Physical Sciences and Mathematics Commons^™

Development And Optimization Of A 1-Dimensional Convolutional Neural Network-Based Keyword Spotting Model For Fpga Acceleration, Trysten E. Dembeck

Masters Theses

Spoken Keyword Spotting (KWS) has steadily remained one of the most studied and implemented technologies in human-facing artificially intelligent systems and has enabled them to detect specific keywords in utterances. Modern machine learning models, such as the variants of deep neural networks, have significantly improved the performance and accuracy of these systems over other rudimentary techniques. However, they often demand substantial computational resources, use large parameter spaces, and introduce latencies that limit their real-time applicability and offline use. These speed and memory requirements have become a tremendous problem where faster and more efficient KWS methods dominate and better meet industry …

The Mechanical Strength Of Sedimentary Rocks At Meridiani Planum, Mars, Tyler J. Seyglinski

Masters Theses

The physical properties of rocks such as their strength, hardness, and density can help inform our understanding of the formation and modification history of rock units. For sedimentary rocks, their strength is inherently linked to factors such as porosity and degree of induration, which are in turn controlled by factors such as burial depth and water-rock interaction. On Earth, rock strength is typically assessed as unconfined compressive strength (UCS) and can be measured directly or inferred via indirect strength tests (e.g., the Schmidt hammer test). On Mars, instruments such as the Rock Abrasion Tool (RAT) onboard the Opportunity rover can …

3d-Magnetometer Arrays In Physics Experiments, Shaun G. Vavra

Masters Theses

This study presents the design and experimental evaluation of a magnetometer array utilizing LIS3MDL chips integrated with an Arduino microcontroller. Magnetometer arrays find crucial applications in various fields, including physics research, geophysics, and navigation systems. The goal of this research is to create an affordable and versatile magnetometer array for scientific investigations and practical applications. The paper begins by outlining the hardware and software components of the array. The LIS3MDL chips, known for their high sensitivity and low power consumption, are employed as the core sensing elements. The Arduino microcontroller is utilized for data acquisition and processing. The integration of …

Neural-Network-Based Detection Of Radiopharmaceutical Extravasation In Pet/Ct Data, Elijah D. Berberette

Masters Theses

The immediate identification of PET/CT radiopharmaceutical extravasation can eliminate many adverse effects such as misdiagnosis and improper therapy. Radiopharmaceutical extravasation is the leakage of an injected radiotracer from the patient’s intended vein into surrounding tissues. The detection of this phenomenon often requires the use of an external monitoring device; due to a lack of robust visual features that can provide indication that it has occurred. In this thesis, the feasibility of using neural networks trained on PET/CT data to identify extravasation is explored. This approach begins with a novel preprocessing methodology that automatically extracts body weight normalized standard uptake values …

Koopman-Inspired Proximal Policy Optimization (Kippo), Andrei Cozma

Masters Theses

Reinforcement Learning (RL) has made significant strides in various domains, yet developing effective control policies for environments with complex, nonlinear dynamics remains a challenge, particularly for policy gradient methods. These methods often struggle due to high-variance in gradient estimates, non-convex optimization landscapes, and sample inefficiency, resulting in unstable learning, suboptimal policies, and trade-offs between performance and reproducibility. The quest for more robust, stable, and effective methods has led to numerous innovations and remains a critical area of research. Proximal Policy Optimization (PPO) has gained popularity in recent years due to its balance in performance, training stability, and computational efficiency. In …

Comparison Of Core-Collapse Supernova Explosions With 15 Solar Mass Progenitors, Chien-Hui Chen

Masters Theses

The study of core-collapse supernovae (CCSNe) helps us understand the origin and history of chemical abundances in our Universe. Previous numerical studies of CCSNe have shown the importance of non-radial motion in pre-collapse progenitors on the explosion outcome. In this thesis, I use the 2D Chimera neutrino radiation hydrodynamics code to run simulations of four models with 15 solar mass (M⊙) progenitors but different initial conditions sourced from different 1D and 2D pre-collapse burning environments. To analyze the models, I compare the explosion evolution of their nuclear abundances, shocks, neutrino heating, accretion, explosion geometry, and turbulent convection. Despite the differences …

