Physical Sciences and Mathematics Commons^™

Using Discovery-Based Learning To Prove The Behavior Of An Autonomous Agent, David N. Mezera

Theses and Dissertations

Computer-generated autonomous agents in simulation often behave predictably and unrealistically. These characteristics make them easy to spot and exploit by human participants in the simulation, when we would prefer the behavior of the agent to be indistinguishable from human behavior. An improvement in behavior might be possible by enlarging the library of responses, giving the agent a richer assortment of tactics to employ during a combat scenario. Machine learning offers an exciting alternative to constructing additional responses by hand by instead allowing the system to improve its own performance with experience. This thesis presents NOSTRUM, a discovery-based learning DBL system …

A Study Of Automated Estimating Of Software Cost, Steven Shouli Wang

Masters Theses

The objectives of this thesis are to survey software cost estimation methods and to discuss how the methods can be applied as conceptual knowledge in a software cost estimation expert database system. The various applications of expert database systems are discussed. Consequently, a new method to approach the software cost estimation has been proposed.

This proposed method is based upon a dozen years of analyzing software cost models which have been done by some dedicated scientists in universities, research organizations, and industry. A CASE tool called IASCE has been designed to assist the project manager to estimate a proposed project …

Real Time Texture Analysis From The Parallel Computation Of Fractal Dimension, Halford I. Hayes Jr.

Computer Science Theses & Dissertations

The discrimination of texture features in an image has many important applications: from detection of man-made objects from a surrounding natural background to identification of cancerous from healthy tissue in X-ray imagery. The fractal structure in an image has been used with success to identify these features but requires unacceptable processing time if executed sequentially.

The paradigm of data parallelism is presented as the best method for applying massively parallel processing to the computation of fractal dimension of an image. With this methodology, and sufficient numbers of processors, this computation can reach real time speeds necessary for many applications. A …

Recognition Of Quadric Surfaces From Range Data: An Analytical Approach, Ivan X. D. D'Cunha

Electrical & Computer Engineering Theses & Dissertations

In this dissertation, a new technique based on analytic geometry for the recognition and description of three-dimensional quadric surfaces from range images is presented. Beginning with the explicit representation of quadrics, a set of ten coefficients are determined for various three-dimensional surfaces. For each quadric surface, a unique set of two-dimensional curves which serve as a feature set is obtained from the various angles at which the object is intersected with a plane. Based on a discriminant method, each of the curves is classified as a parabola, circle, ellipse, hyperbola, or a line. Each quadric surface is shown to be …

Graphical Evolution Experiments In Artificial Life, Gary R. Greenfield

Department of Math & Statistics Technical Report Series

Larry Yaeger's alife simulation running on a Silicon Graphics Iris Workstation is called Poly World. Our description of PolyWorld is based on notes taken during an oral presentation and video demonstration given in the Artificial Life Panel Session of SIGGRAPH '92: In PolyWorld the visual organisms roam on a bounded two dimensional grid. The organisms "brains" are small neural nets enabling the organisms to control their external visual appearance and to perceive the external world by processing pixmaps. The simulation controls for total energy while striving to explore competition and self-organization. Genes present are for size, strength, maximum speed, mutation …

Robust Reinforcement Learning In Motion Planning, Satinder P. Singh, Andrew G. Barto, Roderic Grupen, Christopher Connolly

Roderic Grupen

While exploring to find better solutions, an agent performing on-line reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, or even catastrophic, results, often modeled in terms of reaching 'failure' states of the agent's environment. This paper presents a method that uses domain knowledge to reduce the number of failures during exploration. This method formulates the set of actions from which the RL agent composes a control policy to ensure that exploration is conducted in a policy space that excludes most of the unacceptable policies. The resulting action set has a more abstract …

