Digital Commons Network^™

Pennycress Establishment In Response To Management Of Corn Residue And Harvest Date, Bethany Wohrley

Theses and Dissertations

Cover crops are a key management strategy for mitigating the negative environmental impacts of agriculture. However, only 3% of Illinois crop acres report planting cover crops, largely due to a lack of direct financial incentive. Pennycress (Thlaspi arvense L.) is a cash cover crop that could provide a solution to this problem by providing environmental benefit as well as an economic return. Although it has achieved profitable yields in clean, well-managed breeding plots, pennycress faces establishment challenges when planted after corn in an agricultural setting. Therefore, the objective of this research project was to evaluate different agronomic management strategies to …

Using Generative Adversarial Networks To Augment Unmanned Aerial Vehicle Image Classification Training Sets, Benjamin J. Mccloskey

Theses and Dissertations

A challenging task in computer vision is finding techniques to improve the object detection and classification capabilities of ML models used for processing images acquired by moving aerial platforms. This research explores if GAN augmented UAV training sets can increase the generalizability of a detection model trained on said data. To answer this question, the YOLOv4-Tiny Object Detection Model was trained with aerial image training sets depicting rural environments. The salient objects within the frames were recreated using various GAN architectures, placed back into the original frames, and the augmented frames appended to the original training sets. GAN augmentation on …

Classification And Keyword Identification Of Covid 19 Misinformation On Social Media: A Framework For Semantic Analysis, Grace Y. Smith

Theses and Dissertations

The growing surge of misinformation among COVID-19 communication can pose great hindrance to truth, magnify distrust in policy makers and/or degrade authorities’ credibility, and it can even harm public health. Classification of textual context on social media data relating to COVID-19 is an effective tool to combat misinformation on social media platforms. In this research, Twitter data was leveraged to 1) develop classification methods to detect misinformation and identify Tweet sentiment with respect to COVID-19 and 2) develop a human-in-the-loop interactive framework to enable identification of keywords associated with social context, here, being misinformation regarding COVID-19. 1) Six fusion-based classification …

Global Sporadic-E Climatological Analysis Using Gps Radio Occultation And Ionosonde Data, Travis J. Hodos

Theses and Dissertations

A climatology of sporadic-E (Es) derived from a combined data set of GPS radio occultation (GPS-RO) and ground-based ionosonde soundings is presented for the period from September 2006 to February 2019. The ionosonde soundings were measured using the Lowell Digisonde International (LDI) Global Ionosphere Radio Observatory (GIRO) network consisting of 65 sites and 13,141,060 total soundings. The GPS-RO observations were taken aboard the Constellation Observing System for Meteorology, Ionosphere, and Climate (COSMIC) satellites and processed using two binary Es detection algorithms, totaling 9,072,922 occultations. The first algorithm is an S4 amplitude threshold calibrated to the occurrence of any blanketing Es …

Simultaneous Actuation And Sensing Of Electrostatic Mems, Jacob E. Song

Theses and Dissertations

Micro-Electro-Mechanical Systems (MEMS) are devices that play important roles of sensing and actuation in many different industries including automation, electronics, medical, communications, and defense. In order to make full use of these devices, it is important to understand the peripherals that enable these devices. Simultaneous actuation and control of MEMS devices is an important area of research as it enables feedback control of these device and allows devices to maintain performance as devices depreciate over their lifetime. The aim of this thesis is to perform a design space analysis on an electrostatic MEMS simultaneous actuation and sensing circuit that is …

Team Air Combat Using Model-Based Reinforcement Learning, David A. Mottice

Theses and Dissertations

We formulate the first generalized air combat maneuvering problem (ACMP), called the MvN ACMP, wherein M friendly AUCAVs engage against N enemy AUCAVs, developing a Markov decision process (MDP) model to control the team of M Blue AUCAVs. The MDP model leverages a 5-degree-of-freedom aircraft state transition model and formulates a directed energy weapon capability. Instead, a model-based reinforcement learning approach is adopted wherein an approximate policy iteration algorithmic strategy is implemented to attain high-quality approximate policies relative to a high performing benchmark policy. The ADP algorithm utilizes a multi-layer neural network for the value function approximation regression mechanism. One-versus-one …