Optimization Of Learning Algorithms In Neuromorphic Computing Systems., Oyinpere S. Ameli

Masters Theses

Spiking Neural Networks (SNNs) are a type of artificial neural network that aim to more closely mimic the data processing processes observed in biological neural systems. However, one major challenge in training these networks has been their non-differentiable nature, which makes it difficult to apply traditional gradient-based learning techniques. Different approaches have been proposed to address this challenge, ranging from supervised learning - largely inspired by error backpropagation in Deep Neural Networks - to unsupervised learning, which closely emulates biological learning approaches such as spike-timing dependent plasticity (STDP). Neuromorphic hardware platforms such as Intel's Loihi offer programmable plasticity that allows …

Spontaneous Plant Colonization Of Newly Established Green Roofs: An Experimental Approach, Braden Matthew Coats

Masters Theses

Urban Heat Island Effect (UHI) increases heat risks in densely developed environments. Ecosystem services provided by green spaces are known to mitigate UHI. Green roofs, designed as novel ecosystems, transform less-utilized spaces like rooftops into functional areas, executing ecosystem functions in densely populated urban environments where traditional green spaces are less common. Research has examined ways to reduce the obstacles of implementing green roofs to maximize accessibility and efficiency of the performed ecosystem services. Research involving plant community dynamics found that maximizing biodiversity on green roofs enhances the ecosystem services provided. Utilizing spontaneous colonizing species, or species that are not …

Assessment Of Enzyme Stability In Subsurface Sediments By Computational Methods, Kambiz Kalhor

Masters Theses

The microorganisms found in marine subseafloor sediment play a vital role in global carbon and nitrogen cycles, with an estimated 2.9×10²⁹ cells, accounting for about 0.6% of Earth’s total living biomass. These microbes grow at a very slow rate, with carbon turnover occurring over the course of years to thousands of years, about six orders of magnitude slower than sulfate reducing bacteria in pure culture. These slow metabolic rates suggest that the enzymes they produce must also have extended lifespans in order to be effective over such long periods of time. As a result, these enzymes are likely to …

2d Temperature Map Acquisition Using Hyperspectral Imaging System (Hsis), Anthony Kim

Masters Theses

Imaging techniques are close to our lives and are used for various applications. In the engineering field, one of the dominant techniques is hyperspectral imaging. It is a necessary tool that combines spectroscopy and digital photography and provides additional information on what is imaged by the imaging system. Hyperspectral imaging has been applied to various fields including remote sensing, cultural relic conservation, food microbiology, forensic science, biomedicine, etc.

In particular, work was done to apply hyperspectral imaging to measure the temperature and emissivity of an object. Due to its ability to measure temperature and emissivity without being in contact with …

Transfer Learning For Predictive Maintenance: A Case Study, Colter A. Swanson

Masters Theses

In light of recent strides in high-performance computing, the concept of transfer learning has emerged as a prominent paradigm within the realm of Artificial Intelligence and Machine Learning methodologies. Analogous to the human brain's capacity to assimilate information across related domains for pattern recognition, transfer learning has swiftly asserted its dominance, particularly in deep learning applications such as image classification and natural language processing. Despite its ascendancy in these domains, there exists a lack of comprehensive investigations in alternative domains, notably those encompassing tabular data formats. This thesis seeks to redress this gap by conducting an empirical examination of transfer …

Creative Connections: Building Empathy To Foster Ecoliteracy Through Art Education, Jocelyn Salim

Masters Theses

This thesis investigates the potential positive impact of fostering empathy and understanding for the natural world through art education. Through action research, this study examines various teaching approaches, such as incorporating scientific knowledge, employing literature to discuss ecological themes, and engaging in participatory storytelling activities to cultivate empathy among elementary school children. The objective of this thesis is to explore empathy as a potential pathway to encourage children to foster connections with the natural world and develop compassionate traits, attitudes, and behaviors towards nature as they grow. The findings of this study reveal that children exhibit high levels of enthusiasm …

