Research Article
Indirect Estimation of Swelling Pressure of Expansive Soil: GEP versus MEP Modelling
Table 5
Summary of papers regarding number of observations used for the development of AI models.
| Reference | Artificial intelligence model | Investigated material | Ratio of training/validation | Target variable | Number of input variables | Number of observations | Ratio of observations/input variables |
| Le et al. [122] | ANN | Soil | 70/30 | UCS | 6 | 118 | 19.67 | Pham et al. [123] | GEP | Soil | 67.7/32.3 | UCS | 11 | 1138 | 103.45 | Özdemir [124] | GP | Rock | 66.7/33.3 | UCS | 3 | 30 | 10 | Mozumder and Laskar [125] | ANN | Soil | 70/30 | UCS | 8 | 283 | 35.4 | Yan et al. [126] | GEP | Soil | 65/35 | Resilient modulus | 7 | 97 | 13.85 | Tinoco et al. [127] | ANN and SVM | Soil | — | UCS | 9 | 444 | 49.33 | Eyo et al. [128] | ANN and its metaheuristics | Soil | 75/25 | Expansion | 9 | 517 | 57.44 | Current study | GEP and MEP | Soil | 70/30 | Swelling pressure | 10 | 200 | 20 |
|
|