Digital Commons Network^™

Improving Connectivity For Remote Cancer Patient Symptom Monitoring And Reporting In Rural Medically Underserved Regions, Esther Max-Onakpoya

Theses and Dissertations--Computer Science

Rural residents are often faced with many disparities when compared to their urban counterparts. Two key areas where these disparities are apparent are access to health and Internet services. Improved access to healthcare services has the potential to increase residents' quality of life and life expectancy. Additionally, improved access to Internet services can create significant social returns in increasing job and educational opportunities, and improving access to healthcare. Therefore, this dissertation focuses on the intersection between access to Internet and healthcare services in rural areas. More specifically, it attempts to analyze systems that can be used to improve Internet access …

Multi-Domain Adaptation For Image Classification, Depth Estimation, And Semantic Segmentation, Yu Zhang

Theses and Dissertations--Computer Science

The appearance of scenes may change for many reasons, including the viewpoint, the time of day, the weather, and the seasons. Traditionally, deep neural networks are trained and evaluated using images from the same scene and domain to avoid the domain gap. Recent advances in domain adaptation have led to a new type of method that bridges such domain gaps and learns from multiple domains.

This dissertation proposes methods for multi-domain adaptation for various computer vision tasks, including image classification, depth estimation, and semantic segmentation. The first work focuses on semi-supervised domain adaptation. I address this semi-supervised setting and propose …

Small Approximate Pareto Sets With Quality Bounds, William Bailey

Theses and Dissertations--Computer Science

We present and empirically characterize a general, parallel, heuristic algorithm for computing small ε-Pareto sets. The algorithm can be used as part of a decision support tool for settings in which computing points in objective space is computationally expensive. We use the graph clearing problem, a formalization of indirect organ exchange markets, as a prototypical example setting. We characterize the performance of the algorithm through ε-Pareto set size, ε value provided, and parallel speedup achieved. Our results show that the algorithm's combination of parallel speedup and small ε-Pareto sets is sufficient to be appealing in settings requiring manual review (i.e., …

Multi-Agent Learning For Game-Theoretical Problems, Kshitija Taywade

Theses and Dissertations--Computer Science

Multi-agent systems are prevalent in the real world in various domains. In many multi-agent systems, interaction among agents is inevitable, and cooperation in some form is needed among agents to deal with the task at hand. We model the type of multi-agent systems where autonomous agents inhabit an environment with no global control or global knowledge, decentralized in the true sense. In particular, we consider game-theoretical problems such as the hedonic coalition formation games, matching problems, and Cournot games. We propose novel decentralized learning and multi-agent reinforcement learning approaches to train agents in learning behaviors and adapting to the environments. …

A Secure And Distributed Architecture For Vehicular Cloud And Protocols For Privacy-Preserving Message Dissemination In Vehicular Ad Hoc Networks, Hassan Mistareehi

Theses and Dissertations--Computer Science

Given the enormous interest in self-driving cars, Vehicular Ad hoc NETworks (VANETs) are likely to be widely deployed in the near future. Cloud computing is also gaining widespread deployment. Marriage between cloud computing and VANETs would help solve many of the needs of drivers, law enforcement agencies, traffic management, etc. The contributions of this dissertation are summarized as follows: A Secure and Distributed Architecture for Vehicular Cloud: Ensuring security and privacy is an important issue in the vehicular cloud; if information exchanged between entities is modified by a malicious vehicle, serious consequences such as traffic congestion and accidents can …

Machine-Learning-Powered Cyber-Physical Systems, Enrico Casella

Theses and Dissertations--Computer Science

In the last few years, we witnessed the revolution of the Internet of Things (IoT) paradigm and the consequent growth of Cyber-Physical Systems (CPSs). IoT devices, which include a plethora of smart interconnected sensors, actuators, and microcontrollers, have the ability to sense physical phenomena occurring in an environment and provide copious amounts of heterogeneous data about the functioning of a system. As a consequence, the large amounts of generated data represent an opportunity to adopt artificial intelligence and machine learning techniques that can be used to make informed decisions aimed at the optimization of such systems, thus enabling a variety …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …

The Basil Technique: Bias Adaptive Statistical Inference Learning Agents For Learning From Human Feedback, Jonathan Indigo Watson

Theses and Dissertations--Computer Science

We introduce a novel approach for learning behaviors using human-provided feedback that is subject to systematic bias. Our method, known as BASIL, models the feedback signal as a combination of a heuristic evaluation of an action's utility and a probabilistically-drawn bias value, characterized by unknown parameters. We present both the general framework for our technique and specific algorithms for biases drawn from a normal distribution. We evaluate our approach across various environments and tasks, comparing it to interactive and non-interactive machine learning methods, including deep learning techniques, using human trainers and a synthetic oracle with feedback distorted to varying degrees. …

