<p> Although the traditional intrusion detection problem has been well studied with the release of the KDD&rsquo;99 and NSL-KDD datasets, recent intrusion detection has expanded to include wireless 802.11 networks and Industrial Control Systems &amp; Supervisory Control and Data Acquisition (ICS/SCADA) systems. This research investigates the application of two novel models to multi-domain intrusion detection. The first model is hybrid ensemble that uses complementary-based diversity measures in an efficient greedy search pruning process. The proposed hybrid ensemble is constructed from a heterogeneous combination of decision tree and Naive Bayes classifiers and evaluated for intrusion detection performance on an 802.11 wireless system, a power generation system, and a gas pipeline system. The second model is based on a one-versus-all (OVA) binary framework comprising multiple nested sub-ensembles. To provide good generalization ability, each sub-ensemble contains a collection of sub-learners, and only a portion of the sub-learners implement boosting. A class weight based on the sensitivity metric (true positive rate), learned from the training data only, is assigned to the sub-ensembles of each class. The second model is applied to traditional and 802.11 wireless network intrusion detection. Overall, the proposed models achieve higher detection rates and good overall false positive performance when evaluating the model compared to state-of-the-art methods for effective multi-domain intrusion detection.</p><p>

Estimating the cost of new technology insertion into an existing (or new) operating environment is of great concern and interest for those entities that own and operate that technology. New technology has many cost requirements associated with it, for instance; design, manufacturing, operation, maintenance and disposal all add to the life-cycle cost of a technology. Estimation and planning methods are needed to better match the costs associated with technology life-cycle requirements (design, manufacturing, etc.) in order to optimize the spending of funds. By optimizing (or closely matching) predicted technology life-cycle costs to a budget the new technology system will have a high probability of operating more efficiently and will minimize costs. System Dynamics has been used to understand and simulate how complex systems of people and technologies operate over time. Decisions (such as how much funding is allocated when in a technology life-cycle) that occur temporally or in a complex environment (i.e., many causes and effects) can be simulated to evaluate the impact the decision may have. Currently, the majority of decision theories and tools are focused on one moment in time (event-focused) rather than including the dynamic nature that decisions can have over time. Evaluating decisions at one instant versus taking into account the life-cycle impact a decision can have, is especially important to the US Government, where investment decisions can involve billions of dollars today, but potentially hundreds of billions later for technology life-cycle requirements. The Navy has experienced large cost overruns in the implementation of new technologies especially in the operations, support and disposal life-cycle phases. There is a lack of detailed knowledge of the dynamic nature of the technology operations, support and disposal (OS&D) processes undertaken by aircraft-carrier builders and planners. This research effort is to better understand and simulate the dynamics prevalent in the new technology implementation process and use a dynamic modeling technique, namely, System Dynamics in our study. A System Dynamics model based on the information and data obtained from experts including; General Dynamics - Newport News Shipbuilding, the Naval Sea Command Cost Estimating Group, and Virginia Polytechnic and State University - System Performance Laboratory. The model was constructed to simulate and predict the cost of operating, maintaining and disposing of a new technology. The investigation of the dynamics yields four dominant behaviors that characterize the technology OS&D process. These four dynamic behaviors are; exponential growth, goal seeking, overshoot & collapse and S-shaped growth with overshoot. Furthermore, seven dynamic hypotheses in the system are investigated. The model predicts an increase in the risk and degradation of new technologies leads to an increase in the total costs in the technology OS&D process. Three interesting insights that lead to increased total OS&D costs were; an inequality between the requirements for OS&D and provided budget, any delay in additional funding being provided and that as the new technology system grew older, it became less costly to maintain. / Master of Science

No description available.