计算机科学与探索 ›› 2009, Vol. 3 ›› Issue (3): 330-336.DOI: 10.3778/j.issn.1673-9418.2009.03.011

• 学术研究 • 上一篇    

多类别模糊补偿支持向量机新模型研究

邱晓红

  

  1. 江西农业大学 软件学院,南昌 330045
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-05-15 发布日期:2009-05-15
  • 通讯作者: 邱晓红

New SVM Model Based on Multi-classed Fuzzy Compensation

QIU Xiaohong

  

  1. School of Software, Jiangxi Agriculture University, Nanchang 330045, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-05-15 Published:2009-05-15
  • Contact: QIU Xiaohong

摘要: 提出了一种更一般化描述的多类别模糊补偿支持向量机(M-FSVM)算法,用它来解决经典支持向量机对类别分类误差的不均衡性问题。并在开源代码LibSVM的基础上实现了新算法,并应用于网络入侵检测。实验结果表明训练样本数目少的类别的分类精度得到了提高。

关键词: 支持向量机, 统计学习理论, 模式识别, 模糊集

Abstract: A new support vector machine (SVM) algorithm based on multi-classed fuzzy compensation (M-FSVM) is described in more general format to solve the classification training bias problem in the traditional SVM application. And the algorithm is programmed based on the LibSVM code and is used to classify the network intrusion data. The test results show that the small size class classifier precision is improved.

Key words: support vector machines, statistical learning theory, pattern recognition, fuzzy set