Table 8 Comparative analysis for prediction of the CS of concrete.
From: Machine learning and interactive GUI for concrete compressive strength prediction
Reference | Best model | Dataset size | R2 | RMSE (MPa) | MAE (MPa) |
|---|---|---|---|---|---|
Feng et al. (2020)93 | AdaBoost | 1030 | 0.94 | 1.93 | 1.43 |
Hongwei et al. (2021)19 | Bagging regressor | 98 | 0.95 | 4.97 | 3.69 |
Yang et al. (2022)37 | RF | 471 | 0.89 | 4.71 | 3.26 |
Beskopylny et al. (2022)94 | KNN | 249 | 0.99 | 2.62 | 1.97 |
Liu (2022)91 | XGBoost | 60 | 0.999 | 1.372 | – |
Li and Song (2022)95 | GBDT | 204 | 0.942 | 3.077 | 2.507 |
Liang et al. (2023)86 | BP-GA | 190 | 0.947 | 5.8 | 4.49 |
Satish et al. (2023)92 | XGBoost | 633 | 0.95 | 3.06 | 2.13 |
Elhishi et al. (2023)88 | XGBoost | 1030 | 0.91 | 4.37 | 3.04 |
Present study | CatBoost | 1030 | 0.966 | 3.06 | 2.27 |
