Parameter optimization of LS-SVM base on PSO prediction of field intensity in mine tunnel

DOI

10.2991/wartia-16.2016.301How to use a DOI?

Keywords

mine tunnel, field intensity, prediction, PSO-LSSVM

Abstract

The least squares support vector machines to solve small sample, nonlinear show some advantages, is very suitable for prediction of complex field intensity in mine tunnel , but the choice of kernel function and parameters for predicting the results have greater impact .PSO optimizing LSSVM parameters can improve prediction accuracy and generalization ability of the model. In this paper, in order to improve accuracy of prediction of field intensity in mine tunnel, PSO optimize the parameters of LS-SVM algorithm is adopted to the prediction of field intensity in mine tunnel .and the prediction results are compared with the results of normal LS-SVM and BP neural network. The simulation results show that the PSO-LSSVM prediction of field intensity in mine tunnel is more efficient and accurate. For complex prediction of field intensity in mine tunnel theory has guiding significance.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xunhong Li
AU  - Jinli Wu
PY  - 2016/05
DA  - 2016/05
TI  - Parameter optimization of LS-SVM base on PSO prediction of field intensity in mine tunnel
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 1477
EP  - 1482
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.301
DO  - 10.2991/wartia-16.2016.301
ID  - Li2016/05
ER  -