Digital Commons Network^™

Face Recognition With Neural Networks, Dennis L. Krepp

Theses and Dissertations

This study investigated neural networks for face verification and classification. The research concentrated on developing a neural network based feature extractor and/or classifier to perform authorized user verification in a realistic work environment. Recognition accuracy, system assumptions, training time, and execution time were analyzed to determine the feasibility of a neural network approach. Data was collected using a camcorder and two segmentation schemes: manual segmentation and motion-based, automatic segmentation. Data consisted of over 2000. 32x32 pixel, 8 bit gray scale images of 52 subjects; each subject had two to ten days worth of images collected. Several training and test sets …

Computer Simulation Of A General Purpose Satellite Modem, William L. Montgomery Jr.

Theses and Dissertations

The purpose of this research was to model and simulate the performance of a digital phase shift keyed satellite modem. The probability of bit error (P sub b) at different levels of energy per bit to noise power ratio (E sub b/N sub o) was the performance measure. The channel was assumed to contribute only additive white Gaussian noise. A second order Costas loop performs demodulation in the modem and was the key part of the simulation. The Costas loop with second order Butterworth arm filters was tested by finding the response to a phase or frequency step. The Costas …

Digital Signal Processing Using Lapped Transforms With Variable Parameter Windows And Orthonormal Bases, Brian D. Raduenz

Theses and Dissertations

This thesis develops and evaluates a number of new concepts and tools for the analysis of signals using variable overlapped windows and orthonormal bases. Windowing, often employed as a spectral estimation technique, can result in irreparable distortions in the transformed signal. By placing conditions on the window and incorporating it into the orthonormal representation, any signal distortion resulting from the transformation can be eliminated or cancelled in reconstruction. This concept is critical to the theory underpinning this thesis. As part of this evaluation, a tensor product based general N-point fast Fourier transform algorithm was implemented in the DOD standard language, …

Radar Cross Section Models For Limited Aspect Angle Windows, Mark C. Robinson

Theses and Dissertations

This thesis presents a method for building Radar Cross Section (RCS) models of aircraft based on static data taken from limited aspect angle windows. These models statistically characterize static RCS. This is done to show that a limited number of samples can be used to effectively characterize static aircraft RCS. The optimum models are determined by performing both a Kolmogorov and a Chi-Square goodness-of-fit test comparing the static RCS data with a variety of probability density functions (pdf) that are known to be effective at approximating the static RCS of aircraft. The optimum parameter estimator is also determined by the …

Automated Face Recognition System, Kenneth R. Runyon

Theses and Dissertations

In this thesis three variations of an end-to-end face recognition prototype system are developed, implemented and tested. Each version includes real-time image collection, automated segmentation, preprocessing, feature extraction, and classification. The first version uses a Karhunen Loeve Transform (KLT) feature extractor and a K-nearest neighbor classifier. Version two uses the same feature set but utilizes a multilayer perception neural network with a back propagation learning rule. Finally the third version uses a Discrete Cosine Transform as the feature extractor and the K-nearest neighbor as the classifier. Only the KLT versions of the system were tested. The tests were based on …

Acquisition Of Direct Sequence Spread Spectrum Signals Using Digital Signal Processing Techniques, Ronald E. Schmitz

Theses and Dissertations

This thesis investigates the use of digital signal processing (DSP) techniques to achieve initial synchronization with Global Positioning System (GPS) Pseudo-Noise (PN) signals. Synchronization with the transmitted PN signal is essential to the despreading of the transmitted Direct Sequence Spread Spectrum (DS/SS) signals and decoding of the transmitted satellite data. The use of DSP methods to decrease the time required to achieve initial synchronization is investigated. This thesis proposes an initial acquisition section of the GPS receiver and derives the equations to show the method is mathematically feasible. Computer simulations of the proposed receiver using received signals corrupted by Doppler …

Detection Of Spoofing, Jamming, Or Failure Of A Global Positioning System (Gps), Juan R. Vasquez

Theses and Dissertations

The Air Force has equipped its aircraft with avionic systems such as Global Positioning System (GPS) and Inertial Guidance Systems (INS) capable of providing accurate navigation solutions. The aircrews flying these aircraft require a system that can either survive the hostile environments encountered in combat or notify the aircrew that their performance has been significantly degraded. This research focuses on failure detection and isolation techniques using an extended Kalman filter and generalized likelihood ratios using matched filters. Analysis is conducted using a Kalman filter development package known as the Multimode Simulation for Optimal Filter Evaluation (MSOFE). Both a large order …

