TY - JOUR
T1 - Efficient machine learning models for prediction of concrete strengths
AU - Nguyen, Hoang
AU - Vu, Thanh
AU - Vo, Thuc P.
AU - Thai, Huu Tai
PY - 2021/1/10
Y1 - 2021/1/10
N2 - In this study, an efficient implementation of machine learning models to predict compressive and tensile strengths of high-performance concrete (HPC) is presented. Four predictive algorithms including support vector regression (SVR), multilayer perceptron (MLP), gradient boosting regressor (GBR), and extreme gradient boosting (XGBoost) are employed. The process of hyperparameter tuning is based on random search that results in trained models with better predictive performances. In addition, the missing data is handled by filling with the mean of the available data which allows more information to be used in the training process. The results on two popular datasets of compressive and tensile strengths of high performance concrete show significant improvement of the current approach in terms of both prediction accuracy and computational effort. The comparative studies reveal that, for this particular prediction problem, the trained models based on GBR and XGBoost perform better than those of SVR and MLP.
AB - In this study, an efficient implementation of machine learning models to predict compressive and tensile strengths of high-performance concrete (HPC) is presented. Four predictive algorithms including support vector regression (SVR), multilayer perceptron (MLP), gradient boosting regressor (GBR), and extreme gradient boosting (XGBoost) are employed. The process of hyperparameter tuning is based on random search that results in trained models with better predictive performances. In addition, the missing data is handled by filling with the mean of the available data which allows more information to be used in the training process. The results on two popular datasets of compressive and tensile strengths of high performance concrete show significant improvement of the current approach in terms of both prediction accuracy and computational effort. The comparative studies reveal that, for this particular prediction problem, the trained models based on GBR and XGBoost perform better than those of SVR and MLP.
KW - Ensemble learning
KW - High performance concrete
KW - Multi-layer Perceptron
KW - Support vector machine
KW - Tree-based algorithms
UR - http://www.scopus.com/inward/record.url?scp=85092744807&partnerID=8YFLogxK
U2 - 10.1016/j.conbuildmat.2020.120950
DO - 10.1016/j.conbuildmat.2020.120950
M3 - Article
AN - SCOPUS:85092744807
VL - 266
JO - Construction and Building Materials
JF - Construction and Building Materials
SN - 0950-0618
IS - Part B
M1 - 120950
ER -