Power Analysis In Flexible Automation, Nathan A. Titus

Theses and Dissertations

The performance of an automation or robotic device can be measured in terms of its power efficiency. Screw theory is used to mathematically define the task instantaneously with two screws. The task wrench defines the effect of the device on its environment, and the task twist describes the motion of the device. The tasks can be separated into three task types: kinetic, manipulative, and reactive. Efficiency metrics are developed for each task type. The output power is strictly a function of the task screws, while device input power is shown to be a function of the task, the device Jacobian, …

Applications Of Harmonic Functions To Robotics, Christopher Connolly, Roderic Grupen

Roderic Grupen

Harmonic functions are solutions to Laplace's Equation. As noted in a previous paper, they can be used to advantage for potential-field path planning, since they do not exhibit spurious local minima. In this paper, harmonic functions are shown to have a number of other properties (including completeness) which are essential to robotics applications. These properties strongly recommend harmonic functions as a mechanism for robot control.

Monitoring Computer Systems: An Intelligent Approach, Myron Zhihong Xu

Computer Science Theses & Dissertations

Monitoring modern computer systems is increasingly difficult due to their peculiar characteristics. To cope with this situation, the dissertation develops an approach to intelligent monitoring. The resulting model consists of three major designs: representing targets, controlling data collection, and autonomously refining monitoring performance. The model explores a more declarative object-oriented model by introducing virtual objects to dynamically compose abstract representations, while it treats conventional hard-wired hierarchies and predefined object classes as primitive structures. Taking the representational framework as a reasoning bed, the design for controlling mechanisms adopts default reasoning backed up with ordered constraints, so that the amount of data …

Reasoning By Analogy In A Multi-Level System Architecture For The Design Of Mechanisms, Ghassan F. Issa

Computer Science Theses & Dissertations

Since the first attempts to integrate AI technology and engineering design nearly two decades ago, few expert systems have been shown to demonstrate sufficient reasoning capabilities to solve real-world design problems. The complex nature of design, the lack of understanding of the design process, and the limitations of current expert system technology have all been shown to have adverse effects on the maturity of this research area. Therefore, our direction in this research concentrates on understanding the design process, investigating a novel area of research focusing on creative design, and incorporating the results into a system model feasible for production …

Formant Estimation From Dctc's Using A Feedforward Neural Network, Shubhangi U. Kelkar

Electrical & Computer Engineering Theses & Dissertations

Formants are the natural frequencies of the human vocal tract. Existing methods for estimating formants from speech signals are computationally complex and subject to errors for certain type of speech sounds. This thesis describes a method for estimating vowel formant frequencies from Discrete Cosine Transform Coefficients (DCTC's), a form of cepstral coefficients, using a feedforward neural network with back-propagation training. Experimental results are based on a large multispeaker data base. The results are obtained for both a linear transformation and a feedforward neural network with a nonlinear hidden layer. In general, the neural network transformation is superior to the linear …

Hardware-Verification Through Logic Extraction, Michael A. Dukes

Theses and Dissertations

A Prolog-based system is described which employs logic-extraction to perform hardware-verification. The extraction rules are built automatically from hierarchical structural VHDL models, enabling the equivalence of a structural VHDL description and a layout specification to be verified. Pin-to-pin critical- path analysis is performed within the logic-extraction process; many noncritical paths are pruned early, making pin-to-pin critical path analysis of large circuits feasible. It is demonstrated that a design methodology based on logic extraction, VHDL, and a layout tool can provide a fabricated functionally- correct IC design without circuit-level or switch-level simulation. This methodology is shown to be practical for VLSI …

Some Developments In Information Technology In The Irish Hotel And Catering Industry, Sean Connell, Elaine Sunderland, Ciaran Mcdonnell

Conference papers

This paper describes the current and potential future use of computers in the Hospitality Industry in Ireland. It briefly outlines two research projects which are being carried out in the Dublin College of Catering in the application of computers to the Industry.