A Thesis, Or Digressions On Sculptural Practice: In Which, Concepts & Influences Thereof Are Explained, Set Forth, Catalogued, Or Divulged By Way Of Commentaries To A Poem, First Conceived By The Artist, Fed Through Chatg.P.T., And Re-Edited By The Artist, To Which Are Added, Annotated References, Impressions And Ruminations Thereof, Also Including Private Thoughts & Personal Accounts Of The Artist, Jaimie An

Masters Theses

This thesis is an exercise in, perhaps a futile, attempt to trace just some of the ideas, stories, and musings I might meander through in my process. It’s not quite a map, nor is it a neat catalogue; it is a haphazard collection of tickets and receipts from a travel abroad, carelessly tossed in a carry-on, only to be stashed upon returning home. These ideas are derived from much greater thinkers and authors than myself; I am a mere collector or a translator, if that, and not a very good one, for much is lost. I do not claim comprehensive …

Fluid Futures: The Revitalization Of Yangzhou Through Its Historical Waterways, Feiyang Wu

Masters Theses

In China, cities such as Yangzhou, which in pre-modern times played central roles in the political, cultural, and economic functioning of the country based on their geographic location, proximity to water-based trade routes, and connections to the imperial court, are today facing uncertain futures due to waterways no longer being critical to trade, and government-driven development being focused on first-tier cities such as Beijing, Shanghai, Shenzhen, and Guangzhou. With this, the working-age population migrates from smaller cities toward these urban giants, leaving behind aging relatives, a less robust and diversified economic base, and few attributes other than cultural tourism that …

Searching For The Hyperobject: Crystals As Transscalar Vehicles, Jay Costello

Masters Theses

When I touch the street outside my house, I'm touching Los Angeles—a contiguous vector of material bisecting a continent. A slab, a stone, dust and oil, a googolplex of tightly packed anisotropic particles... At nightfall, I sneak to the edge of the highway and break off a piece. 'What does it mean for a worm to be aware of the scale of the planet?' Bruno Latour's evocative questioning of scalar jumps prompts an existentialism that places me somewhere between the hyperlocal and the massively distributed. Like a cosmic traveler floating through the universe, I feel adrift. I look around, grasping …

Einstein Field Equations And The Solutions For Uncharged Black Holes, Yogesh Mahat

Masters Theses

The General Theory of Relativity, formulated by the brilliant mind of Albert Einstein, stands as one of the most fundamental and revolutionary pillars of modern physics. This elegant theory of gravity not only offers a comprehensive explanation of the workings of the universe on a large scale, but it has also paved the way for groundbreaking advancements in the field of mathematics. This thesis begins by providing a concise overview of the key mathematical principles that are crucial to understanding Einstein’s theory. These principles form the basis for deriving the field equations that Einstein introduced. From there, these equations are …

Environmental Fate And Transport Of Pfas In Wastewater Treatment Plant Effluent Discharged To Rapid Infiltration Basins, Kai M. Trobisch

Masters Theses

Fate and transport of per- and polyfluoroalkyl substances (PFAS) in wastewater treatment plant (WWTP) effluent discharged to rapid infiltration basins (RIBs) is investigated using data from 26 WWTPs in Michigan and numerical modeling to assess the role of air-water interface (AWI) sorption in modulating mass fluxes to the saturated zone. Analysis of RIB physical properties yields a median separation distance of 6.5 meters between land surface and the water table, and a continuum of area-normalized effluent fluxes ranging from 0.01 to 0.62 meters per day. A subset of WWTPs with RIBs indicate higher PFAS concentrations in groundwater than effluent with …

Moral Responsibility And Other Visceral Attitudes Of Western Michigan University Students Toward Food Waste, Quinn Heiser

Masters Theses

Despite the large number of people that go hungry on a regular basis in America, food waste remains a looming issue, globally and nationally. Both American college students and the universities themselves contribute a large portion to the national food waste totals. A dichotomy that is especially curious is the difference between students who live on-campus and whose main source of meals is the dining centers, versus students who live off campus and rely mainly on groceries to make meals independently. However, food waste has seldom been studied in the context of the fact that college is a major transition …

Operation Shark: Addressing The Negative Portrayal Of Sharks In Media, Michael R. O'Shea

