Fig 1.
Boxplot describing input and output variable range.
Fig 2.
Correlation analysis of the input and output variables.
Table 1.
Detail of database collection.
Table 2.
Summary of the input and output variables.
Fig 3.
An ANN framework used in this research.
Fig 4.
Methodology flow chart.
Table 3.
Summary of different ANN characteristics and investigation parameters in this study.
Fig 5.
Performance of the ANN as a function of neuron count in two hidden layers, as measured by (a) mean R2 for the training and testing parts; (b) mean RMSE for the training and testing parts; and (c) mean MAE for the training and testing parts.
Fig 6.
Color-map of ANN with two hidden layers for the testing part in relation to (a) mean R2; (b) StD R2; (c) mean RMSE; (d) StD RMSE; (e) mean MAE; and (f) StD MAE.
Fig 7.
Convergence study of ANN [8–14–4–1] architecture in terms of (a) the R2 of the training and testing parts; (b) RMSE of the training and testing parts; (c) MAE of the training and testing parts.
Fig 8.
Experimental and predicted shear strength results in function of sample index for the training and testing datasets.
Fig 9.
Experimental and predicted shear strength results in the function of sample index for the training and testing datasets.
Fig 10.
Regression graphs for the case of the best predictor ANN-[9–17–1]: (a) training dataset; (b) testing dataset.
Table 4.
Values of the best performance evaluation criteria of ANN-SCG model [8–14–4–1] for training and testing dataset.
Table 5.
Comparison of different machine learning models for predicting compressive strength of concrete containing GGBFS.
Fig 11.
Feature importance of 8 variables used in this investigation.