Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

1994

Computer Sciences

Theses and Dissertations

Articles 31 - 46 of 46

Full-Text Articles in Physical Sciences and Mathematics

Artificially Intelligent Air Combat Simulation Agents, Daniel E. Gisselquist Dec 1994

Artificially Intelligent Air Combat Simulation Agents, Daniel E. Gisselquist

Theses and Dissertations

The Advanced Research Projects Agency (ARPA), in an effort to improve military simulations, has proposed a standard for Distributed Interactive Simulation (DIS). This network protocol will allow dissimilar applications to communicate simulation information. In the field of air combat, this will allow pilots in remote simulators to fly in a common simulation. The success of this standard is dependent on applications being able to work within that standard, as well as a large variety of Computer Generated Forces (CGFs) to complement interactive forces. CGFs are needed to help simulate the large combat scenarios that can only occur in wartime. By …

Go to article

Design And Implementation Of Tools To Increase User Control And Knowledge Elicitation In A Virtual Battlespace, Jim J. Rohrer Nov 1994

Design And Implementation Of Tools To Increase User Control And Knowledge Elicitation In A Virtual Battlespace, Jim J. Rohrer

Theses and Dissertations

AFIT's Synthetic BattleBridge is an immersive command observatory for viewing large-area activity within a virtual environment. Three basic areas for improvement are addressed: (1) an improved, immersive, user interface, (2) direct control of atmospheric effects, and (3) improved knowledge elicitation by means of remote viewers, a new space scope, and an enhanced RADAR scope. These requirements are analyzed and implemented. Some functionality was lost but the results show a general improvement of environmental control and knowledge elicitation.

Go to article

Searching For Plans Using A Hierarchy Of Learned Macros And Selective Reuse, Douglas E. Dyer Jun 1994

Searching For Plans Using A Hierarchy Of Learned Macros And Selective Reuse, Douglas E. Dyer

Theses and Dissertations

This research presents a new approach to improving the performance of a macro planner: selective reuse. In macro planning, reuse can result in poorer performance than when planning with only primitive operators, a phenomenon that has been called the utility problem. The utility problem arises because the benefits of reuse are outweighed by the cost of retrieving a macro to reuse and the cost of searching through the larger search space caused by considering reuse candidates. Selective reuse contains the expansion of the search space by limiting the number of reuse candidates considered and limits the search required by considering …

Go to article

Feature And Model Selection In Feedforward Neural Networks, Jean M. Steppe Jun 1994

Feature And Model Selection In Feedforward Neural Networks, Jean M. Steppe

Theses and Dissertations

This research advances feature and model selection for feedforward neural networks. Feature selection involves determining a good feature subset given a set of candidate features. Model selection involves determining an appropriate architecture number of middle nodes for the neural network. Specific advances are made in neural network feature saliency metrics used for evaluating or ranking features, statistical identification of irrelevant noisy features, and statistical investigation of reduced neural network architectures and reduced feature subsets. New feature saliency metrics are presented which provide a more succinct quantitative measure of a features importance than other similar metrics. A catalogue of feature saliency …

Go to article

Subgrouped Real Time Recurrent Learning Neural Networks, Jeffrey S. Dean May 1994

Subgrouped Real Time Recurrent Learning Neural Networks, Jeffrey S. Dean

Theses and Dissertations

A subgrouped Real Time Recurrent Learning (RTRL) network was evaluated. The one layer net successfully learns the XOR problem, and can be trained to perform time dependent functions. The net was tested as a predictor on the behavior of a signal, based on past behavior. While the net was not able to predict the signal's future behavior, it tracked the signal closely. The net was also tested as a classifier for time varying phenomena; for the differentiation of five classes of vehicle images based on features extracted from the visual information. The net achieved a 99.2% accuracy in recognizing the …