An Analysis Of Telework Performance During The Covid-19 Pandemic, Patrick J. Lopez

Theses and Dissertations

The COVID-19 pandemic forced many individuals to shift from an atmosphere of face-to-face work to the digital work environment known as telework. Telework is an effective mitigation tool that ensures the continuity of operations. However, maximized telework may not be effective for all individuals. Many individual, organizational, and group level factors influence one’s telework performance and this study examines four of the most influential antecedents. Using linear regression analysis, conscientiousness, overload, communication, and non-distractibility were found to be significant predictors that account for over half the variance explained in telework performance. Supported by self-regulation theories, both conscientiousness and non-distractibility contained …

Life Cycle Analysis Of Hydrogen Fuel Derived From Aluminum Versus Diesel, Tyson S. Metlen

Theses and Dissertations

The Department of Defense needs energy sources beyond petroleum products to effectively combat area denial strategies employed by its adversaries. Petroleum fuels are expensive, they have deleterious environmental impacts, and most of the world’s oil reservoirs are in volatile countries. A proposed alternative energy carrier is reacting aluminum with water to produce hydrogen and using the hydrogen as a fuel source. Normally aluminum forms a protective oxide layer that prevents continuous reaction but if aluminum is mixed with a 3.5% by weight gallium-indium eutectic, the oxide layer cannot form, and the reaction is sustainable. This study conducts a life cycle …

The Impacts Of Climate Uncertainty On Streamflow In Andes, Antioquia, Colombia, Kristen R. Roberts

Theses and Dissertations

Natural hazards, such as hurricanes, wildfires, floods, and droughts impact human systems that rely on predictable patterns in the natural elements with which they interact. Skillful prediction of the impacts of climate change on linked, human-natural systems, like surface water resources, can help ensure physical risks within vulnerable communities are mitigated, resource sustainability is maximized, and intersectoral markets continue to contribute to socioeconomic stability. Due to water resources being a primary conduit through which climate uncertainty impacts people, economies, and ecosystems, its study is worthy of investigation; particularly, where those resources are uncertain and demanded by a variety of competitive …

Investigation Of Additively Manufactured Molybdenum-Tungsten-Rhenium Alloys, Randolph T. Abaya

Theses and Dissertations

The process of creating metal components through additive manufacturing is changing the way different industries can avoid the shortcomings of traditional metal production. Metals such as tungsten, molybdenum, and rhenium have many advantages for different applications, especially when alloyed together. In this study, an additively manufactured alloy containing 70% molybdenum, 25% tungsten, and 5% rhenium (70Mo-25W-5Re) is tested for its strength, ductility, hardness, and porosity. The 70Mo-25W-5Re alloy is printed through Laser Powder Bed Fusion (LPBF) under different conditions such as printing speed and printing atmosphere. Additionally, the effects of post printing heat treatment are conducted to understand the advantages …

Analyzing The Impact Of Blood Transfusion Kits And Triage Misclassification Errors For Military Medical Evacuation Dispatching Policies Via Approximate Dynamic Programming, Channel A. Rodriguez

Theses and Dissertations

Members of the armed forces greatly rely on having an effective and efficient medical evacuation (MEDEVAC) process for evacuating casualties from the battlefield to medical treatment facilities (MTF) during combat operations. This thesis examines the MEDEVAC dispatching problem and seeks to determine an optimal policy for dispatching a MEDEVAC unit, if any, when a 9-line MEDEVAC request arrives, taking into account triage classification errors and the possibility of having blood transfusion kits on board select MEDEVAC units. A discounted, infinite-horizon continuous-time Markov decision process (MDP) model is formulated to examine such problem and compare generated dispatching policies to the myopic …

Performance Of Heterogeneous Multi-Agent Systems With Applications In Combined Arms, Robert J. Wilson