Masters Theses

Sharks are some of the most well adapted and effective animals in the animal kingdom. Unfortunately, they are also some of the most feared. For many people the word shark evokes images of vicious attacks like those seen in movies such as Jaws. Sharks have also been negatively portrayed in the media. This negative portrayal of sharks has led to misconceptions about sharks that have damaged their populations. Efforts have been made to raise awareness and fight common misconceptions of sharks. However, many people still hold on to the incorrect ideas they have about sharks. This thesis will examine the …

Thermal Physiology Of Sceloporus Olivaceus And Sceloporus Variabilis In South Texas, Ian Rockel

Masters Theses

This study explores the thermal physiology of two sympatric lizard species, Sceloporus olivaceus (Texas spiny lizard) and Sceloporus variabilis (rose-bellied lizard), in South Texas. I document the metabolic rate and its temperature sensitivity, thermal limits, and performance at different temperatures to better understand the impact of rising temperatures and urbanization on these ectotherms, whose body temperature and, consequently, metabolic rate, activity level, and reproductive success depend on their thermal environment. We hypothesize that S. olivaceus will exhibit greater thermal resilience owing to its broader latitudinal range, variable habitat usage within Texas, and presumed more versatile thermoregulatory strategies. Scelorporus olivaceus's higher …

Mercury Biomagnification In Aquatic Food Webs Of Great Smoky Mountains National Park, Zachary Winston Clark

Masters Theses

Mercury is a widespread pollutant threatening human, fish, and ecosystem health on a global scale. Biomagnification concentrates mercury in upper trophic level organisms including predatory fishes, a primary route of dietary mercury exposure for humans. However, mercury biomagnification is not well understood in stream ecosystems, especially in places with no known point sources of contamination. A 2016 study revealed that Smallmouth Bass Micropterus dolomeiu mercury concentrations varied between three streams in Great Smoky Mountains National Park (GSMNP), Tennessee USA. However, the reason for this spatial variation in mercury concentrations is not understood. Our objectives were to (1) measure environmental and …

Evaluation Of Avian Use Of Agricultural Cover Crops During The Winter, Migration Stopover, And The Breeding Season In Tennessee, Brittany Panos

Masters Theses

The U.S. Department of Agriculture Natural Resources Conservation Service administers the cover crop program to provide technical and financial assistance to agricultural producers to sow herbaceous plant seeds to establish cover crops to protect agricultural fields from soil erosion during the non-growing season (late fall through spring). Soil retention and water quality benefits have been documented, but potential benefits for avian wildlife remain largely unknown. I used line-transect avian and vegetation surveys to examine use of cover crop fields by birds during the non-breeding period (winter), migration, and the breeding season. I compared avian use of cover crop fields with …

Genetic Algorithm Optimization Of Experiment Design For Targeted Uncertainty Reduction, Alexander Amedeo Depillis

Masters Theses

Nuclear cross sections are a set of parameters that capture probability information about various nuclear reactions. Nuclear cross section data must be experimentally measured, and this results in simulations with nuclear data-induced uncertainties on simulation outputs. This nuclear data-induced uncertainty on most parameters of interest can be reduced by adjusting the nuclear data based on the results from an experiment. Integral nuclear experiments are experiments where the results are related to many different cross sections. Nuclear data may be adjusted to have less uncertainty by adjusting them to match the results obtained from integral experiments. Different integral experiments will adjust …

Evaluation Of Regression Methods And Competition Indices In Characterizing Height-Diameter Relationships For Temperate And Pantropical Tree Species, Sakar Jha

Masters Theses

Height-diameter relationship models, denoted as H-D models, have important applications in sustainable forest management which include studying the vertical structure of a forest stand, understanding the habitat heterogeneity for wildlife niches, analyzing the growth rate pattern for making decisions regarding silvicultural treatments. Compared to monocultures, characterizing allometric relationships for uneven-aged, mixed-species forests, especially tropical forests, is more challenging and has historically received less attention. Modelling how the competitive interactions between trees of varying sizes and multiple species affects these relationships adds a high degree of complexity. In this study, five regression methods and five distance-independent competition indices were evaluated for …

