In this study, the prediction performance of the artificial neural network (ANN) and multiple regression (MR) models in predicting the limit void ratios of coarse-grained soils was investigated and compared. The data available in the literature were collected and used to construct both two distinct ANN-1 and ANN-2 models and two distinct MR-1 and MR-2 models: ANN-1 and MR-1 for the prediction of minimum void ratio (emin) and ANN-2 and MR-2 for the prediction of maximum void ratio (emax) of coarse-grained soils. Two basic soil graining properties such as coefficient of uniformity (Cu) and mean grain size (D50) are utilized in the simulation of the feed forward ANN models with back propagation algorithm and the MR models.The emax and emin values predicted from both ANN and MR models were compared with the experimental values taken from the literature. Moreover, five performance indices i.e. the determination coefficient, variance account for, mean absolute error, root mean square error, and the scaled percent error were calculated to examine the prediction capacity of the ANN and MR models developed in this study. The performance indices calculated indicated that both ANN models showed better performance than both MR models. It has been demonstrated that both ANN models can be used satisfactorily to predict limit void ratio values of coarse-grained soils as a rapid inexpensive substitute for laboratory techniques.
In this study, artificial neural network (ANN) and multiple regression (MR) models were developed to predict the California Bearing Ratio (CBR) values of clayey soil stabilised with tyre buffings and lime. To achieve this, a series of the CBR tests were performed on clayey soil mixed with tyre buffings and lime in ratios of 0, 5, 10, and 15%, and 0, 2, 4, and 6% of dry weight of the specimens, respectively. The results of the CBR tests were used in the development of both models. The predicted CBR values from both ANN and MR models were compared with experimentally measured CBR values. It is found that the ANN model gives more reliable predictions than the MR model. Moreover, several performance indices called as the determination coefficient, variance account for, mean absolute error, root mean square error, and the scaled percent error were used as the criteria for measuring the performance of the ANN and MR models. Based on these indices, the proposed ANN model yielded better performance than MR model in predicting the CBR values of clayey soil stabilized with tyre buffings and lime.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.