Real Image Visual Display System, James R. Brandt

Theses and Dissertations

This thesis investigates a technique for improving the perception of three-dimensionality in images generated by a Silicon Graphics workstation. The technique involves using a spherical mirror into which the graphics from the CRT are projected. A real image of the graphic is formed by the mirror and it appears to be floating at the image plane. The three-dimensional effect is improved by adding reflections or shadows of the displayed object. Additionally, a method of using real objects with computer generated shadows and computer generated objects with real shadows is investigated. This is done in an effort to quantify how far …

The Effect Of An Adaptive Optical System's Spatio-Temporal Response On Imaging Performance, Patrick M. Harrington

Theses and Dissertations

Ideally, an adaptive optical control system would have instantaneous temporal response and infinite spatial bandwidth. In real systems, the response time of the adaptive optical control system is limited by the integration time of the wave front sensor, the computational time of the control algorithm, and the actuator response time. Additionally, finite inter actuator spacing limits the deformable mirror's ability to reproduce spatial frequencies having a period less than twice this spacing. Although analyses general enough to account for both the temporal and spatial characteristics of the adaptive optical system exist, they are complex and require detailed information regarding the …

Object Tracking Through Adaptive Correlation, Dennis A. Montera

Theses and Dissertations

This paper discusses the use of a correlation based system to track, an object through a series of images based on templates derived from previous image frames. The ability to track is extended to sequences which include multiple objects of interest within the field of view. This is accomplishes by comparing the height and shape of the template autocorrelation to the peaks in the correlation of the template with the next scene. The result is to identify the region in the next scene which best matches the designated target. In addition to correlation plane postprocessing, an adaptive window is used …

A Gaze-Addressing Communication System Using Artificial Neural Networks, Gabriel Baud-Bovy

Dissertations and Theses

Severe motor disabilities can render a person almost completely incapable of communication. Nevertheless, in many cases, the sensory systems are intact and the eye movements are still under good control. In these cases, one can use a device such as the Brain Response Interface (BRI) to command a remote control (e.g. room temperature, bed position), a word-processor, a speech synthesizer, and so on.

The BRI is a gaze-addressing communication system that was developed by Dr. Erik E. Sutter at the Smith-Kettlewell Eye Research Institute, San-Francisco: a menu of communication objects (e.g. letter, word, command) is displayed on a TV screen; …

Waste-Surface Mapping Of The Fernald K-65 Silos Using A Structured Light Measurement System, B. L. Burks, Fred W. Depiero, M. A. Dinkins, J. C. Rowe, C. B. Selleck, D. L. Jacoboski

Electrical Engineering

During FY 1991, a remotely operated surface-mapping measurement system was developed by the Robotics & Process Systems Division at Oak Ridge National Laboratory for use in the K-65 waste-storage silos at Fernald, Ohio. The mapping system used three infrared line-generating laser diodes as illumination sources and three high-resolution, low-lux, calibrated, black-and-white, chargecoupled- device video cameras as receivers. These components were combined to form structured light source range and direction sensors with six different possible emitter-receiver pairs. A technology demonstration and predeployment tests were performed at Fernald during July and August 1991, using the empty Silo 4 into which was placed …

The Effect Of Contacts On The Performance Of Electron-Beam Controlled Gaas And Diamond Switches, Michael Kevin Kennedy

Electrical & Computer Engineering Theses & Dissertations

The performance of GaAs and diamond as electron-beam controlled closing and opening switches has been studied. An emphasis has been placed on the effect of contacts on the current-voltage characteristics. The two materials studied were GaAs and diamond. Using the same semi-insulating GaAs wafer as a source of material, a bulk device and a p-i-n device have been fabricated and compared. The asymmetry of the pin diode allows operation at higher voltage because of the ability to suppress the lock-on effect. Whereas GaAs was ionized through cathodoluminescence; diamond, in the form of thin films, has been directly ionized by the …

Bayesian Defeat Of Camouflage, Rufus H. Cofer

Electrical Engineering and Computer Science Faculty Publications

A new technique is shown for refining and reducing incoming camouflage data based upon the Bayesian paradigm. Innovation is displayed in use of a statistical conditioning sequence that avoids the need to form target features from the data. The result is a simplified and more accurate probabilistic indication of actual target presence. This probabilistic indication can then be incorporated into a variety of target detection scenarios or, alternately, to form the basis of a theoretically optimal Bayesian target detector. Numeric simulation is presented to show the effectiveness of the technique against simulated camouflage

Explanation Mode For Bayesian Automatic Object Recognition, Thomas L. Hazlett, Rufus H. Cofer, Harold K. Brown

Electrical Engineering and Computer Science Faculty Publications

One of the more useful techniques to emerge from AI is the provision of an explanation modality used by the researcher to understand and subsequently tune the reasoning of an expert system. Such a capability, missing in the arena of statistical object recognition, is not that difficult to provide. Long standing results show that the paradigm of Bayesian object recognition is truly optimal in a minimum probability of error sense. To a large degree, the Bayesian paradigm achieves optimality through adroit fusion of a wide range of lower informational data sources to give a higher quality decision - a very …

