期刊文献+

基于核路径算法的支持向量回归机参数选择 被引量:2

Parameter Selection of Support Vector Regression Based on the Kernel Path Algorithm
下载PDF
导出
摘要 参数选择是支持向量机研究领域的重要问题。针对核参数的选择,提出一种基于二分法的核参数解路径算法。由于解为核参数的非线性光滑函数,该算法随着参数的更新,可以在已有参数得出的解的基础上通过更新公式进行推导计算,从而求得当前参数所对应的解,其目标函数的极值所对应的参数值即为最优参数解。该算法可以快速地求得最优参数。将该方法应用于双酚A生产过程的质量指标软测量建模,仿真结果表明了该算法的可行性和有效性。 Parameters selection problem in support vector machines is discussed. A solution path algorithm with respect to kernel parameter based on the bisection method is proposed. The path is a piecewise smooth function of the kernel parameter. As the update of the parameter, the current solution is computed based on an already obtained one, and the value of the parameter which is correlated with the extreme value of the target function is the optimal one. And this algorithm can obtain the optimal parameter quickly. The proposed algorithm is used in a soft-sensor model for the Bisphenol-A productive process, and the simulation results show the feasibility and effectiveness of the algorithm.
作者 杨慧中 王芳
出处 《控制工程》 CSCD 北大核心 2009年第1期23-26,87,共5页 Control Engineering of China
基金 国家自然科学基金资助项目(60674092) 江苏省高技术研究基金资助项目(工业部分)(BG2006010)
关键词 支持向量回归机(SVR) 参数选择 核路径算法 软测量 support vector regression (SVR) parameter selection kernel path algorithm soft-sensor
  • 相关文献

参考文献9

  • 1Vapnik V. The nature of statistical learning theory (2nd Edition) [ M]. New York: Springer-Verlag, 1999 : 138-167.
  • 2Chapelle O, Vapnik V, Bousquet O,et al. Choosing multiple parameters for support vector machine[ J]. Machine Learning, 2002,46(1) :131-160.
  • 3Keerthi S, Sindhwani V,Chapelle O. An efficient method for gradient-based adaption of hyperparameter in SVM models [ C ]// Advances in Neural Information Processing Systems 19 (NIPS-06) , Cambridge, MA : MIT Press ,2007.
  • 4邵信光,杨慧中,陈刚.基于粒子群优化算法的支持向量机参数选择及其应用[J].控制理论与应用,2006,23(5):740-743. 被引量:128
  • 5Efron B, Hastie T, Johnstone I,et al. Least angle regression [ J ]. Annals of Statistics, 2004,32 (2) :407-499.
  • 6Hastie T, Rosset S,Tibshirani R. The entire regularization path for the support vector machine [ J ]. Journal of Machine Learning Research ,2004,5 ( 1 ) : 1391-1415.
  • 7Wang G, Yeung D, Lochovsky F. Two-dimensional solution path for support vector regression [ C ]. Pittsburgh, Pennsylvania: ACM International Conference Proceedings Series, 2006.
  • 8Wang G, Yeung D, Lochovsky F. A kernel path algorithm for support vector machines [ C ]// Proceedings of the 24th International Conference on Machine Learning ( ICML-07 ), Corvallis, Oregon : ACM International Conference Proceedings Series,2007:951-958.
  • 9Chang C, Lin C. LIBSVM: a library for support vector machines [OL/DB ]. http://www.csie. ntu. edu. tw/-cjlin/L: bsvm/, 2007-11-29.

二级参考文献11

  • 1邵信光,杨慧中,石晨曦.ε不敏感支持向量回归在化工数据建模中的应用[J].东南大学学报(自然科学版),2004,34(B11):215-218. 被引量:6
  • 2VAPNIK V N.The Nature of Statistical Learning Theory[M].New York:Springer-Veriag,1995.
  • 3SMOLA A J,SCHOLKOPF B.A tutorial on support vector regression[R].NeuroCOLT2 Technical Report NC2-TR-1998-030.London:Royal Holloway College,University of London,1998.
  • 4SANCHEZ A D.Advanced support vector machines and kernel methods[J].Neurocomputing,2003,55(1):5-20.
  • 5CHAPPELLE O,VAPNIK V,BOUSQUET O,et al.Choosing multiple parameters for support vector machines[J].Machine Learning,2002,46(1):131-160.
  • 6CHEN Pengwei,WANG Jungying,LEE Hahnming.Model selection of SVMs using GA approach[C]//Proc of 2004 IEEE Int Joint Conf on NeuralNetworks.Piscataway,NJ:IEEE Press,2004:2035-2040.
  • 7ZHENG Chunhong,JIAO Licheng.Automatic parameters selection for SVM based on GA[C]//Proc of the 5th World Congress on Intelligent Control and Automation.Piscataway,NJ:IEEE Press,2004:1869 -1872.
  • 8KENNEDY J,EBERHART R.Particle swarm optimization[C] //Procof IEEE Int Conf on Neural Networks,Perth,Australia.Piscataway,NJ:IEEE Press,1995:1942-1948.
  • 9EBERHART R,KENNEY J.A new optimizer using particle swarm theory[C]//Proc of the Sixth International Symposium on Micro Machine and Human Science,Nagoya,Japan.Piscataway,NJ:IEEE Press,1995:39-43.
  • 10VANDEN B F,ENGELBRECHT A P.Training product uhit networks using cooperative particle swarm optimizers[C]]//Proc of the Third Genetic and Evolutionary Computation Conference (GECCO),San Francisco,USA.Piscataway,NJ:IEEE Press,2001:126-132.

共引文献127

同被引文献11

引证文献2

二级引证文献5

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