Research Article
Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts
Table 3
The performance of all the regression models.
| | Metrics | Models | MAE | MSE | RMSE | R2 | RRMSE |
| DT | 6.08 | 129.58 | 11.38 | 54.8936 | 0.19 | SVM | 8.55 | 118.90 | 10.90 | 58.6104 | 0.20 | LR | 8.13 | 86.28 | 9.29 | 69.9663 | 0.17 | KNN | 4.59 | 38.36 | 6.19 | 86.6482 | 0.10 | LGBM | 4.87 | 38.32 | 6.18 | 86.6942 | 0.11 | XGB | 4.56 | 34.84 | 5.90 | 87.8705 | 0.10 | RF | 3.60 | 24.10 | 4.91 | 91.6111 | 0.09 | ETR | 3.46 | 22.83 | 4.78 | 92.0511 | 0.08 | BagXGB | 3.62 | 22.44 | 4.74 | 92.1885 | 0.08 | BagETR | 3.76 | 24.00 | 4.90 | 91.6450 | 0.08 | Voting | 3.42 | 21.74 | 4.66 | 92.4307 | 0.08 |
|
|