Go to article

Multirate Time-Frequency Distributions, John R. O'Hair May 1994

Multirate Time-Frequency Distributions, John R. O'Hair

Theses and Dissertations

Multirate systems, which find application in the design and analysis of filter banks, are demonstrated to also be useful as a computational paradigm. It is shown that any problem which can be expressed a set of vector-vector, matrix-vector or matrix-matrix operations can be recast using multirate. This means all of numerical linear algebra can be recast using multirate as the underlying computational paradigm. As a non-trivial example, the multirate computational paradigm is applied to the problem of Generalized Discrete Time- Frequency Distributions GDTFD to create a new family of fast algorithms. The first of this new class of distributions is …

Go to article

Global Picture Archiving And Communication Systems (Gpacs): An Overview, Russell C. Ellis Apr 1994

Global Picture Archiving And Communication Systems (Gpacs): An Overview, Russell C. Ellis

Theses and Dissertations

The world is currently experiencing a computer revolution. With the expansion and development of new computer technology, the age of video is upon us. The medical world is also currently undergoing a dramatic change. With the development and perfection of non-invasive techniques of probing the body, large amounts of computer data is collected and much of it is used to generate images. The organization and management of these images is the topic of this thesis. The discussion of storage schemes, databases, communications and data compression techniques gives the reader a background and some insight to the current state of the …

Go to article

Clustering Techniques In Speaker Recognition, Douglas N. Prescott Mar 1994

Clustering Techniques In Speaker Recognition, Douglas N. Prescott

Theses and Dissertations

This thesis presents a comparison based on identification rate, of three clustering techniques applied to cepstral features for speaker identification. LBG vector quantization as developed by Linde, Buzo and Gray; is used to provide benchmark performance for comparison with Fuzzy clustering (based on the unsupervised fuzzy partition-optimal number of classes, UFP-ONC algorithm by Gath and Geva) and an Artificial Neural Network, the Multilayer Perceptron. Cepstral features from the TIMIT, King and AFIT93 corpus speaker databases are used to produce speaker-identification classifiers using each of the clustering algorithms. The experiment reported evaluates the speaker identification performance using the 20-dimensional cepstral features …

Go to article

Application Of Sequential Quadratic Programming To Large-Scale Structural Design Problems, Mark A. Abramson Mar 1994

Application Of Sequential Quadratic Programming To Large-Scale Structural Design Problems, Mark A. Abramson

Theses and Dissertations

Large-scale structural optimization problems are often difficult to solve with reasonable efficiency and accuracy. Such problems are often characterized by constraint functions which are not explicitly defined. Constraint and gradient functions are usually expensive to evaluate. An optimization approach which uses the NLPQL sequential quadratic programming algorithm of Schittkowski, integrated with the Automated Structural Optimization System ASTROS is tested. The traditional solution approach involves the formulation and solution of an explicitly defined approximate problem during each iteration. This approach is replaced by a simpler approach in which the approximate problem is eliminated. In the simpler approach, each finite element analysis …

Go to article

A Format For Storing And Managing Multiple Level Of Detail Terrain For Simulated Environments, Keith L. Meissner Mar 1994

A Format For Storing And Managing Multiple Level Of Detail Terrain For Simulated Environments, Keith L. Meissner

Theses and Dissertations

This study investigated a method of storing, managing and rendering terrain data, while addressing conflicting goals of. rendering speed, display detail and memory usage. A data structure is presented to store terrain data, with an object oriented system to manage the data stored in the structure. The structure stores terrain data in a compact form which is converted into rendering structures in real time. The structure uses levels of detail to maintain display detail. The structure is compared against an existing format for storing terrain data, MultiGen Flight. The system managing the structure is shown to decrease memory usage and …

Go to article

Dyadic Wavelet Features For Isolated Word Speaker Dependent Speech Recognition, Stephen Ainge Mar 1994

Dyadic Wavelet Features For Isolated Word Speaker Dependent Speech Recognition, Stephen Ainge

