Digital Commons Network^™

Multi-Task Deep Learning Approach For Segmenting And Classifying Competitive Swimming Activities Using A Single Imu, Mark Shperkin

Theses and Dissertations

Competitive swimming performance analysis has traditionally relied on manual video review and multi-sensor systems, both of which are resource-intensive and impractical for everyday training use. This study investigates whether a single wrist-worn inertial measurement unit (IMU) can be used to automatically segment and classify swimming activities with high accuracy. We propose a multi-task deep learning pipeline based on the MTHARS (Multi-Task Human Activity Recognition and Segmentation) architecture introduced by Duan et al. to perform stroke classification, lap segmentation, stroke count estimation, and underwater kick count estimation. Data were collected from eleven collegiate-level swimmers wearing left-wrist-mounted IMUs, each performing five 100-yard …

Process-Grounded Knowledge-Infused Learning And Decision Making, Kaushik Roy

Theses and Dissertations

This dissertation introduces process-grounded knowledge-infused learning and reasoning, a novel framework for integrating domain-expertise-based process knowledge into the learning and reasoning mechanisms of artificial intelligence systems. This approach is designed to produce controlled, transparent, and reliable predictions in critical tasks such as medical diagnosis and recommendation. By focusing on the case study of mental illness diagnosis and recommendation—where decision-making must be grounded in processes such as disorder-specific diagnostic criteria—this work demonstrates methods to embed structured decision-making directly into the system architecture during both training and inference. This integration facilitates end-to-end training and reasoning while ensuring that outputs strictly adhere to …

An Investigation Of Preservice And Novice Elementary Education Graduate Students’ Self-Efficacy Toward Teaching Engineering Design, Victoria Harkins Cameron

Theses and Dissertations

This mixed-methods action research study examined how an experiential learning–based pedagogical approach influenced the development of teaching engineering self-efficacy in preservice and novice elementary education graduate students. Grounded in Bandura’s self-efficacy theory and Kolb’s experiential learning cycle, the study examined the impact of mastery experiences, vicarious experiences, verbal persuasion, and affective states on shaping participants’ instructional self-efficacy. Data were collected using the Teaching Engineering Self-Efficacy Scale (TESS), written reflections, and a focus group. Engineering pedagogical content knowledge was the only TESS construct to show statistically significant gains, while qualitative findings indicated broader growth in self-efficacy and emotional readiness. The study’s …

Circannual And Kinship Cues Shape Reproduction And Epigenetic Aging In Peromyscus, Kim Tuyen Huynh Dam

Theses and Dissertations

Evolutionary success is defined by the ability of a species to adapt and survive across many generations. This success is not determined by any single attribute but rather includes the entrenched, complex system that could be associated with biological rhythms, reproductive strategies, and regulations of epigenetic and genetic components. By using closed Peromyscus colonies as a model and by coupling mathematical modeling, analyses of breeding records, epigenetic studies, and in vitro and in vivo experiments, this dissertation aims to discover how Peromyscus adjusts to the internal and external pressures to ensure their survival and preserve evolutionary fitness in controlled environments. …

Satellite Radar Imagery Analysis For Ground Hazard Risk Monitoring In Railway Tracks And Slopes, Sumanth Varma Byrraju

Theses and Dissertations

Railway transportation is essential to national economies globally, and disruptions from geohazards can result in significant operational delays and considerable economic consequences. Satellite radar technologies, including Interferometric Synthetic Aperture Radar (InSAR), offer an effective means to monitor geohazard risks across extensive railway networks. This thesis employs Multi-Temporal InSAR (MTInSAR) techniques, including Persistent Scatterer InSAR (PSInSAR) and Small Baseline Subset (SBAS), to identify high-risk areas along railway rights of way (ROW) prior to geohazard occurrences. However, the efficiency of these MT-InSAR and, consequently, the caliber of the data generated may be restricted by elements like topographical profile, vegetation, and surface soil …

Action Research To Explore The Use Of Augmented Reality To Support High School Students In Understanding And Creating Art Work In A Drawing Course, Alicia Joanne Cobler

