基于支持向量数据描述的数据约简  

Data Reduction Based on Support Vector Data Description

作　　者：郑晓星[1] 吴今培[1] 

机构地区：[1]五邑大学智能技术与系统研究所,广东江门529020

出　　处：《现代电子技术》2007年第2期74-76,共3页Modern Electronics Technique

摘　　要：提出了一种基于支持向量数据描述(SVDD)的数据约简方法,该方法利用一类学习算法SVDD的特性,通过迭代优化运算有效地实现了对原始训练样本数据的约简。实验数据的结果表明,该方法简单易行,具有稳定性和准确性,能大大缩减原始训练集规模的同时保持原分类问题的识别精度。A new method of data reduction based on Support Vector Data Description （SVDD） is introduced in this paper. Using the characteristic of the one class learning method SVDD, the method can reduce the original train data effectively by the operation of optimization. The result of experiments shows that it is an easy to use,stable and Precise method that can reduce the scale of the original train data greatly and keep the classify problem＇s precision by the same time.

关 键 词：支持向量机 支持向量数据描述 数据约简 分类 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]