Prediction of Mine Gas Emission with Improved Particle Swarm Support Vector Machine
MENG Qian
MA Xiaoping
ZHOU Yan
Abstract：In this paper, a support vector regression algorithm based on the improved particle swarm optimization ( IPSO-SVR) was proposed. A chaotic map and grid partitioning method was introduced into the particle swarm optimization ( PSO) in order to avoid PSO from getting into local optimum. A prediction model for gas emission was established on the basis of IPSO-SVR, the results showed that the support vector regression prediction model for gas emission established on the basis of IPSO optimization algorithm had better prediction effect. The prediction effect of IPSO-SVR results was much better than that of the PSO-SVR algorithm and the generalized regression neural network ( GRNN) , so it can be used for the practical prediction of gas emission, this indicated that the proposed IPSO algorithm was an effective approach for the parameter optimization of SVR.
Keywords：supporting vector regression machinechaosparticle swarmprediction of gas emission
Publication Date：2015-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1-5 )