Theses and Dissertations

High school students in Drawing 1 at a high school in South Carolina struggle to understand meaning or make personal connections to their own artwork. The purpose of this action research was to evaluate the implementation of immersive reality technology, specifically augmented reality (AR), in art for high school Drawing 1 students to help them understand meaning in art and create their own meaningful artwork. Creating personally meaningful symbolic works of art is one of the first Visual Art National Core Standards (National Core Visual Art Standards, 2014). Creating meaning in artwork allows students to understand society, provide an opportunity …

Development Of Teacher Leader Identities In Stem Teacher Leader Programs: Key Experiences From The Perspectives Of Program Developers And Program Completers, Paula Adams

Theses and Dissertations

The purpose of this qualitative case study was to add to the understanding of attributes of a STEM teacher leader project that contribute to the growth of STEM teacher leader identity. Single case study design was employed to explore key experiences in a collaborative Science Technology Engineering and Math teacher leader project and to explore how those experiences enhanced the teacher leader identity of participants. This research includes seven programs from six universities across the United States. The perceptions of two subunits, program developers and program completers, were considered. Data collection began with a document review which included initial university …

Regression With Atypical Data: Measurement Error, Periodicity, And Non-Normality, Nicholas W. Woolsey

Theses and Dissertations

Regression is a ubiquitous and fundamental method that can be found in any ele- mentary statistics course. The simplicity and self evidently useful nature of linear regression beguiles a non-negligible portion of researchers into disrespecting assump- tions required by these models, namely in terms of accuracy of covariates and the underlying nature of the data. This disregard can at best lead to meaningless results and at worse cause significant misunderstandings in scientific pursuit.

In this dissertation we strive propose remedies to violations of specific assump- tions. Namely the assumptions that covariates are either observed without measure- ment error or they …

Rapid Charging Lithium-Ion Batteries: Structure, Morphology, And Methodology, Sean Cade Wechsler

Theses and Dissertations

The initial commercialization and subsequent development of the lithium-ion battery (LIB) in 1991 has revolutionized the way that humans power devices, cars, and homes and led to the advent of many technologies that seemed impossible just half a century ago. As LIBs are integrated into more of daily life through handheld devices, wearable medical devices, transportation, and grid-level energy storage, the demand for fast charging and high energy density increases rapidly. To design a battery with these favorable qualities, an understanding of the effect of electrode crystal structure and electrode morphology on the ionic/electronic transport and failure modes must be …

Quantifying Biomass Burning Impacts On Soil Nox Emissions And Reactive Nitrogen Cycling, Olivia Rae Steinbeck

Theses and Dissertations

Nitrogen oxides (NOx = NO + NO₂) are trace gases that play a critical role in the atmosphere by influencing air quality, oxidation chemistry, and the deposition of fixed nitrogen. Historically, NOx emissions have been primarily linked to anthropogenic sources such as fossil fuel combustion, industrial activities, and agriculture. However, as successful legislation has significantly reduced these emissions, the relative importance of natural NOx sources has become an increasing concern. Soil NOx emissions are of particular interest due to their strong temperature dependence and their connection to global climate change. Rising global temperatures are expected to accelerate soil NOx emissions …

Autoregressive Modeling Of Dna Molecule Shapes Accompanied By An Empirical Assessment Of The Ljung-Box Test, David William Custer

Theses and Dissertations

The assumption of independence rarely holds in real-world data. Correlated observations are ubiquitous, especially in sequential contexts where time series models are essential for capturing temporal dependence. This study analyzed six groups of damaged and undamaged DNA sequences, where an "F" in the middle of a sequence indicates damage. One biological aim is to understand how DNA regenerates with the assistance of proteins that recognize damaged regions. Motivated by empirical support for AR(2) modeling, we fit autoregressive models to the first three principal component scores of each DNA group, capturing the dominant structure in the data. We conducted model diagnostics, …

Essential Characteristics And Perceived Needs Of Teachers And School Leaders Of Steam-Focused Elementary Schools: An Exploratory Study, Christopher Abbaleo

