Browsing by Subject "Security systems"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Artificial intelligence in computer security: Detection, temporary repair and defense(2012-05) Randrianasolo, Arisoa; Pyeatt, Larry D.; Mengel, Susan A.; Rushton, J. Nelson; Lim, SunhoComputer security system providers are unable to provide timely security updates. Most security systems are not designed to be adaptive to the increasing number of new threats. Companies lose considerable amount of time and resources when security attacks manifest themselves. As an answer to these problems, this research is aimed at developing security systems capable of learning and updating themselves. The goal is to create security systems that will autonomously mature with exposure to threats over time. To achieve this goal, this research is exploring learning techniques from the Artificial Intelligence field. This research is proposing artificial intelligence based security systems with learning capability to perform intrusion detection, temporary repair and diagnostics, and defending a network. For network intrusion detection, this research is proposing the utilization of an Artificial Immune System based on Holland's Classifier. A Q-learning approach is proposed to provide a self learning temporary repair and diagnostic mechanism for attacked software. Finally, a General Game Player approach is used as a network defender designed to fight unknown attackers. These approaches are trained and tested with simulations employing DARPA's dataset. Despite the need for an initial training time and the massive use of memory, these approaches appear to have the ability to learn and are in close competition with the other approaches that were tested on the same dataset.Item A low-complexity radar for human tracking(2006) Lin, Adrian; Ling, HaoHuman detection and tracking have become the key necessities in security and surveillance systems, especially with the growth of terrorism threats and incidents worldwide. A low-cost, low-complexity radar for tracking multiple moving humans in indoor surveillance applications is investigated in this research. The basic concept is to employ two-element receiving array to obtain the bearing of the targets. Conventional bearing detection requires the use of an antenna array with multiple elements. In this dissertation, the use of only two elements in the receiver array for bearing tracking is investigated. The concept entails resolving the Doppler frequencies of the returned signals from the moving targets, and then measuring the phase difference at each Doppler frequency component to calculate the bearing of the targets. The concept is extended by employing an additional element for vertical scanning. This extension enables the system to provide two-dimensional bearing tracking of multiple movers in the azimuth and elevation planes. A possible application of frontal-imaging of human is also investigated. Given the fact that body parts in a moving human may give rise to different Doppler returns, their bearing information may be extracted and correlated to construct a frontal image of human. Since the frontal view of human may offer more information than the conventional top-down view (down-range), it can potentially be used for target classification purposes. The concept is extended further by incorporating two frequencies to obtain the target range information. The Doppler separation among the moving targets are again exploited and pre-filtered before measuring the phase difference to arrive at the range information of the targets. The final extension of the basic concept turns the system into a low-cost, low-complexity, three-dimensional radar for human tracking. Simulations are performed to demonstrate the concept and to assess the system performance bounds. A simplified model of human-gait is developed and used in the simulations to represent realistic factors such as microDoppler returns of body parts. An experimental system is designed and constructed to test the concept. Measurement results of human subjects in various indoor and outdoor environments are presented, including through-wall scenarios.