Artificial Intelligence Lab, Department of MIS, University of Arizona / Effective and efficient link analysis techniques are needed to help law enforcement and intelligence agencies fight organized crimes such as narcotics violation, terrorism, and kidnapping. In this paper, we propose a link analysis technique that uses shortest-path algorithms, priority-first-search (PFS) and two-tree PFS, to identify the strongest association paths between entities in a criminal network. To evaluate effectiveness, we compared the PFS algorithms with crime investigatorsâ typical association-search approach, as represented by a modified breadth-first-search (BFS). Our domain expert considered the association paths identified by PFS algorithms to be useful about 70% of the time, whereas the modified BFS algorithmâ s precision rates were only 30% for a kidnapping network and 16.7% for a narcotics network. Efficiency of the two-tree PFS was better for a small, dense kidnapping network, and the PFS was better for the large, sparse narcotics network.

Artificial Intelligence (AI) encompasses the following general areas of research: (1) automatic programming, (2) computer vision, (3) expert systems, (4) intelligent computer-assisted instruction, (5) natural language processing, (6) planning and decision support, (7) robotics, and (8) speech recognition. Intelligent library systems utilize artificial intelligence technologies to provide knowledge-based services to library patrons and staff. This paper examines certain key aspects of AI that determine its potential utility as a tool for building library systems. It discusses the barriers that inhibit the development of intelligent library systems, and it suggests possible strategies for making progress in this important area. While all of the areas of AI research indicated previously may have some eventual application in the development of library systems, this paper primarily focuses on a few that the author judges to be of most immediate significance--expert systems, intelligent computer-assisted instruction, and natural language applications. This paper does not discuss the use of AI knowledge-bases in libraries as subject-oriented library materials.

The principal problem is the control of a nonlinear system with uncertainty. We will consider a robot manipulator system, which is nonlinear, and uncertain (unknown parameters and modeling errors). Our goals are to come up with a design of controllers that insure the stability of the system and provide robustness to parameters changes and modeling errors. We will use the theory developed for uncertain linear systems after carrying out an exact linearization of the original system. This linearization which is not an approximation, has been recently developed. The linear part of the controller has been designed so as to guarantee tracking and disturbance rejection. However, additional constraints resulting from the original nonlinear system have to be taken care of. Our design is tested by simulation on a two degree of freedom robot manipulator, which is simple enough to simulate but has all the properties of more general manipulators.

Artificial Neural Networks have been developed at Rice University for the forecasting of the Dst index from solar wind and Dst parameters. The one hour Dst index is an Earth based measurement of variations in the H-component of the magnetic field that is indicative of the strength of the ring current, and thus magnetic storms. Comparison of the neural networks' outputs to the OMNI dataset values of Dst will be presented. These results verify the success of the neural networks in predicting Dst. Network performance when predicting Dst two or more hours into the future and testing of MSFM output based on neural net Dst input for the August 1990 storm will be presented. Comparisons between MSFM equatorial particle fluxes and CRRES satellite observations show the MSFM 10 keV proton equatorial fluxes raise interesting questions about the MSFM's use of the Dst input parameter.

<p> With the rise of powerful mobile devices and the broad availability of computing power, <i>Automatic Speech Recognition</i> is becoming ubiquitous. A flawless ASR system is still far from existence. Because of this, interactive applications that make use of ASR technology not always recognize speech perfectly, when not, the user must be engaged to repair the transcriptions. </p><p> We explore a <i>rational user interface</i> that uses of machine learning models to make its best effort in presenting the best repair strategy available to reduce the time in spent the interaction between the user and the system as much as possible. A study is conducted to determine how different candidate policies perform and results are analyzed. </p><p> After the analysis, the methodology is generalized in terms of a decision theoretical framework that can be used to evaluate the performance of other rational user interfaces that try to optimize an expected cost or utility.</p>

<p>An evolutionary algorithm (EA) is a biologically inspired metaheuristic that uses mutation, crossover, reproduction, and selection operators to evolve solutions for a given problem. Learnable Evolution Model (LEM) is an EA that has an evolutionary algorithm component that works in tandem with a machine learner to collaboratively create populations of individuals. The machine learner infers rules from best and least fit individuals, and then this knowledge is exploited to improve the quality of offspring. </p><p> Unfortunately, most of the extant work on LEM has been <i>ad hoc </i>, and so there does not exist a deep understanding of how LEM works. And this lack of understanding, in turn, means that there is no set of best practices for implementing LEM. For example, most LEM implementations use rules that describe value ranges corresponding to areas of higher fitness in which offspring should be created. However, we do not know the efficacy of different approaches for sampling those intervals. Also, we do not have sufficient guidance for assembling training sets of positive and negative examples from populations from which the ML component can learn. </p><p> This research addresses those open issues by exploring three different rule interval sampling approaches as well as three different training set configurations on a number of test problems that are representative of the types of problems that practitioners may encounter. Using the machine learner to create offspring induces a unique emergent selection pressure separate from the selection pressure that manifests from parent and survivor selection; an outcome of this research is a partially ordered set of the impact that these rule interval sampling approaches and training set configurations have on this selection pressure that practitioners can use for implementation guidance. That is, a practitioner can modulate selection pressure by traversing a set of design configurations within a Hasse graph defined by partially ordered selection pressure. </p>

Diss. Ronneby : Tekn. högsk., 2002.

Thesis (Ph.D.)--Lehigh University, 2007.

Thesis (M.S. in Modeling, Virtual Environments, and Simulation (MOVES))--Naval Postgraduate School, March 2008. / Thesis Advisor(s): Darken, Christian. "March 2008." Description based on title screen as viewed on May 21, 2008. Includes bibliographical references (p. 47-49). Also available in print.

Thesis (M.A.)--Liberty University Graduate School of Religion, 1991. / Includes bibliographical references.