光滑支持向量分类机的收敛上界研究  

Upper bound of convergence for smooth support vector classifier

作　　者：李广明[1] 熊金志[1] 

机构地区：[1]东莞理工学院计算机学院,广东东莞523808

出　　处：《计算机应用》2009年第8期2243-2244,2249,共3页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60773050);广东省科技计划资助项目(2008B060600076)

摘　　要：Lee等人使用光滑技术,提出了光滑支持向量分类机模型(SSVM),但该分类机的收敛上界问题尚待解决。介绍了光滑支持向量分类机模型的原理,用集合论等方法证明模型SSVM的收敛性,然后得到收敛上界的计算公式。成功解决了光滑支持向量分类机的收敛上界问题。Lee et al. used smoothing technique to propose Smooth Support Vector Machine for classification（ SSVM）. However, the problem still exists in upper bound of the convergence. The principle of SSVM model was introduced. Rough Set （RS） theory was used to prove the global convergence of SSVM, and then a formula for computing the upper bound of convergence was deduced. Therefore, the problem of upper bound of convergence was successfully solved for SSVM.

关 键 词：分类 支持向量机 光滑 收敛上界 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]