Fusion of Statistic, Data Mining and Genetic Algorithm for feature selection in Intrusion Detection

Abstract

The security of information and data is a critical issue in a computer networked environment. In our society computer networks are used to store proprietary information and to provide services for organizations and society. So in order to secure this valuable information from unknown attacks (intrusions) need of intrusion detection system arises. There are many intrusion detection approaches focused on the issues of feature reduction as some of the features are irrelevant or redundant which results in lengthy detection process and degrading the performance of an IDS. So in order to design lightweight IDS we investigate the performance of three feature selection approaches CFS, Information Gain and Gain Ratio. In this paper we propose a fusion model by making use of the three standard algorithms and finally applying genetic algorithm that identify important reduced input features. We apply Naive Bayes classifier on the dataset for evaluating the performance of the proposed method over the standard ones. The reduced attributes shows that proposed algorithm give better performance that is efficient and effective for detecting intrusions

Authors and Affiliations

MeghaAggarwa , Amrita

Keywords

Related Articles

Fault Tolerant Environment in web crawler Using Hardware Failure Detection  

Fault Tolerant Environment is a complete programming environment for the reliable execution of distributed application programs. Fault Tolerant Distributed Environment encompasses all aspects of modern fault-tolerant dis...

Performance Investigation of Two-Stage Operational Amplifier

As CMOS technology scaling down transistor channel lengths to satisfy the thrust of low power consumption in modern electronics system . There is need to investigate the performance of the upcoming scaled channel length...

A Survey on Image Mosaicing Techniques 

Image Mosaicing is a method of assembling multiple overlapping images of the same scene into a larger image. The output of the image mosaic will be the union of two input images. Image-mosaicing algorithms are used...

Design and Simulation of Throughput based QoS MANET Routing for K-color Multiple Packet Reception Devices 

Adhoc network is a self configuring mutually cooperated network of autonomous nodes. We consider the case of a Mobile Ad-Hoc Network (MANET), with nodes that have multiple packet reception (MPR) capability.MPR i...

A Maintainability Estimation Model and Metrics for Object-Oriented Design (MOOD)  

Maintainability is that phase which may help the designer for improving the quality of the software system before deliver to a customer. This paper uses a multivariate linear model, which estimates the maintainabil...

Download PDF file
  • EP ID EP115208
  • DOI -
  • Views 109
  • Downloads 0

How To Cite

MeghaAggarwa, Amrita (2013). Fusion of Statistic, Data Mining and Genetic Algorithm for feature selection in Intrusion Detection. International Journal of Advanced Research in Computer Engineering & Technology(IJARCET), 2(5), 1725-1731. https://europub.co.uk/articles/-A-115208