作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2006, Vol. 32 ›› Issue (20): 7-9,12. doi: 10.3969/j.issn.1000-3428.2006.20.003

• 博士论文 • 上一篇    下一篇

基于支持向量数据描述的预警技术及其应用

林 健1,2,彭敏晶1,2   

  1. (1. 华南理工大学工商管理学院,广州 510641;2. 五邑大学系统科学与技术研究所,江门 529020)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2006-10-20 发布日期:2006-10-20

SVDD Based Early Warning Technique and Its Application

LIN Jian1,2, PENG Minjing1,2   

  1. (1. School of Business Administration, South China University of Technology, Guangzhou 510641; 2. Institute of Systems Science & Technology, Wuyi University, Jiangmen 529020)
  • Received:1900-01-01 Revised:1900-01-01 Online:2006-10-20 Published:2006-10-20

摘要: 分析当前的主要预警方法,指出由于缺少非正常数据样本,使得现有的大部分预警方法不适用。为解决该问题,提出了基于核方法的支持向量数据描述预警技术。建立了一个用于检测非正常数据对象的一类分类器,检测数据对象是否在正常值超球体范围内。如果在超球体外,预警专家将最终确认这个数据对象是否为非正常的预警警兆。以广东省江门市的宏观区域经济数据为例,证明了该预警技术的有效性。

关键词: 预警, 支持向量数据描述, 核方法, 数据样本

Abstract: After reviewing the current early warning researches, this paper presents that most of current early warning methods are unsuitable because of lacking a historical “ill-represented” dataset. And then the support vector data description early warning technique based on kernel method is proposed to solve the problem. A one-class classifier is fitted to detect the “ill-represented” data objects by enclosing all “good” data objects in a hypersphere. If an object is outside the boundary of the hypersphere, an early warning expert would be prompted to decide whether the object is enough “ill-represented” for issuing a warning. An early warning experiment based on the macro-economic dataset of Jiangmen, Guangdong is conducted to verify the proposed technique.

Key words: Early warning, Support vector data description (SVDD), Kernel method, Data feature

中图分类号: