Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Anhui Normal University(Natural Science)》 2018-02
Add to Favorite Get Latest Update

Extreme Learning Machine-Based Network Traffic Classification and Visualization

CHEN Xing-ru;WEI Shu-ning;School of Information Science and Engineering,Hunan Normal University;  
Accurate network traffic classification is of fundamental importance to network traffic measurement and analysis. Machine learning takes use of various characteristics instead of depending on port numbers and protocol details.The paper takes ELM and H-ELM as the main algorithm which to be used in client or server recognition. The multiple layer network traffic data visualization can be real through data analysis of link layer,network layer and application layer.Comparing H-ELM to ELM,the results of experiment show that ELM algorithm can be used in classification effectively and the classification based on ELM model has many advantages of quite high accuracy and training speed and H-ELM improves the overall learning performance by removing redundancy of the original inputs with compact features.
【Fund】: 湖南省教育厅一般项目(531120);; 湖南师大教改项目(1210786);湖南师大自然科学研究项目(160432)
【CateGory Index】: TP181;TP393.06
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved