基于网格搜索的支持向量机核函数参数的确定Identifying the Parameters of the Kernel Function in Support Vector Machines Based on the Grid-Search Method
王兴玲,李占斌
摘要(Abstract):
为提高支持向量机的分类准确率,研究了支持向量机核函数的参数确定问题,得到了1种确定支持向量机核函数的参数的有效途径。利用网格搜索法可使各组核函数参数相互解耦,从而便于并行计算,提高了运行效率。将此方法用于测井岩性分类器的训练得到了较理想的仿真结果。
关键词(KeyWords): 支持向量机;核函数;网格搜索
基金项目(Foundation): 深海热液沉积物保真采样系统(0408-7A008)资助
作者(Author): 王兴玲,李占斌
DOI: 10.16441/j.cnki.hdxb.2005.05.032
参考文献(References):
- [1]Cortes C,Vapnik V.Support-vector networks[J].Machine Learn-ing,1995,20(3):273-297.
- [2]Vapnik V N.Statical Leaming Theory[M].New York:John Wiley&Sons lnc,1998.
- [3]张学工.关于统计学习理论与支持矢量机[J].自动化学报,2000,26(1):32-42.
- [4]Kulkarni A,Jayaraman V K,Kulkarni B D.Support vector classifica-tion with parameter tuning assisted by agent-based technique[J].Computers and Chemical Engineering,2004,28(3):311-318.
- [5]Pal M,Jayaraman V K,Kulkarni B D.Support vector machines forclassification in remote sensing[J].International Journal of RemoteSensing,2005,26(5):1007-1011.
- [6]冯天谨.神经网络技术[M].青岛:青岛海洋大学出版社,1994.187-189.
- [7]Knerr S,Personnaz L,Dreyfus G.Single-layer learning revisited:astepwise procedure for building and training a neural network[M].Neurocomputing:Algorithms,Architectures and Applications.Springer-Verlag,1990.
文章评论(Comment):
|
||||||||||||||||||
|