Application of the PSO-SVM model for coal mine safety assessment

Abstract

Coal mine safety is a complex system, which is controlled by a number of interrelated factors and is difficult to estimate. Due to the various influences, coal mine safety assessment reveals highly nonlinear characteristics. Recently, support vector machine (SVM), with nonlinear mapping capabilities of forecasting, has been successfully employed to solve nonlinear classification problems. However, it is still lack of systematic approaches to determine appropriate parameter combination for a SVM model. This study applies particle swarm optimization (PSO) algorithm to choose the suitable parameter combination for a SVM model. A PSO-SVM model for coal mine safety assessment is developed. Calculating tests show that the PSO-SVM based model makes assessments much more accurate than the neural network (NN) based model does when the samples are limited.