Theses and Dissertations

While STEAM (science, technology, engineering, arts, and mathematics) education has traditionally been emphasized at the high school level, there is growing recognition of its importance in elementary education. This exploratory, action research multiple-case study identified the essential characteristics of two STEAM-focused elementary schools and how they are operationalized as well as the perceived needs of teachers and school leaders working within the schools. Within-case analyses and a cross-case synthesis revealed both common and distinct STEAM-focused curricular approaches, along with other commonalities such as enriching co-curricular offerings, connections to STEAM careers, professional development, teacher collaboration, visionary leadership, and networking with external …

Characterizing The Relationships Between Cranial Geometry, Brain Morphometry, And Brain Mechanical Properties Using Mr Imaging And Elastography, Jessica Restivo

Theses and Dissertations

Traumatic brain injury (TBI) is a global health concern, with over 69 million cases annually. TBI risk depends on subject-specific neuroanatomical variation, yet research often only considers generic finite element (FE) models, based on the geometry and material composition of a 50th percentile male head. Although highly accurate, subject-specific models require expensive magnetic resonance (MR) imaging, elastography, and time-consuming computational resources. There is a need to create subject-specific TBI models that account for subject-specific variations, without neuroimaging. This study aims to create mathematical models to predict brain morphometry (dimensions, volume) [Objective 1] and mechanical properties (shear stiffness, damping ratio, octahedral …

Elevating Next Generation Wireless Devices Towards Contactless Sensing For Healthcare Applications, Aakriti Adhikari

Theses and Dissertations

There is an increasing interest in technologies that can understand and perceive at-home human activities to provide personalized healthcare monitoring, aimed at early detection of disease markers and assisting physicians in making clinical decisions. Existing approaches, such as wearables, require users to wear sensors that can be cumbersome and cause discomfort. Vision based solutions, such as optical cameras, IRs, LiDARs, etc., can be used to design contactless at-home monitoring systems. However, these systems are limited by poor lighting and occlusion, and they are privacy-invasive. Fortunately, high-frequency millimeter-wave wireless devices provide an effective alternative to the existing systems to enable fine-grained …

The Role Of Symmetries In Atomic, Electromagnetic, And Particle Physics, Joshua Martin O'Connor

Theses and Dissertations

Symmetries in atomic, electromagnetic, and weak interaction physics are explored to understand symmetry-breaking extensions of the Standard Model of particle physics. Lorentz-violating field theories are extremely interesting theoretically, since they possess many new features that are absent in Lorentz-invariant models. We outline the formalism and experimental status of the Lorentz- and CPT-violating Standard Model Extension, in both the classical and quantum regimes. Processes such as vacuum Cerenkov radiation, which are kinematically forbidden when Lorentz symmetry is exact may become allowed when this symmetry is weakly broken. Particle decays, such as pion and kaon decays, although allowed in Lorentz-invariant theories, are …

Dissections Of Lacunary Eta Quotients And Identically Vanishing Coefficients, Timothy Huber, James Mclaughlin, Dongxi Ye

School of Mathematical & Statistical Sciences Faculty Publications

For any function A(q)=∑∞n=0anqn defineA(0):={n∈N:an=0}.Now suppose C(q) and D(q) are two functions whose m-dissections are given byC(q)=c0G0(qm)+c1qG1(qm)+…+cm−1qm−1Gm−1(qm),D(q)=d0G0(qm)+d1qG1(qm)+…+dm−1qm−1Gm−1(qm).If it is the case that ci=0⟺di=0, i=0,1,…,m−1, then we say that C(q) and D(q) have similar m-dissections, and then it is also clear that C(0)=D(0), in which case we say that C(q) and D(q) have identically vanishing coefficients. In the present paper some new 4-dissections of particular eta quotients are developed. These are used in conjunction with known 2- and 3-dissections to prove many results on the identical vanishing of coefficients of various eta quotients, results which were found experimentally …

Mtu-Llm: Llm-Based Multi-Robot Task Allocation And Path Planning For Heterogeneous Robots In Search And Rescue Operations, Kaushik Kannan, Jungyun Bae

