Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study
This paper aims at performing a comparative study to investigate the predictive capability of machine learning (ML) models used for estimating the compressive strength of self-compacting concrete (SCC). Seven prominent ML models, including deep neural network regression (DNNR), extreme gradient boos...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/20/3771 |
| _version_ | 1797471755397234688 |
|---|---|
| author | Nhat-Duc Hoang |
| author_facet | Nhat-Duc Hoang |
| author_sort | Nhat-Duc Hoang |
| collection | DOAJ |
| description | This paper aims at performing a comparative study to investigate the predictive capability of machine learning (ML) models used for estimating the compressive strength of self-compacting concrete (SCC). Seven prominent ML models, including deep neural network regression (DNNR), extreme gradient boosting machine (XGBoost), gradient boosting machine (GBM), adaptive boosting machine (AdaBoost), support vector regression (SVR), Levenberg–Marquardt artificial neural network (LM-ANN), and genetic programming (GP), are employed. Four experimental datasets, compiled in previous studies, are used to construct the ML-based methods. The models’ generalization capabilities are reliably evaluated by 20 independent runs. Experimental results point out the superiority of the DNNR, which has excelled other models in three out of four datasets. The XGBoost is the second-best model, which has gained the first rank in one dataset. The outcomes point out the great potential of the utilized ML approaches in modeling the compressive strength of SCC. In more details, the coefficient of determination (<i>R</i><sup>2</sup>) surpasses 0.8 and the mean absolute percentage error (MAPE) is always below 15% for all datasets. The best results of <i>R</i><sup>2</sup> and MAPE are 0.93 and 7.2%, respectively. |
| first_indexed | 2024-03-09T19:52:41Z |
| format | Article |
| id | doaj.art-f054ad564d684f5e959ba1ba572b9fb9 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T19:52:41Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-f054ad564d684f5e959ba1ba572b9fb92023-11-24T01:06:46ZengMDPI AGMathematics2227-73902022-10-011020377110.3390/math10203771Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset StudyNhat-Duc Hoang0Institute of Research and Development, Duy Tan University, Da Nang 550000, VietnamThis paper aims at performing a comparative study to investigate the predictive capability of machine learning (ML) models used for estimating the compressive strength of self-compacting concrete (SCC). Seven prominent ML models, including deep neural network regression (DNNR), extreme gradient boosting machine (XGBoost), gradient boosting machine (GBM), adaptive boosting machine (AdaBoost), support vector regression (SVR), Levenberg–Marquardt artificial neural network (LM-ANN), and genetic programming (GP), are employed. Four experimental datasets, compiled in previous studies, are used to construct the ML-based methods. The models’ generalization capabilities are reliably evaluated by 20 independent runs. Experimental results point out the superiority of the DNNR, which has excelled other models in three out of four datasets. The XGBoost is the second-best model, which has gained the first rank in one dataset. The outcomes point out the great potential of the utilized ML approaches in modeling the compressive strength of SCC. In more details, the coefficient of determination (<i>R</i><sup>2</sup>) surpasses 0.8 and the mean absolute percentage error (MAPE) is always below 15% for all datasets. The best results of <i>R</i><sup>2</sup> and MAPE are 0.93 and 7.2%, respectively.https://www.mdpi.com/2227-7390/10/20/3771self-compacting concretecompressive strengthdeep neural networkgradient boosting machinemachine learning |
| spellingShingle | Nhat-Duc Hoang Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study Mathematics self-compacting concrete compressive strength deep neural network gradient boosting machine machine learning |
| title | Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study |
| title_full | Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study |
| title_fullStr | Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study |
| title_full_unstemmed | Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study |
| title_short | Machine Learning-Based Estimation of the Compressive Strength of Self-Compacting Concrete: A Multi-Dataset Study |
| title_sort | machine learning based estimation of the compressive strength of self compacting concrete a multi dataset study |
| topic | self-compacting concrete compressive strength deep neural network gradient boosting machine machine learning |
| url | https://www.mdpi.com/2227-7390/10/20/3771 |
| work_keys_str_mv | AT nhatduchoang machinelearningbasedestimationofthecompressivestrengthofselfcompactingconcreteamultidatasetstudy |