Digital Commons Network^™

Comparative Analysis Of Machine Learning Models For Glioblastoma Survival., Muna Awel

All Graduate Theses, Dissertations, and Other Capstone Projects

Glioblastoma multiforme (GBM) remains one of the most lethal brain tumors, necessitating improved survival prediction models that integrate clinical and molecular data. This study develops a comprehensive machine learning pipeline leveraging TCGA-derived multi-omics datasets to predict binary survival outcomes. The framework integrates four classifiers Logistic Regression, Random Forest, XGBoost, and Support Vector Machine (SVM) and includes rigorous preprocessing with MCAR testing, KNN imputation, feature scaling, and hyperparameter optimization via GridSearchCV. SMOTE was applied to mitigate class imbalance and enhance model robustness for minority survival classes. Comparative performance analyses revealed Random Forest and XGBoost as top performers, achieving the highest recall …

Rotary Operations Management & Automation Platform (Romap): Modernizing Attendance Tracking And Data Submission For Rotary Clubs, Zaineel Mithani

2025 Fall Honors Capstones Projects - Archive

As Technical Lead of the Rotary Operations Management & Automation Platform (ROMAP), my Honors contribution focused on developing a Bluetooth Low Energy proximity-based attendance system enabling automatic, hands-free member check-ins. I researched and selected beacon hardware, designed RSSI-based distance calculation algorithms, and implemented platform-specific background processing for iOS and Android, achieving 97% detection accuracy. Beyond this Honors component, I architected the complete backend infrastructure including a Node.js API with 20+ endpoints, PostgreSQL database with Prisma ORM, and JWT authentication. I also developed a novel GPT-4 Vision automation system that intelligently populates web forms through computer vision, achieving 95% success rate …

Identifying The Constituents Of Pyrolysis Oil Using Supercritical Fluid Chromatography- Fraction Collection (Sfc-Fc) And Gas Chromatography- Mass Spectrometry/Vacuum Ultraviolet Spectroscopy (Gc-Ms/Vuv), Sadid Morshed

2025 Fall Honors Capstones Projects - Archive

Plastic waste continues to accumulate as production increases and disposal methods remain insufficient. Even with recycling programs in place, much of the discarded plastic still ends up in landfills or waterways, eventually breaking down into harmful microplastics. One promising solution is the conversion of plastic waste into pyrolysis oil, which can also serve as an alternative feedstock for chemicals. Pyrolysis oil is produced by heating plastics to approximately 800 °C in the absence of oxygen, resulting in a complex mixture of hydrocarbons that includes paraffins, isoparaffins, olefins, naphthenes, and aromatics. Analyzing the amount of oxygen, nitrogen, and sulfur in these …

The Effect Of Zebra Mussels On Minnesota Fish Communities, Benjamin D. Strei

Journal of Earth and Life Science

Zebra mussels Dreissena polymorpha are an aquatic invasive species that has been spreading quickly throughout Minnesota water bodies since 1989. Zebra mussels are known to change certain morphological conditions in lakes such as turbidity, phytoplankton abundance, and aquatic invertebrate populations. However, studies showing impacts of the infestation of zebra mussels on the health of a fish community have been hard to prove due to a lack of repeated surveys and a suite of other confounding variables such as natural and seasonal variability, plant community, and lake morphometry. Therefore, the objective of this study is to determine whether zebra mussels have …

The Impact Of Inter-Subunit Communication On F420h2:Nadp+ Oxidioreductase: A Kinetic Approach, Jamariya A. Howard

Chemistry & Biochemistry Dissertations - Archive

F₄₂₀H₂:NADP⁺ Oxidoreductase (Fno) catalyzes the reversible reduction of NADP⁺ to NADPH using reduced F₄₂₀ as the hydride donor. Both NADPH and the F₄₂₀ cofactor play significant roles in various metabolic pathways, including glycolysis and methanogenesis, particularly in methanogenic and sulfate-reducing archaea. These organisms play an essential role in global carbon cycling by converting carbon dioxide to methane through the methanogenic pathway, which is directly tied to energy production. This thesis investigates the hydride transfer mechanism of Fno from the extreme thermophile Archaeoglobus fulgidus, using fluorescence binding, steady-state and pre steady-state kinetics.