Michigan Tech Publications

Urban Search and Rescue operations after natural disasters involve locating and assisting victims in hazardous environments, which is challenging. Classical Multi-Robot Task Allocation (MRTA) and path planning approaches have been used to deploy heterogeneous robot teams in unsafe areas. However, existing methods often lack focus on workload balance and requirement fulfillment and struggle to generalize across different scenarios. To address these challenges, we propose Multi-robot Task allocation Utilizing LLMs (MTU-LLM), a framework designed to reduce the development time for task allocation and path planning approaches, enabling faster robot deployment. The framework uses an LLM-based “prompt engineering” approach that generates task …

Aiding Depth Perception In Initial Drone Training: Evidence From Camera-Assisted Distance Estimation, John Murray, Steven Richardson, Keith Joiner, Graham Wild

Research outputs 2022 to 2026

Remotely Piloted Aircraft (RPA) pilots frequently experience difficulties with depth perception, particularly when estimating distances between the drone and environmental obstacles. This study evaluates whether the use of onboard camera imagery can improve exocentric distance estimation accuracy among ab initio drone pilots operating under visual line-of-sight (VLOS) conditions. Two groups of undergraduate students performed distance estimation tasks at 20 and 50 m. One group used direct observation only to estimate the exocentric distance between the drone and an obstacle. The second group, as well as direct observation, had access to a live video feed from the drone’s onboard camera via …

Real-World Continuous Smartwatch-Based User Authentication, N. Al-Naffakh, N. Clarke, F. Li, P. Haskell-Dowland

Research outputs 2022 to 2026

User authentication is often regarded as the "gatekeeper"of cyber security. It has, however, long suffered from significant usability issues that have resulted in research focussing upon frictionless and transparent biometric approaches. Activity-based user authentication - a technique that authenticates a user by what they are physically doing at a specific point in time has attracted significant attention, particularly due to the increasing popularity of smartwatches. This research aims to overcome limitations in prior work by exploring the viability of the approach in real-world conditions. The study presents two principal experiments, one focused upon a constrained environment to provide a control …

Winds Of Change: Charting A Pathway To Ecosystem Monitoring Using Airborne Environmental Dna, Rachel L. Tulloch, Clare I.M. Adams, Matthew A. Barnes, Elizabeth L. Clare, Henrik C. Van De Ven, Andrew Cridge, Francisco Encinas-Viso, Kristen Fernandes, Dianne M. Gleeson, Erin Hill, Anna J.M. Hopkins, Anna M. Kearns, Gracie C. Kroos, Anna J. Macdonald, Francesco Martoni, Angela Mcgaughran, Todd G.B. Mclay, Linda E. Neaves, Paul Nevill, Andrew Pugh, Kye J. Robinson, Fabian Roger, Tracey V. Steinrucken, Mieke Van Der Heyde, Cecilia Villacorta-Rath, Jenny Vivian

Research outputs 2022 to 2026

Airborne environmental DNA (airborne eDNA) analysis leverages the globally ubiquitous medium of air to deliver broad species distribution data and support ecosystem monitoring across diverse environments. As this emerging technology matures, addressing critical challenges and seizing key opportunities will be essential to fully realize its potentially transformative impact. In June 2024, the Southern eDNA Society convened over 100 researchers, industry leaders, and biodiversity management stakeholders in a landmark workshop to evaluate the current state of airborne eDNA research and chart a course for future development. Participants explored opportunities for integrating airborne eDNA into existing monitoring systems, but they unanimously agreed …

Amyloid Accumulation, Brain Atrophy, And Cognitive Decline In Emergent Alzheimer's Disease, Ying Xia, Pierrick Bourgeat, Vincent Doré, Jurgen Fripp, Yen Ying Lim, Simon M. Laws, Christopher Fowler, Christopher C. Rowe, Colin L. Masters, Elizabeth J. Coulson, Paul Maruff

