Table 11 The precision of AI- based prediction models.
From: Compressive strength of nano concrete materials under elevated temperatures using machine learning
Samples | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
|---|---|---|---|---|---|---|---|
Temperature | 500 | 700 | 500 | 500 | 800 | 800 | 800 |
Time of exposure | 1 | 1 | 1 | 2 | 2 | 2 | 2 |
%NAl | 2 | 0 | 1 | 1.5 | 1.5 | 0.5 | 0 |
%NCTs | 0 | 0.15 | 0.05 | 0 | 0 | 0.05 | 0.05 |
Experimental | 95.8 | 77.63 | 96.84 | 94.52 | 47.26 | 47.046 | 47.58 |
WCA Prediction | 96.68 | 82.47 | 96.82 | 92.36 | 45.28 | 45.26 | 43.63 |
GA Prediction | 97.49 | 78.89 | 97.14 | 92.28 | 48.70 | 51.16 | 48.07 |
ANN Prediction | 98.32 | 80.88 | 99.43 | 93.92 | 48.42 | 48.47 | 45.68 |
FL Prediction | 96.78 | 79.60 | 97.73 | 94.63 | 47.61 | 50.95 | 49.60 |
MLR Prediction | 89.57 | 77.12 | 90.41 | 83.66 | 60.92 | 61.76 | 61.67 |