Deep Learning Models For Ct Image Standardization, Md Selim

Theses and Dissertations--Computer Science

Multicentric CT imaging studies often encounter images acquired with scanners from different vendors or using different reconstruction algorithms. This leads to inconsistencies in noise level, sharpness, and edge enhancement, resulting in a lack of homogeneity in radiomic characteristics. These inconsistencies create significant variations in radiomic features and ambiguity in data sharing across different institutions. Therefore, normalizing CT images acquired using non-standardized protocols is vital for decision-making in cross-center large-scale data sharing and radiomics studies. To address this issue, we present four end-to-end deep-learning-based models for CT image standardization and normalization. The first two models require paired training data and can …

Structured Attention For Image Analysis, Xin Xing

Theses and Dissertations--Computer Science

Attention mechanism, an approach to maintain the local and global features over the input, is the crucial element of the Transformer. This dissertation explores structured attention for image analysis, proposing attention-based methods for multi-label learning and Alzheimer’s Disease (AD) diagnosis.
For the multi-label learning task, I present two works under the Vision Transformer (ViT) framework. The first work focuses on supervised learning of multi-label classification. I address the problems of the multi-label classification and propose a model named AssocFormer, which adopts the association module to access the objects’ association relationship to improve the model performance. The second work addresses the …

Hard-Hearted Scrolls: A Noninvasive Method For Reading The Herculaneum Papyri, Stephen Parsons

Theses and Dissertations--Computer Science

The Herculaneum scrolls were buried and carbonized by the eruption of Mount Vesuvius in A.D. 79 and represent the only classical library discovered in situ. Charred by the heat of the eruption, the scrolls are extremely fragile. Since their discovery two centuries ago, some scrolls have been physically opened, leading to some textual recovery but also widespread damage. Many other scrolls remain in rolled form, with unknown contents. More recently, various noninvasive methods have been attempted to reveal the hidden contents of these scrolls using advanced imaging. Unfortunately, their complex internal structure and lack of clear ink contrast has prevented …

Deep Learning-Based Intrusion Detection Methods For Computer Networks And Privacy-Preserving Authentication Method For Vehicular Ad Hoc Networks, Ayesha Dina

Theses and Dissertations--Computer Science

The incidence of computer network intrusions has significantly increased over the last decade, partially attributed to a thriving underground cyber-crime economy and the widespread availability of advanced tools for launching such attacks. To counter these attacks, researchers in both academia and industry have turned to machine learning (ML) techniques to develop Intrusion Detection Systems (IDSes) for computer networks. However, many of the datasets use to train ML classifiers for detecting intrusions are not balanced, with some classes having fewer samples than others. This can result in ML classifiers producing suboptimal results. In this dissertation, we address this issue and present …

Deep Learning, 3d Ultrastructural Analysis Reveals Quantitative Differences In Platelet And Organelle Packing In Covid-19/Sarscov2 Patient-Derived Platelets, Sagar S. Matharu, Cassidy S. Nordmann, Kurtis R. Ottman, Rahul Akkem, Douglas Palumbo, Denzel R. D. Cruz, Kenneth Campbell, Gail Sievert, Jamie L. Sturgill, James Zachary Porterfield, Smita Joshi, Hammodah Rawhi Hammodah Alfar, Chi Peng, Irina D. Pokrovskaya, Jeffrey A. Kamykowski, Jeremy P. Wood, Beth A. Garvy, Maria A. Aronova, Sidney W. Whiteheart, Richard D. Leapman, Brian Storrie

Saha Cardiovascular Research Center Faculty Publications

Platelets contribute to COVID-19 clinical manifestations, of which microclotting in the pulmonary vasculature has been a prominent symptom. To investigate the potential diagnostic contributions of overall platelet morphology and their α-granules and mitochondria to the understanding of platelet hyperactivation and micro-clotting, we undertook a 3D ultrastructural approach. Because differences might be small, we used the high-contrast, high-resolution technique of focused ion beam scanning EM (FIB-SEM) and employed deep learning computational methods to evaluate nearly 600 individual platelets and 30 000 included organelles within three healthy controls and three severely ill COVID-19 patients. Statistical analysis reveals that the α-granule/ mitochondrion-to-plateletvolume ratio …

