期刊文献+

SVR模型参数选择方法的研究 被引量:8

Research on Parameters Selection Method of SVR Model
在线阅读 下载PDF
导出
摘要 对时间序列预测问题进行了讨论。首先对支持向量机的回归算法进行了较详细的介绍,接着讨论了模型参数对预测结果的影响,并通过太阳黑子数据加以验证,最后提出了人工选择参数的方法。 The problem of time series prediction is discussed.Firstly,the algorithm of support vector regression(SVR) is introduced in detail.Then the influence of model parameters on prediction results is discussed and it is verified through sunspots dataset.Finally,the method for artificial parameter selection is proposed.
出处 《计算机时代》 2009年第11期53-55,共3页 Computer Era
关键词 支持向量机 统计学习 支持向量回归 参数选择 时间序列预测 support vector machine statistical learning support vector regression parameter selection time series prediction
  • 相关文献

参考文献6

二级参考文献27

  • 1刘勇 康力山.非数值并行算法(第二册)——遗传算法[M].北京:科学出版社,1997..
  • 2Vapnik Vladimir N. The Nature of Statistical Learning Theory [M]. Springer-Verlag, New York, Inc, 2000.
  • 3Burges J C. A Tutorial on Support Vector Machines for Pattern Recognition[M]. Kluwer Academic Publishers, Boston, 1999.
  • 4Joachime T. Estimating the Generalization Performance of a SVM Efficiently[M]. Informatik LSV Ⅲ, University Dortmund, 2001.
  • 5董春曦 饶鲜 杨绍全.支持向量机推广能力估计方法综述[A].第一届全国人工智能基础学术会议,2002..
  • 6Lunts A, Brailovskiy V. Evaluation of Attributes Obtained in Statistical Decision Rules[J]. Enginering Cybernetics, 1967,3:98-109.
  • 7Murphy P M, Aha Irvine D W. CA: University of California,Department of Information and Computer Science [ EB/OL ].http://www. ics. uci. edu/~ mlearn/MLRepository. html, 1994.
  • 8Scholkopf B,Mika S,Burges C et al.Input space vs.feature space in kernel-based methods [J].IEEE Transactions on Neural Networks, 1999; 10(5) : 1000-1017.
  • 9Duan K,Keerrthi S S,Poo A N.Evaluation of simple performance measures for turning svm hyperparameters [R].Control Division Technical Report CD-01-11 ,Department of Mechanical Engineering,National University of Singapore,2001-09.
  • 10Baudat G,Anouar F,Kemel-based methods and function appreximation[C].In:International Joint Conference on Neural Networks(IJCNN01), 2001 : 1244-1249.

共引文献2526

同被引文献78

引证文献8

二级引证文献74

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