Theses and Dissertations

Multi-agent systems show great potential for solving problems in complex and dynamic domains. Such systems comprise multiple individual entities called agents. Agents possessing the same behavior or physical form are called homogeneous while agents which differ in these respects are termed heterogeneous. The overall behavior of the system emerges from the many interactions of its component agents. Most multi-agent systems research to date focuses on systems of homogeneous agents, but recent work suggests that heterogeneous agents may improve system performance in certain tasks. This research examines the impact of heterogeneity on multi-agent system effectiveness and investigates the application of multi-agent …

Analysis Of Microscopic Carbon Fiber Fragments, Zachary R. Scott

Theses and Dissertations

Carbon Fiber (CF) has different tensile strengths and transverse moduli depending on how they are fabricated. Some CF is export controlled as it can be used for weapons, spacecraft, or gas centrifuges for enriching nuclear fuel. This research project explored a new way to prepare micron sized single CF threads to measure their transverse modulus and compare the moduli of non-export controlled CF to that of an export controlled CF. Five total polyacrylonitrile (PAN) fibers were used in this project, one of which was an export controlled fiber.

Evaluating Neural Network Decoder Performance For Quantum Error Correction Using Various Data Generation Models, Brett M. Martin

Theses and Dissertations

Neural networks have been shown in the past to perform quantum error correction (QEC) decoding with greater accuracy and efficiency than algorithmic decoders. Because the qubits in a quantum computer are volatile and only usable on the order of milliseconds before they decohere, a means of fast quantum error correction is necessary in order to correct data qubit errors within the time budget of a quantum algorithm. Algorithmic decoders are good at resolving errors on logical qubits with only a few data qubits, but are less efficient in systems containing more data qubits. With neural network decoders, practical quantum computation …

Analysis Of Generalized Artificial Intelligence Potential Through Reinforcement And Deep Reinforcement Learning Approaches, Jonathan Turner

Theses and Dissertations

Artificial Intelligence is the next competitive domain; the first nation to develop human level artificial intelligence will have an impact similar to the development of the atomic bomb. To maintain the security of the United States and her people, the Department of Defense has funded research into the development of artificial intelligence and its applications. This research uses reinforcement learning and deep reinforcement learning methods as proxies for current and future artificial intelligence agents and to assess potential issues in development. Agent performance were compared across two games and one excursion: Cargo Loading, Tower of Hanoi, and Knapsack Problem, respectively. …

Constructing Prediction Intervals With Neural Networks: An Empirical Evaluation Of Bootstrapping And Conformal Inference Methods, Alexander N. Contarino

Theses and Dissertations

Artificial neural networks (ANNs) are popular tools for accomplishing many machine learning tasks, including predicting continuous outcomes. However, the general lack of confidence measures provided with ANN predictions limit their applicability, especially in military settings where accuracy is paramount. Supplementing point predictions with prediction intervals (PIs) is common for other learning algorithms, but the complex structure and training of ANNs renders constructing PIs difficult. This work provides the network design choices and inferential methods for creating better performing PIs with ANNs to enable their adaptation for military use. A two-step experiment is executed across 11 datasets, including an imaged-based dataset. …

Telemetry Data Mining For Unmanned Aircraft Systems, Li Yu

Theses and Dissertations

With ever more data becoming available to the US Air Force, it is vital to develop effective methods to leverage this strategic asset. Machine learning (ML) techniques present a means of meeting this challenge, as these tools have demonstrated successful use in commercial applications. For this research, three ML methods were applied to a unmanned aircraft system (UAS) telemetry dataset with the aim of extracting useful insight related to phases of flight. It was shown that ML provides an advantage in exploratory data analysis and as well as classification of phases. Neural network models demonstrated the best performance with over …

Differences In List Learning Performance On The Moca Wordlist And Shepherd Verbal Learning Test In Cognitively Normal, Mci, And Ad Individuals, Gabrielle Montgomery Gavitt

Theses and Dissertations

Title: Differences in List Learning Performance on the MoCA wordlist and Shepherd Verbal Learning Test in Cognitively Normal, MCI, and AD Individuals Author: Gabrielle Montgomery Gavitt, M.S. Major Advisor: Anthony LoGalbo, Ph.D. Objective: The present study examines performance on the MoCA wordlist and SVLT wordlist and their association with the outcomes of healthy, MCI, and AD in a memory disorder clinic sample and community sample. Method: Archival data form 125 Health First Memory Disorder Clinic patients was utilized. Data from a community sample of geriatric individuals was also utilized. Participants were included if they were administered both the MoCA and …

Smoothing Of Convolutional Neural Network Classifications, Glen R. Drumm

Theses and Dissertations

Smoothing convolutional neural networks is investigated. When intermittent and random false predictions happen, a technique of average smoothing is applied to smooth out the incorrect predictions. While a simple problem environment shows proof of concept, obstacles remain for applying such a technique to a more operationally complex problem.

