Great Deluge Algorithm Feature Selection for Network Intrusion Detection

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Othman:2013:jasa,

• author = "Zulaiha Ali Othman and Lew Mei Theng and Suhaila Zainudin and Hafiz Mohd Sarim",
• title = "Great Deluge Algorithm Feature Selection for Network Intrusion Detection",
• journal = "Journal of Applied Science and Agriculture",
• year = "2013",
• volume = "8",
• number = "4",
• pages = "322--330",
• month = sep,
• keywords = "genetic algorithms, genetic programming, IDS, great deluge algorithm, feature selection, anomaly detection",
• ISSN = "1816-9112",
• annote = "The Pennsylvania State University CiteSeerX Archives",
• bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
• language = "en",
• oai = "oai:CiteSeerX.psu:10.1.1.1044.6495",
• rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.",
• URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1044.6495",
• URL = "http://www.aensiweb.com/old/jasa/rjfh/2013/322-330.pdf",
• size = "9 pages",
• abstract = "Intrusion detection systems (IDSs) deal with large amounts of data containing irrelevant and/or redundant features. These features result in a slow training and testing process, heavy computational resources, and low detection accuracy. Features selection, therefore, is an important issue in IDSs. A reduced features set improves the system accuracy and speeds up the training and testing process considerably. In this paper propose a wrapper-based feature selection techniques by using Great Deluge algorithm (GDA) as the search strategy to specify a candidate subset for evaluation, as well as using Support Vector Machine (SVM) as the classifier technique. The experiments used four random datasets collected from KDD-cup99. Each data set contains around 4000 records. The performance of the proposed technique has been evaluated based on classification accuracy by comparing with other feature selection techniques such as Bees Algorithm (BA), Rough-DPSO, Rough, Linear Genetic Programming (LGP), Support Vector Decision Function Ranking (SVDF), and Multivariate Regression Splines (MARS). The result shows that the feature subset produced by GDA yield high classification accuracy when compared with other techniques.",
• notes = "Data Mining & Optimization Group (DMO), Centre of Artificial intelligence Technology (CAIT), Faculty ofComputer Science, UniversitiKebangsaan Malaysia, Selangor, 43600 Malaysia",

}

Genetic Programming entries for Zulaiha Ali Othman Lew Mei Theng Suhaila Zainudin Hafiz Mohd Sarim

Citations