Surficial Geologic Map Of The Rockfield 7.5-Minute Quadrangle, Warren, Logan, And Simpson Counties, Kentucky, Wes Buchanan, Meredith Swallom, Antonia Bottoms, Matthew Massey, Bailee Nicole Hodelka, Emily Morris

Contract Reports--KGS

The Rockfield 7.5-minute quadrangle is located west of Bowling Green, Kentucky situated mostly in Warren County, but also includes small areas of Simpson and Logan Counties in its southwestern corner. Regionally, the quadrangle includes parts of the Pennyroyal and Mammoth Cave plateau within the Mississippian Plateaus physiographic region (McDowell, 1986). The Dripping Springs escarpment, which separates the lower-elevation Pennyroyal from the higher-elevation Mammoth Cave plateau is highly dissected in the quadrangle. Topography in the Pennyroyal is characterized by pervasive sinkhole development across a low-relief plain, which is mostly underlain by the Mississippian Ste. Genevieve Limestone. Higher-relief topography is restricted to …

Peer-To-Peer Energy Trading In Smart Residential Environment With User Behavioral Modeling, Ashutosh Timilsina

Theses and Dissertations--Computer Science

Electric power systems are transforming from a centralized unidirectional market to a decentralized open market. With this shift, the end-users have the possibility to actively participate in local energy exchanges, with or without the involvement of the main grid. Rapidly reducing prices for Renewable Energy Technologies (RETs), supported by their ease of installation and operation, with the facilitation of Electric Vehicles (EV) and Smart Grid (SG) technologies to make bidirectional flow of energy possible, has contributed to this changing landscape in the distribution side of the traditional power grid.

Trading energy among users in a decentralized fashion has been referred …

Estimating Bedrock Shear Wave Velocity At Vsap, Paducah, Kentucky, Using Ambient Noise, Russel Rogers

Theses and Dissertations--Earth and Environmental Sciences

Due to the nature of the Mississippi Embayment region and its vicinity to the New Madrid Seismic Zone, earthquake ground-motion site effects are potential hazards and quantifying the associated hazard is a necessary step for public safety. Measuring the V_s contrast between bedrock and overlying soil layers is necessary for site effect evaluation. Various methodologies for investigating shear wave velocity (V_s) profiles have been implemented in the Mississippi Embayment. However, these previous studies provided a wide range of bedrock Vs. In this study, microtremor array measurements, utilizing ambient background noise, were used to provide an additional estimate …

Moral Foundations And Student Perceptions Of Academic Dishonesty: A Mixed Methods Study, Carla Spires Hargus

Theses and Dissertations--Curriculum and Instruction

This mixed methods study explored students’ hypothetical choices of behavior in a series of ten academic vignettes. In addition, it examined student judgments of academic behaviors as acceptable or dishonest. Finally, it compared scores on the Moral Foundations Questionnaire-2 to the importance of factors that might influence student behavioral choices in real world scenarios and explored the differences in perceptions among demographic groups.

Twenty-five undergraduate students participated in the study. In a semi-structured interview, each student discussed ten academic vignettes: predicting their own hypothetical behavioral choice, judging target behaviors as honest or dishonest, and identifying factors that would most influence …

Addressing A Cohort Discrepancy Among Ninth-Grade Students At A Rural/Suburban High School, Bryley Keaton Murphy

Theses and Dissertations--Educational Leadership Studies

Ninth grade is a critical period where some children experience academic and social growth, while others struggle to navigate their new context, leading to reduced outcomes at school and worsened physical/mental health (Benner & Graham, 2007; Rice, 2001). This mixed-methods action research (MMAR) study addressed how professional practice changes could better support students during this foundational period. Quantitative data was collected from school databases to compare the rate of student success and identify demographic discrepancies, while qualitative data was used to identify possible causes. These data were then integrated to create insightful meta-inferences into the problem of practice. From these …

Principals As Instructional Leaders: Building Knowledge Of Applied Learning To Confidently Lead Implementation, Janell Lynn Mcclure

Theses and Dissertations--Educational Leadership Studies

Principals need to understand best practices and research-based strategies that foster student success and that align to their instructional expectations and professional goals. Some of those practices include applied learning strategies such as integrated learning, student-driven learning, and authentic applications. Unfortunately, little professional learning, specifically for principals, is made available on the topic of instructional leadership, current strategies, or applied learning in general. As a result, school leaders continue to follow a traditional instructional model that includes teacher-directed instruction, student recall of information, and standardized tests as measures of content mastery.

