Predictive modelling of the M_R of subgrade cohesive soils incorporating CPT-related parameters through a soft-computing approach

Development of Artificial-Neural-Network-Based Permanent Deformation Prediction Model of Unbound Granular Materials Subjected to Moving Wheel Loading

“…To reduce the complexity of the model and avoid overfitting, the network size should be carefully selected in addition to collecting more training data, as well as using appropriate input variables [ 56 , 57 ]. In this study, certain criteria proposed in the literature were adopted to prevent the network from being overfitted, such as dividing the entire dataset into training and testing sets according to the pre-determined proportions of 80% and 20% [ 54 , 58 , 59 , 60 ], respectively. In addition, the ratio of the number of training samples to the number of free parameters should be at least greater than 30 [ 61 ].…”

Prediction of resilient modulus for subgrade soils based on ANN approach

“…Although most of these models can predict the resilient modulus of different soil samples, some problems, like low precision and high prediction bias, still remain [17] . With the popularization of artificial intelligence, some researchers tried to use the artificial neural network prediction method to predict the resilient modulus [17][18][19][20][21][22] . The regression coefficients k1, k2, and k3 of one MR model were estimated through three different ANN models established by NAZZAL and TATARI [19] .…”

“…To obtain the model coefficients of resilient modulus for plastic and nonplastic soils, two three-layered ANN models were performed by SAHA et al [17] . SADROSSADAT et al [21] established a new empirical equation through the experimental database and estimated resilient modulus by using gene expression programming approach. However, these ANN models are under-developed and have many defects now.…”