Intrusion Detection System Based On Improved One versus All Data Stream Classification
Komal Gandle1, Pallavi Kulkarni2
1Ms. Komal Gandle, Assistant Professor, Information Technology Dept. Government College of Engineering, Aurangabad (M.S.) India.
2Mrs. Pallavi Kulkarni, Assistant Professor, Computer Science & Engineering Dept. Government College of Engineering, Aurangabad (M.S.) India.
Manuscript received on November 27, 2013. | Revised Manuscript received on December 13, 2013. | Manuscript published on December 30, 2013. | PP: 256-259 | Volume-3, Issue-2, December 2013. | Retrieval Number: B2464123213/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: With the marvelous development of information Technology & Network Security the Intrusion Detection (ID) has rapidly become a crucial component of any network defense strategy. Data Stream Classification is the superlative method for revealing of Intrusion Detection (ID). Improved One Versus All (OVA) is one of the multiclass classification techniques On the basis of this we propose the system on Network Intrusion Detection (NID) for security in network as well as computer. In this paper, improved one versus all decision tree algorithms identifies the behavioral attacks actions and newly arising attacks of intrusions. This paper addresses the excellent advantages of Improved OVA data stream classification such as Low error correlation and concept change. Also propose a new learning algorithm for illuminating of network intrusion Detection.
Keywords: Improved OVA decision tree, Intrusion Detection (ID).