Research Article
Optimising the Selection of Input Variables to Increase the Predicting Accuracy of Shear Strength for Deep Beams
Table 8
A comparison between the suggested models’ efficiency in the presence of GAITH.
| Model | Distribution of data in terms of relative error for each model | Training phase | Testing phase | 5% | 10% | 15% | 20% | 5% | 10% | 15% | 20% |
| | 81.67 | 95.00 | 96.67 | 99.44 | 32.61 | 57.61 | 72.83 | 83.70 | | 63.33 | 77.78 | 89.44 | 93.89 | 31.52 | 46.74 | 63.04 | 71.74 | | 26.67 | 45.56 | 61.11 | 70.56 | 19.57 | 38.04 | 50.00 | 61.96 | | 33.89 | 60.56 | 77.22 | 86.67 | 20.65 | 44.57 | 60.87 | 70.65 | | 82.22 | 95.56 | 97.22 | 99.44 | 33.70 | 62.78 | 77.91 | 86.78 | | 60.56 | 82.78 | 91.67 | 93.89 | 27.17 | 53.26 | 65.22 | 75.00 | | 25.56 | 45.00 | 61.67 | 70.56 | 19.57 | 38.04 | 52.17 | 61.96 | | 37.22 | 65.00 | 82.22 | 92.22 | 21.74 | 43.48 | 60.87 | 71.74 | | 80.56 | 93.89 | 97.78 | 99.44 | 30.43 | 60.87 | 77.17 | 85.87 | | 61.11 | 83.89 | 90.00 | 92.22 | 28.26 | 50.00 | 61.96 | 73.91 | | 27.22 | 45.56 | 60.00 | 71.67 | 21.74 | 39.13 | 48.91 | 63.04 | | 35.56 | 65.56 | 84.44 | 91.67 | 21.74 | 36.96 | 57.61 | 71.74 | | 66.67 | 91.11 | 97.22 | 98.89 | 33.70 | 60.87 | 78.26 | 85.87 | | 55.56 | 78.89 | 89.44 | 92.78 | 29.35 | 51.09 | 67.39 | 75.00 | | 25.00 | 41.11 | 61.11 | 72.78 | 18.48 | 40.22 | 51.09 | 63.04 | | 51.67 | 81.67 | 92.78 | 97.22 | 22.83 | 48.91 | 66.30 | 72.83 | | 23.33 | 42.22 | 61.67 | 75.00 | 16.30 | 39.13 | 52.17 | 68.48 | | 57.22 | 74.44 | 85.00 | 90.56 | 18.48 | 35.87 | 54.35 | 64.13 | | 16.11 | 33.33 | 43.33 | 56.11 | 14.13 | 29.35 | 42.39 | 57.61 | | 36.67 | 65.56 | 83.33 | 92.22 | 22.83 | 42.39 | 59.78 | 71.74 |
|
|