earticle

논문검색

Intrusion Detection by Using Hybrid of Decision Tree And K-Nearest Neighbor

초록

영어

In the modern age of information technology security of valuable asset become much important issue. Intrusion detection system plays a most important role in this area. It protects the system by attacks or threats by unauthorized access or person. The previous study has identified the need for more enhancements in the research of intrusion detection. This study gives the outline for intrusion detection and proposed a hybrid classification based method based on Decision Tree and K-Nearest Neighbor. This experiment perform on the bases of cross-10 fold validation techniques on the basis of decision tree and KNN classifiers and proposed hybrid classifier by using KDD cup dataset. Experimental result shows that the proposed idea gives good result as compared to individual base algorithms

목차

Abstract
 1. Introduction
 2. Literature Review
 3. Dataset Description
  3.1. Corrected KDD Dataset
  3.2. 10% KDD Dataset
 4. Decision Tree and K-Nearest Neighbor
 5. Ensemble Mathods
 6. Proposed Hybrid Algorithm
 5. Conclusion and Future Works
 References

저자정보

  • Bilal Ahmad Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
  • Wang Jian Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
  • Muhammad Shafiq Electronic Engineering Department, Sir Syed University of Engineering & Technology, Karachi, Pakistan

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.