期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2013
卷号：4
期号：1
页码：107-112
出版社：TechScience Publications
摘要：The growing rate of network attacks including hacker, cracker, and criminal enterprises have been increasing, which impact to the availability, confidentiality, and integrity of critical information data. Intrusion detection system have become a necessary addition to security infrastructure of most Organizations. Intrusion detection systems (IDS) take either network or host based approach for recognizing and deflecting attacks. Machine Learning includes a number of advanced statistical methods for handling regression and classification tasks.Methods include Support Vector Machines (SVM) for regression and classification, Naive Bayes for classification, and k-Nearest Neighbors (KNN) for regression and classification. Feature selection is a process that selects a subset of original features. Proposed a useful pre-processing step is to run your data through the following data cleaning routines.The proposed system is to enhance the Feature Selection process by using a new MLP based Feature Selection method. Supervised learning algorithms employ a collection of instances to estimate the class label of new input samples. The instances are generally represented by a number of attributes and a class value.In fact, some features can be redundant or irrelevant. By removing such redundant and irrelevant attributes, a classifier with higher predictive accuracy can often be obtained. The experimental results show better results and prediction accuracy.
