电信科学 ›› 2016, Vol. 32 ›› Issue (5): 105-113.doi: 10.11959/j.issn.1000-0801.2016132

• 研究与开发 • 上一篇    下一篇

基于可变特征空间SVM的互联网流量分类

钱亚冠1,关晓惠2,云本胜1,楼琼1,马鹏飞1   

  1. 1 浙江科技学院理学院,浙江 杭州 310023
    2 浙江水利水电学院,浙江 杭州 310018
  • 出版日期:2017-02-22 发布日期:2017-02-22
  • 基金资助:
    国家自然科学基金资助项目;国家自然科学基金资助项目;浙江省网络媒体云处理与分析工程技术中心开放课题资助项目

Internet traffic classification using SVM with flexible feature space

Yaguan QIAN1,Xiaohui GUAN2,Bensheng YUN1,Qiong LOU1,Pengfei MA1   

  1. 1 College of Science,Zhejiang University of Science and Technology,Hangzhou 310023,China
    2 Zhejiang University of Water Resources and Electric Power,Hangzhou 310018,China
  • Online:2017-02-22 Published:2017-02-22
  • Supported by:
    The National Natural Science Foundation of China;The National Natural Science Foundation of China;Education Department Foundation of Zhejiang Province

摘要:

支持向量机(support vector machine,SVM)是一类具有良好泛化能力的机器学习算法,适合应用于互联网动态环境下的流量分类问题。目前将SVM扩展到流量分类这样的多分类问题的方法主要有One-Against-All和One-Against-One方法。这些方法都基于单一的特征空间训练SVM两分类器,没有考虑到不同特征对不同流量类的不同区分能力,因此获得的分离超平面并不是最合理的。为此提出了可变特征空间的SVM集成方法,即为每个两分类 SVM 构建具有最优区分能力的独立特征空间,单独训练两分类 SVM,最后再利用One-Against-All和One-Against-One方法集成为多分类器。实验表明,与原来的单一特征空间的One-Against-All和One-Against-One集成方法相比,提出的方法能有效提高流量分类器分类精度和召回率,更易获得最优分离超平面。

关键词: 支持向量机, 可变特征空间, 流量分类

Abstract:

SVM is a typical machine learning algorithm with prefect generalization capacity,which is suitable for the internet traffic classification.At present,there are two approaches,One-Against-All and One-Against-One,proposed for extending SVM to multi-class problem like traffic classification.However,these approaches are both based on a unique feature space.In fact,the separating capacity of a special traffic feature is not similar to different applications.Hence,flexible feature space for extending SVM was proposed,which constructs independent feature space with optimal discriminability for each binary-SVM and trains them under their own feature space.Finally,these trained binary-SVM were ensemble by One-Against-All and One-Against-One approaches.The experiments show that the proposed approach can efficiently improve the precision and callback of the traffic classifier and easily obtain more reasonable optimal separating hyper-plane.

Key words: support vector machine, flexible feature space, traffic classification

No Suggested Reading articles found!