Browsing by Author "Preecha Somwang"

Now showing 1 - 2 of 2
  • Default Image
    Item
    Anomaly detection based on GA&FART approach of computer network security
    (2012) Preecha Somwang; Woraphon Lilakiatsakun; Surat Srinoy; P. Somwang; Faculty of Information Science and Technology, Mahanakorn University of Technology, Bangkok, Cheumsampan Road, Thailand; email: preechak@nmc.ac.th
    The problems of intrusion detection in a computer network security are difficulty of having a protective line in the information security against attackers. Researchers have developed Intrusion Detection System (IDS) which is capable of detecting attacks in several available environments. This paper aims to provide the intrusion detection technique into the system by using integrates like the Genetic Algorithm (GA) with the Fuzzy Adaptive Resonance Theory (FART). The GA is applied to randomly select the best attribution and reduction to the featured space. The FART is used to classify different group of data: Normal and Anomalous. The results show that this proposed technique can improve the performance of anomalous detection, showing the high performance of the detection rate and minimizing the false alarm rate. The approach was evaluated on the benchmark data from KDDCup'99 data set.
  • Default Image
    Item
    Integrated soft computing for intrusion detection on computer network security
    (2011) Sirikanjana Pilabutr; Preecha Somwang; Surat Srinoy; S. Pilabutr; Faculty of Information Sciences, Nakhon Ratchasima College, Nakhon Ratchasima, Thailand; email: sirikanjana@nmc.ac.th
    Computer network security is very important for all business sectors. The Intrusion Detection Systems (IDS) is one technique that prevents an information system from a computer networks attacker. The IDS is able to detect behavior of new attacker which is indicated both correct Detection Rate and False Alarm Rate. This paper presents the new intrusion detection technique that applied hybrid of unsupervised/supervised learning scheme. To combine between the Independent Component Analysis (ICA) and the Support Vector Machine (SVM) are the advantage of these new IDS. The benefit of the ICA is to separate these independent components from the monitored variables. And the SVM is able to classify a different groups of data such as normal or anomalous. As a result, the new IDS are able to improve the performance of anomaly intrusion detection and intrusion detection. © 2011 IEEE.