Research Article
Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts
Table 4
The performance of all regression models on the augmented dataset.
| | Metrics | Models | MAE | MSE | RMSE | R2 | RRMSE |
| DT | 8.63 | 186.98 | 13.67 | 57.77 | 0.25 | SVM | 10.5 | 175.7 | 13.26 | 60.31 | 0.24 | LR | 11.10 | 187.63 | 13.70 | 57.62 | 0.26 | KNN | 5.95 | 66.82 | 8.17 | 84.9 | 0.15 | LGBM | 6.06 | 66 | 8.12 | 85.09 | 0.15 | XGB | 5.65 | 54.62 | 7.39 | 87.66 | 0.13 | RF | 5.78 | 62.89 | 7.93 | 85.8 | 0.15 | ETR | 5.61 | 50.58 | 7.11 | 88.57 | 0.13 | BagXGB | 6.12 | 65.22 | 8.08 | 85.26 | 0.15 | BagETR | 6.24 | 62.89 | 7.93 | 85.79 | 0.15 | Voting | 5.39 | 49.03 | 7 | 88.92 | 0.13 |
|
|