Research outputs 2022 to 2026

Introduction : Emergent Alzheimer's disease (AD) represents a transitional stage where cognitively unimpaired (CU) individuals exhibit subthreshold but increasing amyloid-β (Aβ) levels. The impact of Aβ accumulation on brain volume loss and cognition during this early stage remains unclear. Methods: This retrospective cohort study analyzed data from 408 CU participants who were initially Aβ− (< 15 Centiloids) and followed for up to 15 years. Changes in basal forebrain and hippocampal volume, along with domain-specific cognitive performance, were compared between those who progressed to Aβ+ (≥20 Centiloids) and those who remained Aβ−. Results: Sixty-five CU participants progressed to Aβ+, indicating emergent AD, and showed faster Aβ accumulation and subtle memory decline. However, no significant differences in rate of BF and hippocampal atrophy were observed between groups. Discussion: The results suggest that during this emergent phase of AD, Aβ accumulation is associated with episodic memory loss, in the absence of detectable accelerated brain atrophy. Highlights: Identified cognitively unimpaired individuals in the emergent stage of Alzheimer's disease (AD). Emergent AD exhibits a greater rate of amyloid-β (Aβ) accumulation. No accelerated volume loss detected in the basal forebrain or hippocampus. Emergent AD is also associated with a subtle decline in memory. Early Aβ accumulation may impair cognitive function before structural atrophy.

Evaluating The Influence Of Carbon Quantum Dots On Starch-Based Bioplastics: Toward Potential Food Packaging Applications, Shima Jafarzadeh, Mitra Golgoli, Zeinab Qazanfarzadeh, Mehrdad Forough, Peng Wu, Wendy Timms, Colin J. Barrow, Minoo Naebe, Masoumeh Zargar

Research outputs 2022 to 2026

Developing biodegradable food packaging films is crucial for reducing dependence on petroleum-based plastics. In this study, nitrogen-doped carbon quantum dots (CDs) were synthesized from citric acid and ethylenediamine via hydrothermal treatment and incorporated into sago starch films at concentrations of 0.5 %, 1 %, 3 %, and 4 % w/w of total solids using a solution casting method. The effects of CDs on structural, thermal, antioxidant, optical, and physicochemical properties were systematically investigated. CD addition enhanced the UV-shielding ability of the films. At 4 % CD content, UV transmittance decreased by 56.4 % (UVA), 66.7 % (UVB), and 73.9 % …

The Response And Recovery Of Carbon And Water Fluxes In Australian Ecosystems Exposed To Severe Drought, C. Stephens, B. Medlyn, L. Williams, J. Knauer, A. Inbar, E. Pendall, S. K. Arndt, J. Beringer, C. M. Ewenz, N. Hinko-Najera, L. B. Hutley, P. Isaac, M. Liddell, W. Meyer, C. E. Moore, J. Cranko Page, R. Silberstein, W. Woodgate

Research outputs 2022 to 2026

Climate change-driven increases in drought risk pose a critical threat to global carbon and water cycles. However, ecosystem-scale responses remain poorly quantified, particularly for severe, multiyear drought events. We addressed this gap by examining ecosystem-scale carbon and water flux sensitivity to the extreme 2018–19 drought in Australia using data from 14 eddy covariance flux sites. The ecosystems span grasslands and semi-arid woodlands to tropical and temperate forests. The driest sites (classed as “grass” and “very dry”) experienced drastic productivity impacts, with a 65% decrease in Gross Primary Productivity (GPP) over 2 years relative to the pre-drought average. However, fluxes in …

Behavioral Responses Of The California Two-Spot Octopus Octopus Bimaculoides To Changes In Color And Sound, Sofia I. Ramirez, Nathalie Reyns

McNair Summer Research Program

Recreational and commercial boat activity, military and construction operations, and seismic surveys among other human activities produce excessive sound that is classified as anthropogenic noise. Because the intensity and frequency of anthropogenic noise is often higher than that of natural underwater acoustic stimuli, marine animals may experience physiological damage to their sound-detecting organs which in turn, affects their communication and orientation abilities. In our study, we aimed to analyze the differences in behaviors exhibited by the California two-spot octopus (Octopus bimaculoides) when exposed to various volumes of noise at 54 Hz. To further investigate behavioral changes under varying conditions, we …

The Persistence Of Benefit Cliffs: A Behavioral Look At A Policy Problem, Vladimir Snurenco

