期刊文献+

基于惩罚加权支持向量机回归的径流预测模型 被引量:21

Runoff forecast based on weighted support vector machine regression model
原文传递
导出
摘要 径流预测是水文科学研究的重要内容。针对径流时间序列的特性,本文尝试建立了一种惩罚加权支持向量机回归的径流预测模型。通过与BP神经网络和标准支持向量机的结果进行比较,表明该模型预测精度更高,可以用于河川径流的中长期预测。 Runoff forecast is a fundamental part of hydrology.This paper proposes a penalty weighted support vector machine regression model to better describe the features of runoff time series.In comparison to BP neural network and standard support vector machine regression,this model is more accurate and suitable for mid-long term runoff forecast.
出处 《水力发电学报》 EI CSCD 北大核心 2012年第6期35-38,43,共5页 Journal of Hydroelectric Engineering
基金 国家自然科学基金资助项目(50679098) 国家科技支撑计划(2008BAB29B09)
关键词 水文学 径流预测 惩罚系数 惩罚加权支持向量机 hydrology runoff forecast penalty parameter penalty weighted support vector machine
  • 相关文献

参考文献8

  • 1杨旭,栾继虹,冯国章.中长期水文预报研究评述与展望[J].西北农业大学学报,2000,28(6):203-207. 被引量:61
  • 2ASCE Task Committee. Artificial neural networks in hydrology - I :Preliminary concepts [ J]. Journal of Hydrologic Engineering, 2000,5(2) :115-123. 被引量:1
  • 3ASCE Task Committee. Artificial neural networks in hydrology - ll: Hydrological applications [ J ]. Journal of Hydrologic Engineering, 2000,5 ( 2 ) : 124-137. 被引量:1
  • 4Cortes C, Vapnik V. Support-vector networks [ J ]. Machine Learning, 1995,20 ( 3 ) :273-297. 被引量:1
  • 5Vapnik V. The Nature of Statistical Learning Theory [ M ]. New York:Springer Verlag, 1999. 被引量:1
  • 6Smola A J, Schoelkopf B. A tutorial on support vector regression [ J]. Statistics and Computing,2004,14 : 199-222. 被引量:1
  • 7Hsu C W, Chang C C, Lin C J. A Practical Guide to Support Vector Classification [ R]. Technical report, Department of Computer Science and Information Engineering, National Taiwan University , 2003. 被引量:1
  • 8Francis E H Tay, L J Cao. Modified support vector machines in financial time series forecasting [ J]. Neurocomputing,48 (2002), 847-861. 被引量:1

二级参考文献23

共引文献60

同被引文献217

引证文献21

二级引证文献152

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部