Narrative Analysis Of Open-Source Social Media Activity In The Indopacom Aor, Aaron K. Glenn

Theses and Dissertations

Emotion classification can be a powerful tool to derive narratives from social media data. Recurrent Neural Networks (RNN) can meet or exceed the performance of state-of-the-art traditional machine learning techniques using exclusively open-source data and models. Specifically, these results show that RNN variants can produce more than an 8% gain in accuracy in comparison to Logistic Regression and SVM techniques and a 15% gain over Random Forest when using FastText embeddings. This research found a statistical significance in the performance of a single layer Bi-directional Long Short-Term Memory (Bi-LSTM) model over a 2-layer stacked Bi-LSTM model. This research also found …

A New Approach To Career Field Matching For Commissioning Air Force Cadets, Daniel Griffen Laird

Theses and Dissertations

The current method of assigning graduating cadets from the United States Air Force Academy and Reserve Officers' Training Corps (ROTC) detachments to their career fields uses an integer programming model to maximize \global" Air Force utility, subject to several Air Force-defined constraints. This utility evaluates the positive benefit of assigning a certain cadet to a certain career field. This paper discusses the issues with such a model, as well as presents a new, more refined approach to the problem. Rather than provide a one-size-fits-all formulation of this particular assignment problem, a Value-Focused Thinking (VFT) framework is applied, in conjunction with …

Automated Aircraft Visual Inspection With Artificial Data Generation Enabled Deep Learning, Nathan J. Gaul

Theses and Dissertations

Aircraft visual inspection, which is essential to daily maintenance of an aircraft, is expensive and time-consuming to perform. Augmenting trained maintenance technicians with automated UAVs to collect and analyze images for aircraft inspection is an active research topic and a potential application of CNNs. Training datasets for niche research topics such as aircraft visual inspection are small and challenging to produce, and the manual process of labeling these datasets often produces subjective annotations. Recently, researchers have produced several successful applications of artificially generated datasets with domain randomization for training CNNs for real-world computer vision problems. The research outlined herein builds …

Analysis Of Task Performance During Radiological Surveillance By Means Of Discrete Event Simulation, Michael H. Ames

Theses and Dissertations

The surveillance and detection of radioactive contamination on surfaces and in the environment are commonly investigated by surveyors utilizing portable detection equipment. The availability of Discrete Event Simulation (DES) and Human Performance Modeling (HPM) allows for the analysis of physical and cognitive processes associated with these operations, as well as the effect that external environmental factors have on surveyor performance. This research uses the Improved Performance Research Integration Tool (IMPRINT) to approximate the performance of a radiological detection task informed by the observation of six surveyors. The effects of chemical Individual Protective Equipment (IPE) use is evaluated along with the …

Development Of A Methodology For The Quantification Of Reaerosolization Of A Biological Contaminant Surrogate Particle From Military Uniform Fabric, George D. Cooksey

Theses and Dissertations

During a mass casualty medical evacuation after a bioaerosol attack, a decontamination method is needed that is effective at both decontamination and preventing the secondary hazard of biological particles reaerosolizing from contaminated clothing. However, neither the efficacy of current decontamination methods nor the risk of biological particle reaerosolization is significantly explored in existing literature. The goals of this thesis were to develop a repeatable methodology to quantify the reaerosolization of a biological contaminate off Airman Battle Uniform (ABU) fabric swatches, and to test the efficacy of one decontamination method (high-volume, low-pressure water) using 1 mpolystyrene latex (PSL) spheres as a …

Comparison Of The Gad-7 And Impact Symptom Cluster Scores In Measuring Anxiety Among College Athletes, Robert Steven Cruz

