计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (6): 96-97.

• 学术探讨 • 上一篇    下一篇

回归型支持向量机改进算法及应用

丁 蕾1,陶 亮2   

  1. 1.安庆师范学院 物理与电气工程学院,安徽 安庆 246011
    2.安徽大学 计算机科学与技术学院,合肥 230039
  • 收稿日期:2007-06-12 修回日期:2007-08-13 出版日期:2008-02-21 发布日期:2008-02-21
  • 通讯作者: 丁 蕾

Improved algorithm and application of SVM for regression

DING Lei1,TAO Liang2   

  1. 1.Department of Physics and Electrical Engineering,Anqing Normal College,Anqing,Anhui 246011,China
    2.College of Computer Science and Technology,Anhui University,Hefei 230039,China
  • Received:2007-06-12 Revised:2007-08-13 Online:2008-02-21 Published:2008-02-21
  • Contact: DING Lei

摘要: 对用于回归估计的标准SVR算法加以改进,提出了回归型支持向量机的一种改进算法。并针对医学上胆固醇含量测定问题进行了回归估计。实验表明,该算法在运算速度和回归估计精度的稳定性上都明显优于标准算法,特别适于解决大规模样本问题。

Abstract: Based on the traditional support vector machine for regression,a improved algorithm of the SVM for regression is presented.The improved algorithm based methods are used to determine serum cholesterol levels in medical science.The experimental results show that the proposed methods are much better than the traditional algorithm in learning speed and stability of accuracy,be applied in solving large-scale problems especially.