Paper Info
Title
A Feature Selection Approach for Network Intrusion Detection Based on Tree-Seed Algorithm and K-Nearest Neighbor
Abstract
Network intrusion detection is one of the hottest and most difficult issues in the field of network security. K-nearest neighbor technique is a kind of lazy classification algorithm which has been successfully applied to network intrusion detection. However, with the increase of the characteristic dimensions of network data, classification performance is significantly reduced. Considering that tree-seed algorithm(TSA)has good classification ability in reducing feature redundancy, it can be used in network intrusion detection. In the paper, the tree-seed algorithm(TSA) is introduced to extract the effective feature of the input data, and KNN is used for classification. A novel network intrusion detection model (KNN-TSA) based on K-nearest neighbor (KNN) and tree-seed algorithm (TSA) algorithm is proposed to select features to improve improve Classification efficiency of intrusion detection. This paper uses some data from UCI repository and KDD CUP 99 datasets to test the performance of the proposed model. Experimental results testify that the proposed model is able to remove the redundant features and reduce the input dimensions of classifier. In addition, it can improve the accuracy and efficiency of network intrusion detection.
Year
DOI
Venue
2018
10.1109/IDAACS-SWS.2018.8525522
2018 IEEE 4th International Symposium on Wireless Systems within the International Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS)
Keywords
DocType
ISBN
network security,intrusion detection,Tree-Seed algorithm,feature selection,k-Nearest Neighbor
Conference
978-1-5386-7588-5
Citations 
PageRank 
References 
0
0.34
4
Authors
5
Name
Order
Citations
PageRank
Feng Chen154.51
Zhiwei Ye2127.86
Chunzhi Wang38620.81
Lingyu Yan46814.95
Ruoxi Wang512.42