期刊名称：Oriental Journal of Computer Science and Technology
印刷版ISSN：0974-6471
出版年度：2010
卷号：3
期号：1
页码：155-159
出版社：Oriental Scientific Publishing Company
摘要：The earlier approaches are relied upon various datasets for detecting network attacks. A hugedataset (size of 744 MB data with 4,940,000 records ) was used for ascertaining network attacks. Theprocessing becomes time costly. The reduction and formulation of representive dataset from initialdataset is important. The computational complexity is reduced through the process of Rough-settheory and by utilizing the logic of correlation, functional dependency and closure property. Acomparative analysis is performed on an experimental basis and the results are validated and theirpurity/perfectionality is measured by the aid of SVM (Support Vector Machine ) comparatively
关键词：Intrusion Data Set; Correlation; Functional Dependency; Closer Property; Cardinality
