Figure 4
The workflow diagram shows a process beginning with data collection followed by data preprocessing. The dataset is separated into training data and testing data and proceeds to feature scaling. The prepared data are used for model training and testing using feed forward and recurrent neural network models. Model optimization and evaluation follow the training stage. Model validation includes evaluation metrics M S E, R M S E, M A E, and R 2. The workflow ends with selection of the optimum model.Process of analysis using ANN for the prediction of stabilized soil properties
Source: Author’s own work