Advancing Compact Modeling Of Electronic Devices: Machine Learning Approaches With Neural Networks, Mixture Density Networks, And Deep Symbolic Regression, Jack Robert Hutchins

Masters Theses

This thesis pioneers the integration of deep learning techniques into the realm of compact modeling, presenting three distinct approaches that enhance the precision, efficiency, and adaptability of compact models for electronic devices. The first method introduces a Generalized Multilayer Perception Compact Model, leveraging the function approximation capabilities of neural networks through a multilayer perception (MLP) framework. This approach utilizes hyperband tuning to optimize network hyperparameters, demonstrating its effectiveness on a HfOx memristor and establishing a versatile modeling strategy for both single-state and multistate devices.

The second approach explores the application of Mixture Density Networks (MDNs) to encapsulate the inherent stochasticity …

Understanding Student Experiences With Tls Client Authentication, Clay A. Shubert

Masters Theses

This thesis presents a comprehensive investigation into student experiences with TLS client authentication, highlighting the usability challenges and learning curves associated with this long term key managament system. We designed a study that required future innovators in technology and security to use modern-day implementations of this certificate-based authentication system. From this study, we analyzed server logs, project reports, and survey responses from students enrolled in the applied cryptography course. We revealed significant hurdles in the initial setup and long-term key management of credentials used in TLS client authentication, emphasizing the gap between theoretical knowledge and practical implementation skills. Through quantitative …

An Evaluation Of Spectroscopic Databases: Content, Structure, Toolsets, Usability, And Documentation, Joseph William Braker

Masters Theses

Spectroscopic databases provide a critical service in the greater field of spectroscopy. Many subdisciplines of spectroscopists use the data contained within, whether calculating theoretical models, evaluating the atmosphere of a planet in the furthest reaches of the galaxy, or monitoring the emission levels of a chemical process. The intention of this research is to seek a deeper level of understanding of spectroscopy and the resources available while providing a comparison of the databases, the content within, and their peripheral tools and features. An experimental effort was derived to utilize existing experimental data from multiple sources and determine which data source …

Mapping Arbitrary Spiking Neural Networks To The Ravens Neuroprocessor, Jongheon Park

Masters Theses

In neuromorphic computing, a hardware implementation of a spiking neural network is used to provide improved speed and power efficiency over simulations of the networks on a traditional Von Neumann architecture. These hardware implementations employ bio-inspired architecture usually consisting of artificial neurons and synapses implemented in either analog, digital, or mixed-signal circuits. Since these hardware spiking neural networks are designed to support arbitrary networks under the constraints imposed by the available hardware resource, they have to be programmed by off-chip software with awareness of those constraints. The TENNLab research group at the University of Tennessee, Knoxville has recently developed the …

Winter Roost Selection Of Eastern Red Bats And Impacts Of Non-Growing Season Prescribed Fire On Foraging Activity Of Forest Roosting Bats In Tennessee, Ashley D. Epstein

Masters Theses

With an increase in wind energy development and continued deforestation and habitat degradation, eastern red bats (Lasiurus borealis; LABO) and other migratory foliage roosting bats (hoary bat [Lasiurus cinereus; LACI], silver-haired bat [Lasionycteris noctivagans; LANO]) are at risk of severe population declines, potentially leading to the need for protection under the Endangered Species Act. While studies have been done examining the ecology of these species, there is still a lack of research on winter roosting and foraging behaviors. This research aims to fill some of those knowledge gaps by 1) Examining roost use (i.e., trees vs. litter) …

Easier Air Alert Platform: A Design And Approach To Creating A Distributed Air Quality Monitoring And Alert System, Bryceton Bible

Masters Theses

This thesis presents the design approach, development and implementation of the Elders Alert System for Imminent Environmental Risk (EASIER) project, an air quality monitoring and alert system aiming to improve the health and wellness of under-served elder communities, as a part of the Tennessee Valley Authority Connected Communities initiative for Environmental Justice. The EASIER project provides homes with a fully integrated, connected system capable of real-time air quality monitoring, notifications and descriptions of potential air quality risks, and educational material to empower these community members to take charge of their own air health. Further, EASIER aims to inform relevant family/friends …