This dissertation was a mixed-methods action research study. The …

Embracing Rural First-Generation College Student Scholar Identity: Wading Waist Deep In Unfamiliar Waters, Robert Hayes

Theses and Dissertations--Educational Policy Studies and Evaluation

First-generation college students do not persist to degree completion at the same rate as their continuing generation peers. There is a wide range of research focusing on the challenges and opportunities that first-generation college students experience, ranging from pre-matriculation factors, the transition period to college, and throughout the undergraduate years. The achievement gap, in terms of persistence to degree, has been a consistent focus of research as first-generation students routinely do not earn college degrees at the same rate as their continuing generation peers. This research takes a holistic approach to understanding the first-generation college student experience that does not …

Principal Leadership Practices At Kentucky High Schools Administering The Pisa For Schools: Leading For Global Competitiveness, Marjorie L. Johnson

Theses and Dissertations--Education Sciences

Since launching Sputnik in 1957, the United States education system has been trying to climb to the top of the international education rankings. The Organisation for Economic and Co-operative Development (OECD) began analyzing how well school systems prepared students to compete in the global economy in 2000. The OECD uses the Programme for International Student Assessment (PISA). U.S. students rank at or near the OECD averages in reading and science but consistently perform below the OECD average in mathematics. In addition to the PISA, the OECD released the PISA for Schools, which provides PISA data at the school level.

In …

The Perceptions And Usage Of The Interactive Video Playposit In A General Chemistry Course, Tracy Gastineau-Stevens

Theses and Dissertations--Education Sciences

Technology within science, technology, engineering, and mathematics (STEM) classrooms has been a topic of discussion for decades (Reiser, 2001, 2007). With the inclusion of more technologies or digital tools in the classroom has pushed classes towards a blended learning or flipped classroom approach (Atkins 2015; Tayebinik & Puteh, 2013; Williams et al., 2008). One such digital tool that has started gaining traction in the STEM classroom is the interactive video (M. K. Seery, 2013; Smith, 2013). Interactive videos allow students to watch the general lecture material outside of class and work through problems during normal class time (M. K. Seery, …

Developing Pedagogical Content Knowledge As Communal Practice: A Case Study Of Chemistry Graduate Teaching Assistants, Walker Bryan Mask

Theses and Dissertations--Education Sciences

Learning does not only happen during dedicated instructional time, which also applies to learning how to teach. Teachers can reflect on their practice while working to continue to improve and develop their teaching skills. In addition to self-reflection, teachers can also learn from their colleagues to experiment with new practices and take others’ teaching knowledge into their repertoire. Understanding how these two processes function can lead to developments in teacher education and professional development, specifically for initiatives that seek to promote collaboration among teachers. Post-secondary educators in particular can benefit from collaborative and reflective practices to improve their teaching, especially …

Development And Validity Inquiry Of A Rubric For Interdisciplinary Competencies In Occupational Safety And Health In Capstone Projects Of Carerc Program Graduates, Olumuyiwa Moses Desmennu

Theses and Dissertations--Education Sciences

Emerging demands in the field of interdisciplinary studies reveal a need for competent professionals who can apply their skills and experience to solving complex tasks of the workplace. This has placed inevitable demands on training institutions to adequately equip graduates to deliver on their mandate. Competency appraisal is an effective way to ensure proficiency in graduates. Meanwhile, transparent and valid rubrics provide opportunities for both students and trainers to continuously assess and evaluate the transfer of necessary skills.

This study focused on evaluating interdisciplinary competencies in Occupational Safety and Health (OSH) in the capstone projects of the CARERC program, a …

Julie Giroux’S Symphony No. 6: The Blue Marble Background, Analysis, And Conductor’S Guide, Josh Gillen

Theses and Dissertations--Music

Julie Giroux’s Symphony No. 6: The Blue Marble (2022) is an original work for wind band that is quickly rising in popularity among instrumental conductors and ensembles throughout the world. The purposes of this document are to

1) provide biographical details regarding Julie Giroux and her musical career;

2) provide a background of the work’s conception from a musical and multi-media perspective through interviews with Giroux and the first conductors of the work;

3) provide a multi-parametric structural analysis of the work and its companion film;

4) provide conductors with useful information for programming and rehearsing the work.