Chapter 1 outlines the structural and spectral characteristics …

Statistical Analysis Of Climate Trends And Variability In Tarrant County Using Annual, Decade, And Three-Decade Time Periods, Quinnton Debolt

Earth & Environmental Sciences Theses - Archive

This study is a statistical analysis of climate trends within the Dallas-Fort Worth metroplex according to several time-scale models to understand how the climate for the locality has changed and to provide a basis for projections of what future climate might look like. Trends in mean temperature and precipitation for North Central Texas generally correlate with corresponding global trends linked to natural variability and anthropogenic-induced climate change. Temperature rises in this region annually by 0.08°C and by 0.22°C for a three-decade average. Seasonal increases in three-decadal averages of temperature for North Central Texas relative to the average of the reference …

Scalable, Secure, And Adaptable Perception Systems Through Adversarial Analysis And Federated Fine-Tuning, Arkajyoti Mitra

Computer Science and Engineering Dissertations - Archive

Perception systems are fundamental to intelligent machines, enabling them to sense, understand, and interpret complex environments. However, as perception increasingly underpins critical applications such as autonomous vehicles, IoT healthcare devices, and smart trading platforms, challenges related to security, scalability, and environmental understanding have become more pressing. This work addresses three core research questions: (1) How can we identify, analyze, and mitigate adversarial vulnerabilities in perception systems to ensure reliable operation under adversarial conditions? (2.1) How can AVPS models be efficiently scaled and fine-tuned across decentralized and resource-constrained environments while preserving privacy and performance? (2.2) How can we scale generative models …

Lowering The Barrier For Reading Primary Literature In Stem, Sebastian G. Alvarado, Maral Tajerian

Open Educational Resources

Building Bridges of Knowledge (BBK) is a cross‑CUNY initiative that integrates artificial intelligence (AI) and open educational resources to lower the barrier to primary literature and enhance research‑focused pedagogy. Recognizing that scientific papers are often dense and inaccessible to newcomers, we developed a suite of AI‑assisted instructional materials and activities to help students interpret complex data and methodology. A central component is the use of large language models (LLMs) and tools such as Scite.ai to provide citation‑context analytics and personalized research support. These tools allow students to filter literature by supportive, neutral, or contrasting citation statements and to troubleshoot laboratory …

Consequences Of Artificial Intelligence In Health Insurance: Lawsuits, Policy, And Ethics, Alyssa N. Roberts

Honors Undergraduate Theses

In recent years, the healthcare system has been burdened by a multitude of obstacles that hinder the ability to provide effective, affordable, and timely care. Among these, one of the most significant challenges is the role that health insurance plays in shaping the quality of care. Health insurance companies are designed to decrease financial strain on patients, but they have introduced inefficiencies through delayed coverage approvals, increased denials, and administrative costs. Artificial intelligence (AI) has started to play an integral role in resolving these issues for the health insurance industry. Through its quick automated claim processing, fraud screening, and reduced …

Enhancing The Accuracy Of Image Classification For Degenerative Brain Diseases With Cnn Ensemble Models Using Mel-Spectrograms, Sang-Ha Sung, Michael Pokojovy, Do-Young Kang, Woo-Yong Bae, Yeon-Jae Hong, Sangjin Kim

Mathematics & Statistics Faculty Publications

Alzheimer’s disease (AD) and Parkinson’s disease (PD) are prevalent neurodegenerative disorders among the elderly, leading to cognitive decline and motor impairments. As the population ages, the prevalence of these neurodegenerative disorders is increasing, providing motivation for active research in this area. However, most studies are conducted using brain imaging, with relatively few studies utilizing voice data. Using voice data offers advantages in accessibility compared to brain imaging analysis. This study introduces a novel ensemble-based classification model that utilizes Mel spectrograms and Convolutional Neural Networks (CNNs) to distinguish between healthy individuals (NM), AD, and PD patients. A total of 700 voice …

Covariate Selection For Rna-Seq Differential Expression Analysis With Hidden Factor Adjustment, Farzana Noorzahan, Hyeongseon Jeon, Yet Nguyen

Mathematics & Statistics Faculty Publications

In RNA-seq data analysis, a primary objective is the identification of differentially expressed genes, which are genes that exhibit varying expression levels across different conditions of interest. It is widely known that hidden factors, such as batch effects, can substantially influence the differential expression analysis. Furthermore, apart from the primary factor of interest and unforeseen artifacts, an RNA-seq experiment typically contains multiple measured covariates, some of which may significantly affect gene expression levels, while others may not. Existing methods either address the covariate selection or the unknown artifacts separately. In this study, we investigate two integrated strategies, FSR_sva and SVAall_FSR, …

Movement And Activity Of Burbot, (Mizay; Lota Lota) In A Spring-Fed Minnesota Lake, Abigail M. Fountain

