An integrated approach for network traffic analysis using unsupervised clustering and supervised classification
by Kothandapani Chokkanathan; S. Koteeswaran
International Journal of Internet Technology and Secured Transactions (IJITST), Vol. 9, No. 4, 2019

Abstract: Traffic analysis is a significant task to control the network traffic in heterogeneous manner. The unsupervised learning system fails to expand the supervised classification model for network analysis. Several data mining techniques employed to classify the network traffic pattern using unsupervised learning approach. However, the continuous evaluation of network traffic on multi-dimensional data is a difficult task. In order to solve this issue, an integrated K-means unsupervised clustering and supervised C4.5 Classification (KUC-SC) technique is designed. At first, K means unsupervised learning algorithms is applied in KUC-SC technique to form a 'k' number of clusters. After that, C4.5 is used to classify the data whether it is real-time or non-real-time traffic through the construction of decision-tree. An experimental result shows that the KUC-SC technique obtains better performance in terms of classification accuracy, classification time, true positive rate and communication overhead compared to the state-of-the-art works.

Online publication date: Tue, 08-Oct-2019

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Internet Technology and Secured Transactions (IJITST):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com