Theses and Dissertations

Assessing the needs of mental health among college athletes is important given the prevalence rates, stigma, and complications that may arise after experiencing a concussion. Utilizing the General Anxiety Disorder- 7 (GAD-7) as an independent measure of anxiety at concussion baseline evaluation was explored among Division II collegiate athletes (n=568), which also included the Immediate Post-Concussion Assessment and Cognitive Testing (ImPACT) symptom clusters. ImPACT symptom clusters can be divided into four cluster (affective, cognitive, physical/somatic, and sleep) encompassing a 22-item self-report questionnaire. Simple linear regressions revealed that GAD-7 total score was significantly predicted by all four ImPACT symptom clusters. The …

Marital Satisfaction, Parental Stress, & Perceived Social Support Of Mothers Of Children With Autism Spectrum Disorders, Miriam Khiari Millan

Theses and Dissertations

The present study investigated the effects of both formal and informal social supports on mothers of children with autism spectrum disorder’s marital satisfaction and parental stress. To our knowledge, no other study has examined the relationship between various formal support types and marital satisfaction. This study aimed to fill this gap by examining the effects of both formal and informal social supports on mothers of children with ASD’s marital satisfaction and maternal stress. A sample of 151 mothers of children with ASD completed the online survey, assessing their use of formal and informal supports, their perceived effectiveness of said social …

Group Psychotherapy For Pain: A Meta-Analysis, Cameron Todd Alldredge

Theses and Dissertations

Chronic pain is common and frequently interferes with people’s regular functioning and reduces quality of life. Though pharmacological approaches are used most frequently to treat pain-related issues, the side effects of these medications often lead to other problems. Group therapy has been used and studied for decades in treating pain though it’s general efficacy for addressing pain is not clear. Objectives: to determine group therapy’s efficacy for patients with pain-related issues and whether the effects are moderated by study, patient, leader, or group characteristics. Method: potential articles were selected from searches completed in major databases based on a set of …

Material Characterization Using Nuclear Magnetic Resonance, Giovanna Marcella Pope

Theses and Dissertations

Nuclear magnetic resonance techniques can provide highly accurate information about the local environment of both liquid and solid samples. In the first half of this dissertation research, solid state NMR has provided experimental evidence for turbostratic disorder in layered covalent organic solids. Additionally, comparison with candidate structures allowed a proposed correction to the accepted structure of Covalent Organic Framework-5. The second half of the dissertation work emphasized liquid NMR spectroscopy applied to doped iron oxides (IOs). In particular, the effect of IOs on water proton T2 relaxation times were determined as a measure of contrast agent efficacy. Both types of …

Taxonomic And Phylogenetic Diversity Of Pitcher Plant Bogs In Georgia's Coastal Plain, Melanie Flood

Theses and Dissertations

Diversity studies via floristic survey and taxonomic metrics have proven essential for discerning community composition and biodiversity, however, phylogenetic analyses are necessary to reveal underlying evolutionary change and potential community assembly patterns. Pitcher plant bogs are highly diverse, highly understudied habitats that contain numerous listed and at-risk plant and animal species of Georgia.

In this study I investigated the taxonomic and phylogenetic diversity of pitcher plant bogs by asking the following questions:

1) What is the taxonomic diversity of pitcher plant bogs,

2) What is the dispersion of phylogenetic diversity within bog habitats, and

3) Does taxonomic and phylogenetic diversity …

Cobalt Ferrite Nano-Composites For The Oxidation Of Phenols In Oil Refinery Wastewater, Amira Mohamed

Theses and Dissertations

Phenolic compounds have the tendency to persist in the environment over a long period making them a main source of concern because of their toxic characteristics towards humans and animals (Bruce et al., 1987). Therefore, existence of phenolic compounds in aquatic environment is unfavourable and as a result, many treatment techniques have been implemented to treat the wastewater produced from petroleum refineries. Petroleum refineries are among the top industries that produces significant quantities of high phenol concentration wastewater. Photo-catalysis is a promising and effective method to treat phenol present in oil refineries effluent. In this study, the photo-catalyst used is …