in the testing phase, while DTR and standalone SVR models offer RMSE = 2.55 and 2.33 MPa, respectively.Ahmad SharafatiSeyed Babak Haji Seyed AsadollahNadhir Al-AnsariElsevierarticleHollow concrete block masonry prismsBagging regression modelCompressive strength predictionData divisionEngineering (General). Civil engineering (General)TA1-2040ENAin Shams Engineering Journal, Vol 12, Iss 4, Pp 3521-3530 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hollow concrete block masonry prisms Bagging regression model Compressive strength prediction Data division Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Hollow concrete block masonry prisms Bagging regression model Compressive strength prediction Data division Engineering (General). Civil engineering (General) TA1-2040 Ahmad Sharafati Seyed Babak Haji Seyed Asadollah Nadhir Al-Ansari Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
description	In the current research, a newly developed ensemble intelligent predictive model called Bagging Regression (BGR) is proposed to predict the compressive strength of a hollow concrete masonry prism (fp). A matrix of input combinations is constructed based on several predictive variables, including mortar compressive strength (fm), concrete block compressive strength (fb), and height to thickness ratio (h/t). Three modeling scenarios based on the different data divisions (i.e., 80–20%, 75–25%, and 70–30%) for training-testing phases are evaluated. The proposed model is validated against classical support vector regression (SVR) and decision tree regression (DTR) models using statistical indicators and graphical presentations. Results indicate the superiority of the BGR over the other models. In quantitative terms, BGR attains minimum root mean square error (RMSE = 1.51 MPa) using the data division scenario of 80–20% in the testing phase, while DTR and standalone SVR models offer RMSE = 2.55 and 2.33 MPa, respectively.
format	article
author	Ahmad Sharafati Seyed Babak Haji Seyed Asadollah Nadhir Al-Ansari
author_facet	Ahmad Sharafati Seyed Babak Haji Seyed Asadollah Nadhir Al-Ansari
author_sort	Ahmad Sharafati
title	Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
title_short	Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
title_full	Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
title_fullStr	Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
title_full_unstemmed	Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
title_sort	application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/64843f78f4834b028aad1ee593b10856
work_keys_str_mv	AT ahmadsharafati applicationofbaggingensemblemodelforpredictingcompressivestrengthofhollowconcretemasonryprism AT seyedbabakhajiseyedasadollah applicationofbaggingensemblemodelforpredictingcompressivestrengthofhollowconcretemasonryprism AT nadhiralansari applicationofbaggingensemblemodelforpredictingcompressivestrengthofhollowconcretemasonryprism
_version_	1718418225672224768

Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism

Ejemplares similares