Self-Learning Network Traffic Classification
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2015, Vol 3, Issue 8
Abstract
Network management is part of traffic engineering and security. The current solutions - Deep Packet Inspection (DPI) and statistical classification rely on the availability of a training set. In case of these there is a cumbersome need to regularly update the signatures. Further their visibility is limited to classes the classifier has been trained for. Unsupervised algorithms have been envisioned as an alternative to automatically identify classes of traffic. To address these issues Unsupervised Self Learning Network Traffic Classification is proposed. It uses unsupervised algorithms along with an adaptive seeding approach to automatically let classes of traffic to emerge, making them identified and labelled. Unlike traditional classifiers, there is no need of a-priori knowledge of neither signatures nor a training set to extract the signatures. Instead, Unsupervised Self Learning Network Traffic Classification automatically groups flows into pure (or homogeneous) clusters using simple statistical features. This label assignment (which is still based on some manual intervention) ensures that class labels can be easily discovered. Furthermore, Unsupervised Self Learning Network Traffic Classification uses an iterative seeding approach which will boost its ability to cope with new protocols and applications. Unlike state-of-art classifiers, the biggest advantage of Unsupervised Self Learning Network Traffic Classification is its ability to discover new protocols and applications in an almost automated fashion.
Authors and Affiliations
Vandana M, Sruthy Manmadhan
Keywords
Related Articles
- EP ID EP21170
- DOI -
- Views 225
- Downloads 5
Review on the Effect of Uniaxial Forces on Moony Rivline Hyperelastic Material Model
Analytical material models do not entirely describe the stress-strain relationship in a material under all loading conditions. Therefore, experimental data needs to be created such that a reasonable material model may b...
A study of manet, attacks on it and defencing against packet dropping
Mobile ad-hoc network is a self configuring infrastructure, rapidly deployable, less time consuming and a mobile networks , due to which it is applied in various fields. But there are number of attacks that affect the n...
Efficient Processing of Top-K Preference Queries on Incomplete Information
Incomplete data is general, finding and scrutinizing these kind of data is basic starting late. The top k overwhelming (TKD) queries return k challenges that supersedes most extraordinary number of things in a given dat...
A Novel Method of Induction Motor Speed Control Using PLC
In any industry the induction motor plays an important role due to its low cost and simplicity. In the existing system motor speed is monitoring by HMI (Human Machine Interface). Due to this system, all parameters of mo...
Assessment of Heavy Metals Levels in Some Commonly Consumed Species of Prawns in Southwestern Nigeria
Three different kinds of prawns (Macrobrachium Felicium (MF), Macrobrachium macrobrachium (MM) and Demoscaris Trispinose (DT)) were collected from Ilaje (water side) area of Ondo State, Nigeria. The concentrations of he...