Design And Analysis Techniques For Concurrent Blackboard Systems, John William Mcmanus

Dissertations, Theses, and Masters Projects

Blackboard systems are a natural progression of Artificial Intelligence based systems into a more powerful problem solving technique. They provide a way for several highly specialized knowledge sources to cooperate to solve large, complex problems. Blackboard systems incorporate the concepts developed by rule-based and expert systems programmers and include the ability to add conventionally coded knowledge sources. The small and specialized knowledge sources are easier to develop and test, and are hosted on hardware specifically suited to the task that they are solving.;Designing and developing blackboard systems is a difficult process. The designer is attempting to balance several conflicting goals …

A Capacity Theory Of Comprehension: Individual Differences In Working Memory, Marcel Just, Patricia Carpenter

Marcel Adam Just

No abstract provided.

Robotic Tactile Sensors Fabricated From A Monolithic Silicon Integrated Circuit And A Piezoelectric Polyvinylidene Fluoride Thin Film, Craig S. Dyson

Theses and Dissertations

The purpose of this research effort was to design, fabricate, and test a tactile sensor system consisting of an external high impedance switch circuit, an external multiplexing circuit, and a tactile sensor IC. In order to accomplish this objective, a hardware design and selection process was implemented along with a logical test methodology. An external multiplexer circuit samples all of the array elements in 50 ms. The current prototype sensor has linearity spanning loads of 0.8 g to 135 g, a load resolution of 20 g, and a maximum bandwidth of 25 Hz. Using an elementary shape recognition algorithm the …

Representation Requirements For Supporting Decision-Model Formulation, Tze-Yun Leong

Research Collection School Of Computing and Information Systems

This paper outlines a methodology for analyzing the representational support for knowledge-based decision-modeling in a broad domain. A relevant set of inference patterns and knowledge types are identified. By comparing the analysis results to existing representations, some insights are gained into a design approach for integrating categorical and uncertain knowledge in a context sensitive manner.

Kinematic Synthesis Of Deployable-Foldable Truss Structures Using Graph Theory, Dirk B. Warnaar

Mechanical & Aerospace Engineering Theses & Dissertations

A graph theoretic approach is applied to the conceptual design of deployable truss structures. The characteristics that relate to the inter-connectivity of the elements of a deployable truss structure can be captured in a schematic representation, called a graph. A procedure is presented that enables the exhaustive generation of these graphs for structures of any given number of nodes and links and which are foldable onto a plane or onto a line.

A special type of truss structures, called truss modules, is presented. Graphs of this class of structures form a subset of the graphs of truss structures. Two procedures …

Effectiveness Analysis Of Knowledge Bases, Shensheng Zhao

Computer Science Theses & Dissertations

Knowledge base systems (expert systems) are entering a critical stage as interest spreads from university research to practical applications. If knowledge base systems are to withstand this transition, special attention must be paid to checking their effectiveness. The issue of effectiveness analysis of knowledge base systems has been largely ignored and few works have been published in this field. This dissertation shows how the effectiveness of a knowledge base system can be defined, discussed and analyzed at the knowledge base system level and the knowledge base level. We characterize the effectiveness of a knowledge base system in terms of minimality, …

An Examination And Analysis Of The Boltzmann Machine, Its Mean Field Theory Approximation, And Learning Algorithm, Vincent Clive Phillips

Theses : Honours

It is currently believed that artificial neural network models may form the basis for inte1ligent computational devices. The Boltzmann Machine belongs to the class of recursive artificial neural networks and uses a supervised learning algorithm to learn the mapping between input vectors and desired outputs. This study examines the parameters that influence the performance of the Boltzmann Machine learning algorithm. Improving the performance of the algorithm through the use of a naïve mean field theory approximation is also examined. The study was initiated to examine the hypothesis that the Boltzmann Machine learning algorithm, when used with the mean field approximation, …

Implementing A Neural Network In The Smalltalk Graphical Environment, John M. Damgaard

Presidential Scholars Theses (1990 – 2006)

Interest in artificial neural networks has grown rapidly over the past few years. The technology is intriguing and the potential applications of the technology are exciting and diverse. Another area of growing interest in the computer science field is that of object-oriented programming. The object-oriented paradigm is a very powerful tool which can improve software quality and streamline the development process. The most common object-oriented language is Smalltalk. I feel that Smalltalk is an excellent platform on which to implement artificial neural networks.

