ISSN: 2319-7293
P.Kumaraguru, V.R.Prakash & M.Abraham
The area of internet traffic classification has advanced rapidly over the last few years due to a dramatic increase in the number and variety of applications running over the internet. These applications include www, e-mail, P2P, multimedia, FTP applications, Games etc. Since traditional internet traffic classification techniques become ineffective for certain complicated applications which use dynamic port number instead of well-known port number and various encryption techniques to avoid detection by unauthorised third party, therefore Machine Learning (ML) techniques are developed to handle such problems in internet traffic classification. Neural Networks are also one of the important ML techniques. In this paper, Radial Basis Function Neural Networks (RBFNN) are employed for internet traffic classification which is a type of multilayer feed forward neural network. In this research work, Performance of RBFNN is analysed based upon accuracy, recall, number of hidden layer neurons and training time of network using large feature data set and reduced feature data set . This experimental analysis shows that RBFNN is an efficient technique for offline internet traffic classification for reduced feature data sets too.