Field Calibration Of A Transient Model For Broiler Misting, Richard S. Gates, Douglas G. Overhults, Robert W. Bottcher, Shu Hui Zhang

Biosystems and Agricultural Engineering Faculty Publications

A transient model to predict temperature within a tunnel ventilated broiler house during misting is developed. The model is calibrated with field data to obtain steady-state constants; transient predictions are compared to measured temperatures during cyclic misting for two different size birds. Measured temperatures during cyclic misting are shown to swing between steady-state asymptotes predicted from the model. Transient response of the model was faster than measured temperature data, in part due to temperature sensor dynamic response. The model predicts the length-wise temperature profile within the building during misting, and can be used to investigate alternate misting strategies and designs. …

Implementation Of Back-Propagation Neural Networks With Matlab, Jamshid Nazari, Okan K. Ersoy

Department of Electrical and Computer Engineering Technical Reports

The artificial neural network back propagation algorithm is implemented in Matlab language. This implementation is compared with several other software packages. The effect of reducing the number of iterations in the performance of the algorithm iai studied. The speed of the back propagation program, mkckpmp, written in Matlab language is compared with the speed of several other back propagation programs which are written in the C language. The speed of the Matlab program mbackpmp is, also compared with the C program quickpmp which is a variant of the back propagation algorithm. It is shown that the Matlab program mbackpmp is …

Minimum Separation For Single-Layer Channel Routing, Ronald I. Greenberg, F. Miller Maley

Computer Science: Faculty Publications and Other Works

We present a linear-time algorithm for determining the minimum height of a single-layer routing channel. The algorithm handles single-sided connections and multiterminal nets. It yields a simple routability test for single-layer switchboxes, correcting an error in the literature.

The Detection And Correlation Modeling Of Rayleigh Distributed Radar Signals, Alan L. Buterbaugh

Theses and Dissertations

This thesis provides a method for determining the detection of partially correlated Rayleigh distributed radar returns by a pulsed search radar. The receiver consists of a quadrature demodulator receiver, followed by a square law envelope detector and a linear post-detection integrator. In addition, a technique for determining the pulse-to-pulse correlation of a complex target is given using inverse Fourier transforms of the target scattering centers. An AIM-9 missile is used to illustrate how the partially correlated detection techniques and the pulse-to-pulse correlation predictions can be used to determine the probability of detection. The Detection and Correlation Modeling of Rayleigh Distributed …

Autonomous Face Segmentation, Kevin P. Gay

Theses and Dissertations

The purpose of this study was to implement an autonomous face segmentor as the front end to a face recognition system on a Sun SPARCStation2. Face recognition performance criteria, specifically, the capabilities to isolate and resize faces in an image to a consistent scale, were analyzed to determine current practical limitations. Face images were acquired using a S-VHS camcorder. Segmentation was accomplished using motion detection and predefined rules. Tests were run to determine the suitable of the autonomous segmentor as the front-end to a face recognition system. The segmentation system developed consistently located faces and rescaled those faces to a …

Co-Channel Speaker Separation, Thomas S. Andrews

Theses and Dissertations

In the co-channel speaker separation problem, the goal is to recover two separate speech signals from a monaural channel which contains the sum of the two speech signals. A new methodology is developed that if given that a segment of co-channel speech is separated into a stronger and weaker segment, the correct assignment of these separated segments to the appropriate talker can be made using a Linear Predictive Coding (LPC) based minimum-prediction residual computation. The uniqueness of the developed technique is that no a priori information is required of the co-channel speech signal. The information needed to appropriately assign these …

Speech Recognition Using Visible And Infrared Detectors, Patrick T. Marshall

Theses and Dissertations

A system has been developed that tracks lip motion using infrared (IR) or visible detectors. The purpose of this study was to determine if the additional information obtained from the IR or visible detectors can be used to increase the recognition rate of audio Automatic Speech Recognition (ASR) systems. To accomplish this goal, several hardware analog prototypes had to be designed, built and tested. Different detectors (IR and visible) and modes of operation (active and passive) were tried before a reliable and useful signal was found. An analog-to-digital (A/D) board was then designed and built that digitized both the microphone …

Modification, Reimplementation And Studies Using The Meisner Model Of The Heart, Ari Zvi Zivotofsky

Theses

The study of left ventricular filling in both the normal and the pathological heart is of great importance. A computer model simulation of the heart with emphasis on mitral flow was designed by Meisner in 1986 and implemented in QuickBASIC. This paper discusses how the original program was altered to be able to perform "Parameter vs. Parameter" runs in which it can be observed how varying an input parameter affects output parameters. The output data is then formatted in such a way that it can be used by QUATTRO PRO, a standard spreadsheet package, to yield graphical outputs.