Integration Of Abductive And Deductive Inference Diagnosis Model And Its Application In Intelligent Tutoring System, Jingying Zhang

Computer Science Theses & Dissertations

This dissertation presents a diagnosis model, Integration of Abductive and Deductive Inference diagnosis model (IADI), in the light of the cognitive processes of human diagnosticians. In contrast with other diagnosis models, that are based on enumerating, tracking and classifying approaches, the IADI diagnosis model relies on different inferences to solve the diagnosis problems. Studies on a human diagnosticians' process show that a diagnosis process actually is a hypothesizing process followed by a verification process. The IADI diagnosis model integrates abduction and deduction to simulate these processes. The abductive inference captures the plausible features of this hypothesizing process while the deductive …

Solving Ill-Posed Problems With Artificial Neural Networks, Arun D. Kulkarni

Arun Kulkarni

An Artificial Neural Approach To The Decomposition Problem, Chandrashekar L. Masti

Electrical & Computer Engineering Theses & Dissertations

The goal of this thesis is to develop an artificial neural approach toward addressing the intractability involved with the decomposition problem. The search for the lattice of substitution property (s. p.) partitions essential to decompositions is cast into the framework of constraint satisfaction. An artificial neural network is developed to provide solutions by performing optimization of a mathematically derived objective function over the problem space. The issue of transitivity is verified to belong to a class of problems beyond the scope of solvability for conventional quadratic-order constraint satisfaction neural networks. A theorem is stated and proved establishing that third-order correlations …

A Philosophical Critique Of Artificial Intelligence, David Miller

Mahurin Honors College Capstone Experience/Thesis Projects

The term "Artificial Intelligence" creates fantastic images of robots and omniscient machines. Of all the technological pursuits, Artificial Intelligence best epitomizes man's thirst for technology. The science of making machines think stands at the apex of man's mission, reflecting not only his desire for control over his world but also his quest to control himself. To create a machine capable of thought -- rational life -- would mean that man would have achieved a dream as old as technology itself.

Michigan Apple Pest Identifier And Manager Expert System, James R. Schalk

Masters Theses

The Michigan Apple Pest Identifier and Management System (MAPI) is a knowledge- based consultation software system. MAPI was designed to provide the user with the ability to identify insects which may harm the apples of Michigan orchards and to project occurrences of maximum adult emergence. A discussion of standard entomological and expert system concepts and the application of these concepts to the processing of information by the Michigan Apple Pest Identifier and Management System is presented. Future possible expansions of the system are suggested.

Knowledge-Based System For Flight Information Management, Wendell R. Ricks

Dissertations, Theses, and Masters Projects

No abstract provided.

What One Intelligence Test Measures: A Theoretical Account Of The Processing In The Raven Progressive Matrices Test, Patricia A. Carpenter, Marcel Adam Just, Peter Shell

Marcel Adam Just

No abstract provided.

In The Image Of Man: Reflections On Artificial Intelligence, Noreen L. Herzfeld

Theology Faculty Publications

No abstract provided.

A Classification Approach For Automated Reasoning Systems--A Case Study In Graph Theory, Rong Lin

Computer Science Theses & Dissertations

Reasoning systems which create classifications of structured objects face the problem of how object descriptions can be used to reflect their components as well as relations among these components. Current reasoning systems on graph theory do not adequately provide models to discover complex relations among mathematical concepts (eg: relations involving subgraphs) mainly due to the inability to solve this problem. This thesis presents an approach to construct a knowledge-based system, GC (Graph Classification), which overcomes this difficulty in performing automated reasoning in graph theory. We describe graph concepts based on an attribute called Linear Recursive Constructivity (LRC). LRC defines classes …