Table 5 Estimated performance indices for the studied ML models in the testing stage.
From: Machine learning and interactive GUI for concrete compressive strength prediction
Type | Model | R2 | WI | RMSE (MPa) | SI | MAE (MPa) | MAPE | MBE (MPa) |
|---|---|---|---|---|---|---|---|---|
Non-ensemble | MLR | 0.609 | 0.865 | 10.40 | 0.175 | 8.13 | 0.312 | − 0.530 |
MNLR | 0.561 | 0.831 | 11.02 | 0.186 | 8.76 | 0.342 | − 0.480 | |
SVR | 0.590 | 0.862 | 10.65 | 0.157 | 8.16 | 0.307 | − 1.026 | |
GEP | 0.821 | 0.948 | 7.03 | 0.094 | 5.60 | 0.198 | − 0.316 | |
ANN* | 0.901 | 0.976 | 5.24 | 0.066 | 3.51 | 0.135 | − 0.255 | |
ANFIS | 0.830 | 0.951 | 6.85 | 0.083 | 5.45 | 0.208 | 0.613 | |
Ensemble | RF | 0.932 | 0.981 | 4.35 | 0.067 | 3.12 | 0.117 | − 0.017 |
AdaBoost | 0.803 | 0.935 | 7.39 | 0.140 | 5.96 | 0.255 | − 1.485 | |
XGBoost | 0.951 | 0.987 | 3.69 | 0.052 | 2.63 | 0.098 | − 0.073 | |
CatBoost* | 0.966 | 0.991 | 3.06 | 0.042 | 2.27 | 0.083 | 0.129 |