In addition, …

Practical Constraints Pertinent To The Design Of Neural Networks, Said Sadek Abdallah, Rufus H. Cofer

Electrical Engineering and Computer Science Faculty Publications

in designing a feedforward neural network for numerical computation using the backpropagation algorithm it is essential to know that the resulting network has a practical global minimum, meaning that convergence to a stationary solution can be achieved in reasonable time and using a network of reasonable size. This is in contrast to theoretical results indicating that any square-integrable (L2) function can be computed assuming that an unlimited number of neurons are available. A class of problems is discussed that does not fit into this category. Although these problems are conceptually simple, it is shown that in practice convergence to a …

Review: 'Theory Of Dielectric Optical Waveguides,' 2nd Edition, By Dietrich Marcuse, Bradley D. Duncan

Electro-Optics and Photonics Faculty Publications

I suppose I ought to say up front that while preparing this review I often found myself feeling very much like a student evaluating his teacher. After all, it was, in part, the first edition of Dietrich Marcuse's Theory of Dielectric Optical Waveguides (among a handful of other similar texts) from which I first studied the principles of optical waveguide theory under the demanding, yet patient and graceful guidance of Dr. Ahmad Safaai-Jazi. Thus with the utmost respect for a teacher whom I have never met, I shall try to faithfully share my thoughts and feelings regarding the second edition …

Electroluminescence And Electrical Transport In Poly(3-Octylthiophene) Diodes, David Braun, G. Gustafsson, D. Mcbranch, A. J. Heeger

Electrical Engineering

We report visible light emission from diodes made from poly(3-octylthiophene). Use of a soluble derivative of polythiophene allows fabrication of the light emitting diodes by casting the polymer film from solution with no subsequent processing or heat treatment required. The devices emit dim red-orange light with relatively low external quantum efficiencies, below 2.5×10⁻⁵ photons per electron at room temperature. Electrical characterization reveals diode behavior with rectification ratios greater than 10². The temperature dependence indicates that tunneling phenomena dominate the charge injection.

Rotating-Wave Approximation In High-Gain Lasers, Lee W. Casperson

Electrical and Computer Engineering Faculty Publications and Presentations

Semiclassical models for lasers typically incorporate a fundamental simplification called the rotating-wave approximation. In this study the rotating-wave approximation is reexamined, and its implications for the simplest problem of a steady-state laser oscillator are considered in detail. It is found that for practical laser operating conditions the errors resulting from this approximation may not always be negligible.

Text-Independent Automatic Speaker Identification Using Partitioned Neural Networks, Laszlo Rudasi

Electrical & Computer Engineering Theses & Dissertations

This dissertation introduces a binary partitioned approach to statistical pattern classification which is applied to talker identification using neural networks. In recent years artificial neural networks have been shown to work exceptionally well for small but difficult pattern classification tasks. However, their application to large tasks (i.e., having more than ten to 20 categories) is limited by a dramatic increase in required training time. The time required to train a single network to perform N-way classification is nearly proportional to the exponential of N. In contrast, the binary partitioned approach requires training times on the order of N². …

An Application Of Neural Networks In Data Communication Real-Time Resource Reallocation, Qing Fan

Electrical & Computer Engineering Theses & Dissertations

This thesis presents an application of artificial neural networks in real-time resource reallocation, a methodology used in the implementation of an intelligent interface node in the Computer Integrated Manufacturing (CIM) environment. In particular, the problem is formulated using a Hopfield neural network model. The real-time reallocation problem is mapped into a two-dimensional matrix of neurons similar to Hopfield and Tank's approach to the traveling salesman problem (TSP) . An energy function is formulated in terms of the hard constraints and the solution cost. The interconnection weights and the input biases are determined by the energy function. It is shown through …

A Novel Technique For Deep Level Characterization Of High-Resistivity Semiconductor Materials, Sridhar Panigrahi

Electrical & Computer Engineering Theses & Dissertations

An improved photo induced current transient spectroscopy (PICTS) technique is developed for studying deep level parameters in high-resistivity semiconductor materials. A new digital data acquisition approach and improvement in the cryogenics of the system have enabled us, for the first time in our laboratory, to detect CuA level in a copper doped silicon compensated gallium arsenide (GaAs:Si:Cu) sample. The digital approach improves both the signal to noise ratio (S/N) and the efficiency of the system. Also, multiple PICTS spectra in a single thermal cycle can be obtained. In the present work, various doped and undoped gallium arsenide ( GaAs) and …