Application of the Cuckoo Search Based SUPPORT Vector Machine for the Mean Monthly Runoff Forecasting

DOI

10.2991/itms-15.2015.74How to use a DOI?

Keywords

Mean monthly runoff forecast; support vector machine; cuckoo search; artificial neural network

Abstract

Support vector machine (SVM) which is at the forefront of current research due to its high accuracy was used in this paper to carry out mean monthly runoff forecasting. Cuckoo search (CS) was introduced to determine the SVM parameters (kernel parameter ( ) and penalty parameter (C)). Mean monthly runoff and monthly precipitation from 1952 to 2011 of Yichang station in the upper reaches of the Yangtze River were trained and tested. In order to evaluate the effectiveness of the proposed model, the data sets were also modeled using Artificial Neural Networks (ANN). The results indicate that the proposed model (cuckoo search based SVM) is more accurate compared to ANN. This study suggests new opportunities for runoff forecasting.

Copyright

© 2015, 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  - B. Xing
AU  - Y. Wang
AU  - G.D. Liu
AU  - Y.F. Ren
PY  - 2015/11
DA  - 2015/11
TI  - Application of the Cuckoo Search Based SUPPORT Vector Machine for the Mean Monthly Runoff Forecasting
BT  - Proceedings of the 2015 International Conference on Industrial Technology and Management Science
PB  - Atlantis Press
SP  - 311
EP  - 315
SN  - 2352-538X
UR  - https://doi.org/10.2991/itms-15.2015.74
DO  - 10.2991/itms-15.2015.74
ID  - Xing2015/11
ER  -