This paper presents a hybrid least squares support vector machine (LSSVM) and particle swarm optimization (PSO) techniques to predict the slope stability. A modified PSO algorithm is employed in selecting the optimal values of the LSSVM parameters to improve the forecasting accuracy. Two examples of slope stability are presented to validate the predictive capability of the PSO-LSSVM model presented in this paper. A detailed sensitivity analysis is designed and performed to find the optimum values of parameters of PSO in these two examples. The results show that the proposed PSO-LSSVM model is a feasible and efficient tool for predicting the slope stability with high accuracy.

Blasting is still an economical and viable method for rock excavation in mining and civil works projects. Ground vibration generated due to blasting is an undesirable phenomenon which is harmful for the nearby inhabitants and dwellings and should be prevented. In this study, an attempt has been made to predict the blast-induced ground vibration and frequency by incorporating rock properties, blast design and explosive parameters using the general regression neural network (GRNN) technique. To validate this methodology, the predictions obtained were compared with those obtained using the artificial neural network (ANN) model as well as by multivariate regression analysis (MVRA). Among all the methods, GRNN provides excellent predictions with a high degree of correlation.