Chapter one …

Advancements In Glycogen Detection And Spatial Profiling Reveals A New Therapeutic Path For Ewing Sarcoma: A Non-Traditional Glycogen Storage Disease, Lyndsay E. A. Young

Theses and Dissertations--Molecular and Cellular Biochemistry

Glycogen is the primary glucose storage carbohydrate in mammals, and it is synthesized in most tissues. As glycogen architecture modulates its role in metabolism, it is essential to accurately evaluate and quantify glycogen, glycogen phosphate, and chain length of glucose monomers. Simultaneous quantitation of glycogen architecture is challenging. This work describes a highly-sensitive method for the detection of both glycogen-derived glucose and glucose-phosphate esters utilizing gas-chromatography coupled mass spectrometry (GCMS). We then integrated this glycogen quantitation workflow into a routinely utilized metabolomics-based assay. The work presented describes a workflow for the normalization of polar metabolites utilizing amino acids derived from …

Multilevel Phenotypic Integration Of Metabolism And Behavior In House Sparrows And Mice, Tim Salzman

Theses and Dissertations--Biology

Patterns of multilevel variation in behavior, both within and among individuals, raise challenging questions about underlying mechanisms and the selective pressures acting on them. One intriguing hypothesis is that physiology shows parallel multilevel variation, and so might represent a latent trait that integrates multilevel behavioral responses. For example, foraging acquires the fuel needed to maintain metabolism, and in turn, an individual’s metabolism affects expression of foraging, and other, behaviors. Metabolism and behavior thus might coevolve to become integrated traits. Despite the appeal of this hypothesis, numerous investigations into the link between metabolism and behavior have yielded largely equivocal results.

To …

Brain Glycogen – Beyond Energy Storage In Glycogen Storage Diseases, Kia H. Markussen

Theses and Dissertations--Molecular and Cellular Biochemistry

Glycogen is a carbohydrate molecule that is traditionally viewed as a convenient and easily accessible energy storage form of glucose. However,emerging evidence supports the role of glycogen as more than a glucose storage form. During the last 20 years, glycogen has been shown to play pivotal roles in learning and memory, signaling events, viscosity, protein glycosylation, and be acritical hallmark in devastating diseases. Not only, does glycogen play a role as an energy substrate and critical metabolite during energy deprivation, glycogen is central for neurotransmitter homeostasis, tumor initiation, and ontributes to proper protein glycosylation in the brain. In this work, …

Computational Investigation Of A Series Of Small Molecules As Potential Compounds For Lysyl Hydroxylase-2 (Lh2) Inhibition, Yazdan Maghsoud, Erik Antonio Vázquez-Montelongo, Xudong Yang, Chengwen Liu, Zhifeng Jing, Juhoon Lee, Matthew Harger, Ally K. Smith, Miguel Espinoza, Hou-Fu Guo, Jonathan M. Kurie, Kevin N. Dalby, Pengyu Ren, G. Andrés Cisneros

Markey Cancer Center Faculty Publications

The catalytic function of lysyl hydroxylase-2 (LH2), a member of the Fe(II)/αKG-dependent oxygenase superfamily, is to catalyze the hydroxylation of lysine to hydroxylysine in collagen, resulting in stable hydroxylysine aldehyde-derived collagen cross- links (HLCCs). Reports show that high amounts of LH2 lead to the accumulation of HLCCs, causing fibrosis and specific types of cancer metastasis. Some members of the Fe(II)/αKG-dependent family have also been reported to have intramolecular O2 tunnels, which aid in transporting one of the required cosubstrates into the active site. While LH2 can be a promising target to combat these diseases, efficacious inhibitors are still lacking. We …

Polycomb Deficiency Drives A Foxp2-High Aggressive State Targetable By Epigenetic Inhibitors, Fan Chen, Aria Byrd, Jinpeng Liu, Robert M. Flight, Tanner Ducote, Kassandra J. Naughton, Xiulong Song, Abigail R Edgin, Alexsandr Lukyanchuk, Danielle T. Dixon, Christian M. Gosser, Dave-Preston Esoe, Rani Jayswal, Stuart H. Orkin, Hunter N. B. Moseley, Chi Wang, Christine Fillmore Brainson

Markey Cancer Center Faculty Publications

Inhibitors of the Polycomb Repressive Complex 2 (PRC2) histone methyltransferase EZH2 are approved for certain cancers, but realizing their wider utility relies upon understanding PRC2 biology in each cancer system. Using a genetic model to delete Ezh2 in KRAS-driven lung adenocarcinomas, we observed that Ezh2 haplo-insufficient tumors were less lethal and lower grade than Ezh2 fully-insufficient tumors, which were poorly differentiated and metastatic. Using three-dimensional cultures and in vivo experiments, we determined that EZH2-deficient tumors were vulnerable to H3K27 demethylase or BET inhibitors. PRC2 loss/inhibition led to de-repression of FOXP2, a transcription factor that promotes migration and stemness, and FOXP2 …