| 基于复合神经网络的网络业务分类算法 |
| |
| 引用本文： | 王兆霞,孙雨耕,张强,郝庭柱,孙小薇,秦娟,沈花玉.基于复合神经网络的网络业务分类算法[J].天津大学学报(自然科学与工程技术版),2006,39(Z1):121-124. |
| |
| 作者姓名： | 王兆霞 孙雨耕 张强 郝庭柱 孙小薇 秦娟 沈花玉 |
| |
| 作者单位： | 天津大学电气与自动化工程学院 天津300072(王兆霞，孙雨耕，张强)，天津理工大学光电信息与电子工程学院 天津300191(郝庭柱，秦娟，沈花玉)，桂林电子科技大学通信与信息工程系 桂林541004(孙小薇) |
| |
| 基金项目： | 教育部博士学科点基金(20030056007)，中国博士后科学基金项目(2005037529)，天津市高等学校科技发展基金项目(20041325)，天津理工大学育苗项目(LG03018)． |
| |
| 摘 要： | 针对目前计算机网络业务流管理问题,提出了一种基于复合神经网络的网络业务分类方案．将复合神经网络用于网络业务源特征提取与分类的研究中,打包法和BP算法结合用于复合神经网络的训练．并分析比较与单个神经网络和模糊神经网络算法用于网络业务分类效果．计算机仿真结果表明,复合神经网络分类收敛快、误差小,比单个神经网络算法和模糊神经网络算法更优越；同时,研究结果为解决网络业务源特征提取与分类提供了一种有效的途径．
|
| 关 键 词： | 复合神经网络 BP算法 网络业务 特征提取与分类 |
| 文章编号： | 0493-2137(2006)增刊-0121-04 |
| 修稿时间： | 2005年12月18 |
Algorithm of Classifying Network Traffic Using Ensemble Neural Networks |
| |
| WANG Zhao-xia SUN Yu-geng ZHANG Qiang HAO Ting-zhu SUN Xiao-wei QIN Juan SHEN Hua-yu .School of Electrical and Automation Engineering,Tianjin University,Tianjin ,China.Algorithm of Classifying Network Traffic Using Ensemble Neural Networks[J].Journal of Tianjin University(Science and Technology),2006,39(Z1):121-124. |
| |
| Authors: | WANG Zhao-xia SUN Yu-geng ZHANG Qiang HAO Ting-zhu SUN Xiao-wei QIN Juan SHEN Hua-yu School of Electrical and Automation Engineering Tianjin University Tianjin China |
| |
| Affiliation: | WANG Zhao-xia~1 SUN Yu-geng~1 ZHANG Qiang~1 HAO Ting-zhu~2 SUN Xiao-wei~3 QIN Juan~2 SHEN Hua-yu~2 1.School of Electrical and Automation Engineering,Tianjin University,Tianjin 300071,China, 2.Department of Opto-Electronics Information and Electronic Engineering,Tianjin University of Technology,Tianjin 300191,China, 3.Department of Communication and Information Engineering,Guilin University of Electronic Technology,Guilin 541004,China |
| |
| Abstract: | An algorithm of classifying network traffic based on ensemble neural networks is proposed in this pa- per.Ensemble neural networks(ENN)is used to study the feature extraction and classifying of the network traffic.Bagging and back-propagation algorithms are used for the training of ensemble neural networks.Com- pared with the non-ensemble neural networks(NN)and fuzzy neural networks(FNN),the simulation result demonstrates that ENN not only can be well applicable for classifying the network traffic,but also is superior to NN and FNN.This paper supplies the fundamental research to solve the problem of classifying network traffic. |
| |
| Keywords: | ensemble neural networks back-propagation algorithms network traffic feature extraction and classifying |
| 本文献已被 CNKI 等数据库收录！ |
