@inproceedings{9e6060a754aa4b4bb0a59ff043489baf,
title = "Fuzzy Kernel k-Medoids algorithm for anomaly detection problems",
abstract = "Intrusion Detection System (IDS) is an essential part of security systems to strengthen the security of information systems. IDS can be used to detect the abuse by intruders who try to get into the network system in order to access and utilize the available data sources in the system. There are two approaches of IDS, Misuse Detection and Anomaly Detection (behavior-based intrusion detection). Fuzzy clustering-based methods have been widely used to solve Anomaly Detection problems. Other than using fuzzy membership concept to determine the object to a cluster, other approaches as in combining fuzzy and possibilistic membership or feature-weighted based methods are also used. We propose Fuzzy Kernel k-Medoids that combining fuzzy and possibilistic membership as a powerful method to solve anomaly detection problem since on numerical experiment it is able to classify IDS benchmark data into five different classes simultaneously. We classify IDS benchmark data KDDCup'99 data set into five different classes simultaneously with the best performance was achieved by using 30 % of training data with clustering accuracy reached 90.28 percent.",
author = "Zuherman Rustam and Talita, {A. S.}",
note = "Publisher Copyright: {\textcopyright} 2017 Author(s).; 2nd International Symposium on Current Progress in Mathematics and Sciences 2016, ISCPMS 2016 ; Conference date: 01-11-2016 Through 02-11-2016",
year = "2017",
month = jul,
day = "10",
doi = "10.1063/1.4991258",
language = "English",
series = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",
editor = "Sugeng, {Kiki Ariyanti} and Djoko Triyono and Terry Mart",
booktitle = "International Symposium on Current Progress in Mathematics and Sciences 2016, ISCPMS 2016",
}