How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
This paper presents a security information distribution architecture that allows decentralised adaptation and response to security threats. The inspiration for this work and its underlying principles lie in the human immune system and its mechanisms for adapting to and sharing information about threats. The architecture assumes that the network is...
This thesis has made advances in Distributed Self-Healing Security Systems (DSHSS) -- a tool for the future to defend against the problems faced by industrial automation computer networks, such as critical national infrastructure (CNI), Industrial Control System (ICS) and Supervisory Control and Data Acquisition (SCADA), caused by computer malware...
As network-based technologies become omnipresent, intrusion detection and prevention for these systems become increasingly important. This paper proposed a modified mutual information-based feature selection algorithm (MMIFS) for intrusion detection on the KDD Cup 99 dataset. The C4.5 classification method was used with this feature selection metho...
In this work, a new method for classification is proposed consisting of a combination of feature selection, normalization, fuzzy C means clustering algorithm and C4.5 decision tree algorithm. The aim of this method is to improve the performance of the classifier by using selected features. The fuzzy C means clustering method is used to partition th...
This dissertation project combines both research and software engineering for the investigation of gene expression data analysis using rough set theory based feature selection. The dissertation presents a rough set feature selection algorithm appropriate for processing large continuous-valued gene expression datasets and is packaged within a softwa...