期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2015
卷号：23
期号：2
页码：61-64
DOI：10.14445/22312803/IJCTT-V23P114
出版社：Seventh Sense Research Group
摘要：In the past two decades, internet have experienced tremendous growth that has sped up a shift in computing environments from centralized computer systems to network information systems. A large volume of valuable information such as personal profiles, banking details and other valuable information is distributed and transferred through internet. Hence, network security has become a major concern than ever. Intrusion Detection Systems (IDSs) play a crucial role in detecting various kinds of attacks and defend our computer and data from them. Therefore, intrusion detection systems are effectively used for detecting intrusion accesses. Intrusion Detection Systems have been evolved over decades and various types of systems are currently available to identify and eradicate attacks based on different system conditions and different aptitudes. Many researchers have felt the importance of new techniques other than the ones which are currently uses. Towards this direction, data mining is considered to be very handy in achieving the desired results. Among many techniques fuzzyneural networks (FNN) are very promising in this field. In this paper we are proposing a novel approach that uses Feature Extraction Scheme, FuzzyNeural Networks, Kmeans clustering and Support Vector Machines (SVM) for better results using Kyoto2006+ dataset.
