Table 10 The accuracy of the proposed predictive models.
From: Compressive strength of nano concrete materials under elevated temperatures using machine learning
Method | Type of Data | MAE | MSE | RMSE | R | R2 |
|---|---|---|---|---|---|---|
WCA | Training | 3.094 | 17.344 | 4.165 | 0.964 | 0.930 |
Validation | 1.907 | 6.725 | 2.593 | 0.991 | 0.982 | |
Testing | 2.293 | 8.724 | 2.954 | 0.993 | 0.985 | |
GA | Training | 3.532 | 23.058 | 4.802 | 0.956 | 0.914 |
Validation | 2.716 | 12.384 | 3.519 | 0.986 | 0.973 | |
Testing | 2.940 | 20.707 | 4.551 | 0.987 | 0.974 | |
ANN | Training | 1.331 | 3.028 | 1.741 | 0.9941 | 0.9882 |
Validation | 1.635 | 4.027 | 2.006 | 0.9945 | 0.9892 | |
Testing | 2.404 | 10.2 | 3.194 | 0.9916 | 0.983 | |
FLM | Training | 1.181 | 2.317 | 1.522 | 0.995 | 0.989 |
Validation | 2.261 | 8.081 | 2.8427 | 0.9948 | 0.9896 | |
Testing | 3.362 | 23.25 | 4.822 | 0.981 | 0.962 | |
MLR | Training | 6.390 | 56.499 | 7.5136 | 0.872234 | 0.760 |
Validation | 7.384 | 86.390 | 9.295 | 0.885 | 0.783 | |
Testing | 8.568 | 96.385 | 9.818 | 0.903 | 0.815 |
