Comparison between Support Vector Machine and Fuzzy C-Means as Classifier for Intrusion Detection System

Citations Over TimeTop 10% of 2018 papers

Abstract

In this globalization era, cybercrime has been entering every aspect through internet network. The development of Intrusion Detection System (IDS) is being studied deeply to solve the problem. There are several classifier algorithms for Intrusion Detection System such as Support Vector Machine (SVM) and Fuzzy C-Means (FCM). In this study, we will compare proposed model using both Support Vector Machine and Fuzzy C-Means to find a better result that increase accuracy of the network attacks. KDD Cup 1999 will be used to evaluate which algorithms work best. The results are very encouraging and show that SVM and FCM can be a useful tool for intrusion detection system. We found that SVM achieved 94.43% average accuracy rate while FCM achieved 95.09% average accuracy rate.

Related Papers

• → Network Intrusion Detection Based on Support Vector Machine(2009)65 cited
• → A comparison of feature selection methods for machine learning based automatic malarial cell recognition in wholeslide images(2016)19 cited
• A Hybrid Intrusion Detection System Based on C5.0 Decision Tree and One-Class SVM(2015)
• Abnormal Intrusion Detection System Based on Support Vector Machine(2011)