Theses and Dissertations

This research examines the use of dyadic wavelet features for the recognition of speaker dependent isolated word speech. The features were generated using three different wavelet filters-Daubechies 4 coefficient (Db4), Daubechies 20 coefficient (Db20) and a 31 coefficient cubic spline and three different window lengths-15ms, 8ms and 4ms. The accuracy of the standard and over-sampled dyadic wavelet methods were compared. The over-sampled dyadic wavelet method using the Db4 scaling function, with a maximum accuracy of 65.5, was found to be the most accurate of the wavelet methods tested. The accuracy of this over-sampled dyadic Db4 wavelet method was compared to …

Go to article

Effective Parallel Algorithm Animation, Paul W. Chase Mar 1994

Effective Parallel Algorithm Animation, Paul W. Chase

Theses and Dissertations

The AFIT Algorithm Animation Research Facility AAARF was developed by the Air Force Institute of Technology AFIT as a teaching aid for data structures and algorithm design. In particular, an extensive set of performance animations has been developed for the Intel iPSC Hypercube parallel processing system. This research focuses in part on developing animation support for discrete event simulation, mission routing, and evolutionary algorithms based on abstract representations of parallel algorithm behavior. The effort also builds extensions to the AAARF system and examines direction for further research. An innovative adaptable application-specific animation construction environment has been designed and implemented. The …

Go to article

A Simulation Approach To Granite Sentry System Analysis, Marilyn J. Bauer Mar 1994

A Simulation Approach To Granite Sentry System Analysis, Marilyn J. Bauer

Theses and Dissertations

This study demonstrated the use of simulation modelling to analyze Granite Sentry system performance. The availability simulation model constructed provides a number of system performance measures as a function of component MTBFs and MTTRs. Analysis of failure data prior to model construction supported the generally accepted use of exponentially distributed failure rates and lognormally distributed repair times.

Go to article

A Fortran Based Learning System Using Multilayer Back-Propagation Neural Network Techniques, Gregory L. Reinhart Mar 1994

A Fortran Based Learning System Using Multilayer Back-Propagation Neural Network Techniques, Gregory L. Reinhart

Theses and Dissertations

An interactive computer system which allows the researcher to build an optimal neural network structure quickly, is developed and validated. This system assumes a single hidden layer perceptron structure and uses the back- propagation training technique. The software enables the researcher to quickly define a neural network structure, train the neural network, interrupt training at any point to analyze the status of the current network, re-start training at the interrupted point if desired, and analyze the final network using two- dimensional graphs, three-dimensional graphs, confusion matrices and saliency metrics. A technique for training, testing, and validating various network structures and …

Go to article

Assessing The Vulnerability Of Multi-Commodity Networks With Failing Components, Alan R. Robinson Mar 1994

Assessing The Vulnerability Of Multi-Commodity Networks With Failing Components, Alan R. Robinson

Theses and Dissertations

This research proposes an analytical approach for assessing flow disturbance, or compromise, based on limited sampling of arc flow information in multi-commodity, or multiple origin-destination O-D, networks with failing arcs. There were three objectives established for this research. The first objective was to bound the expected flow, given the arcs fail with certain probabilities, which was accomplished by reviewing current approaches for single-commodity networks and extending the results to the multi-commodity case. The second objective was to determine the best placement of flow monitors to obtain the most accurate estimates of O-D pair volumes. This was accomplished using a multi-criteria …

Go to article

The Effective Use Of Animation In Simulation Model Validation, Christopher L. Swider Mar 1994

The Effective Use Of Animation In Simulation Model Validation, Christopher L. Swider

Theses and Dissertations

This study examined two animation displays moving icons, bar graphs at two presentation speeds to determine how each of these factors affected the animations ability to communicate violations of model assumptions. Subjects viewed animation displays individually and in combination at each presentation speed. Eight problem scenarios were presented to evaluate each animations ability to communicate violations of different assumptions. Each animations communication ability was measured subjectively and objectively. Subjective measures in the form of pairwise comparisons were used to calculate normalized preference ratings for each animation. objective measures included problem identification accuracy and problem time. Subjective results indicated that moving …

Go to article

First Prev