University Faculty Publications and Creative Works

Benefit cliffs—where earning slightly more leads to losing more in government support—are often treated as technical glitches fixable through better formulas. But this article argues that the real problem isn't just economic—it's psychological. Drawing on behavioral economics and lived experience, the piece explores how fear, loss aversion, and system complexity keep low-income Americans trapped—even when policy fixes say they should be better off. Until policymakers account for how people actually feel and behave, benefit cliffs will persist not just on paper, but in real life

Energetic And Economic Aspects Of Rebound, Part Ii: Applications Of The Framework, Matthew Kuperus Heun, Gregor Semieniuk, Paul Brockway

University Faculty Publications and Creative Works

Widespread implementation of energy efficiency is a key greenhouse gas emissions mitigation measure, but rebound can ‘‘take back’’ energy savings. However, the absence of solid analytical foundations hinders empirical determination of rebound magnitudes. In Part I, we developed foundations of a rigorous, analytical, consumer-sided rebound framework that is approachable for both energy analysts and economists. In this paper (Part II), we develop energy, expenditure, and consumption planes, a novel, mutually consistent, and numerically precise way to visualize and illustrate rebound. Further, we operationalize the macro factor (k) for macroeconomic rebound. Using the framework and rebound planes, we calculate and show …

Performance Comparison Of Quantum And Classical Machine Learning Models For Chronic Kidney Disease Prediction, Parama Sridevi, Paramita Basak Upama, Masud Rabbani, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

In this study, we develop and compare quantum and classical machine learning-based chronic kidney disease prediction models. We used the "Chronic_Kidney_Disease Data Set" of the UCI Machine Learning Repository. We performed data preprocessing and applied feature engineering techniques to select the best features. We developed two quantum machine learning-based models and two classical machine learning-based models. We used a hybrid classical-quantum environment for building quantum machine learning models. Finally, we compared the performances of all four models. We found that the Quantum Support Vector Machine performs best among the quantum models. The model’s accuracy was 95% with a k-fold cross-validation …

Emergent Bilingual Educators’ Viewpoint Of Biliteracy Spaces: Building Capacity For Language Preservation And Development, Maria A. Davis

Electronic Theses and Dissertations

This study explored the perspectives of emergent bilingual (EB) educators regarding the value of learning two languages simultaneously for EBs at the elementary level in Texas. The problem examined was that EBs were losing their primary language while acquiring English. More EBs were entering bilingual programs with no language dominance or mixed language dominance, and researchers had explored this issue from various perspectives, including teacher language ideologies and assessment practices based on monolingual standards. This inductive qualitative case study aimed to identify what educators perceived as the benefits of bilingual education in primary classrooms where students learned two languages simultaneously. …

Hdifftg: A Lightweight Hybrid Diffusion-Transformer-Gcn Architecture For 3d Human Pose Estimation, Yajie Fu, Chaorui Huang, Junwei Li, Hui Kong, Yibin Tian, Huakang Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

We propose HDiffTG, a novel 3D Human Pose Estimation (3DHPE) method that integrates Transformer, Graph Convolutional Network (GCN), and diffusion model into a unified framework. HDiffTG leverages the strengths of these techniques to significantly improve pose estimation accuracy and robustness while maintaining a lightweight design. The Transformer captures global spatiotemporal dependencies, the GCN models local skeletal structures, and the diffusion model provides step-by-step optimization for fine-tuning, achieving a complementary balance between global and local features. This integration enhances the model’s ability to handle pose estimation under occlusions and in complex scenarios. Furthermore, we introduce lightweight optimizations to the integrated model …

O-Mapl: Offline Multi-Agent Preference Learning, The Viet Bui, Tien Mai, Hong Thanh Nguyen

Research Collection School Of Computing and Information Systems

Inferring reward functions from demonstrations is a key challenge in reinforcement learning (RL), particularly in multi-agent RL (MARL). The large joint state-action spaces and intricate inter-agent interactions in MARL make inferring the joint reward function especially challenging. While prior studies in single-agent settings have explored ways to recover reward functions and expert policies from human preference feedback, such studies in MARL remain limited. Existing methods typically combine two separate stages, supervised reward learning, and standard MARL algorithms, leading to unstable training processes. In this work, we exploit the inherent connection between reward functions and Q functions in cooperative MARL to …