Biology Graduate Theses

Burbot (Mizay; Lota lota) are a relatively unmanaged freshwater fish, important in many local Indigenous cultures, but often overlooked or maltreated in research, conservation, and fishing practices. As such, relatively little research has been conducted on Burbot, despite ecological significance as an indicator species. A recent resurgence in popularity as a target species, however, has prompted new research to inform management policies. The objectives of this study were to summarize Burbot movement by identifying patterns in swimming activity and identify possible predictors of the movement observed. This study investigated the movements of 39 individuals implanted with acoustic transmitters in Bad …

Perceptions Of Artificial Intelligence Use To Enhance Feedback For Preservice Teachers During Field Experiences, Betsy Schamber

Dissertations and Theses

University supervisors (USs) play a key role in providing feedback for preservice teachers (PSTs). Although artificial intelligence (AI)’s use in providing feedback in educational settings had been explored, its use for feedback for PSTs’ field experience remained unknown. The first case study herein explores PSTs’ perceptions of AI-assisted feedback for field experiences. Findings highlighted PSTs’ perceptions of AI as a catalyst for new idea generation. While AI provided a starting point, the ending output still needed to reflect PSTs’ personalities. Similarly, PSTs valued the human element of feedback, noting how USs’ lived experiences provided an added value. In K–12 classrooms, …

Embedding With Large Language Models For Classification Of Hipaa Safeguard Compliance Rules, Md Abdur Rahman, Md Abdul Barek, Abm Kamrul Islam Riad, Md Mostafizur Rahman, Bajlur Rashid, Md Raihan Mia, Hossain Shahriar, Guillermo Francia, Fan Wu, Alfredo Cuzzocrea, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA rules categories. Therefore, providing guidance of HIPAA rules patterns classification is essential for developing secured applications for Google Play Store. In this work, we identified the limitations of traditional Word2Vec embeddings in processing code patterns. To address this, we adopt multilingual BERT (Bidirectional Encoder Representations from Transformers) which offers contextualized embeddings to the attributes of dataset to overcome the issues. Therefore, we applied this BERT to …

Artificial Intelligence In Society: Transformations And Ethical Paradigm, Yashoda Urmilla Itwaru

Selected Full-Text Master Theses 2021-

The recent advancement and adoption of AI (Artificial Intelligence) make it vital to study the effects it has on individuals and communities. Adopting AI into daily life changes interactions such as the decision-making process and task performance. AI algorithms can shape a user’s online experiences, influence their preferences, beliefs, and behavior. However, people raised concerns regarding privacy, autonomy, and manipulation. For these reasons, debates regarding the ethical aspects of AI arose.

AI provides society with more tools to complete tasks. AI can automate data intensive jobs and physical tasks. This brings a sense of job insecurity, which affects the mental …

Edge-Enhanced Yolo V8 Architecture For Accurate Kl Assessment In Knee Osteoarthritis Imaging, Meghana Arikilla

Selected Full-Text Master Theses 2021-

Knee Osteoarthritis (KOA) is a degenerative joint condition characterized by the progressive narrowing of joint space and structural deterioration. The structural degradation of the joint space is evaluated using the Kellgren–Lawrence (KL) grading system, and accurate classification across all grades, specifically in the early stages, remains a challenge owing to subtle radiographic differences. This study presents an automated KL-grade classification framework that integrates joint edge enhancement with deep learning to improve KOA grading using radiographic images.

Edge detection filters, namely Sobel, Scharr, and Canny, were applied to X-ray images to enhance the joint space boundaries and osteoarthritic features. These preprocessed …

Sptiotemporal Changes In Aboveground Biomass, Canopy Cover And Livestock Movements Across Mongolia Grasslands, Abhinav Chandel

Dissertations and Theses

This study presents an integrated geospatial framework for understanding grassland productivity dynamics and livestock movement behavior across the Mongolian steppe. Mongolia’s grasslands constitute one of the world’s largest pastoral ecosystems, yet they face increasing vulnerability due to climate variability, overgrazing, and land degradation. To quantify vegetation change and grazing responses, this research combines multi-decadal remote sensing with high-frequency GPS-based livestock movement tracking. Using Landsat imagery from 1990 to 2023, Aboveground Biomass (AGB) and Canopy Cover (CC) were estimated through Random Forest regression models integrating key spectral vegetation indices (e.g., NDVI, OSAVI, CTVI, TNDVI, IPVI) and climatic predictors such as summer …

Investigating The Impact Of Pfas Contamination On Mental Health, Jihyun Kim

Open Educational Resources

To explore the intersection of environmental injustice, racial disparities, and public health through an examination of PFAS contamination in drinking water and its impact on communities of color. This study will address environmental, social, and health implications of PFAS exposure, with a specific emphasis on promoting equity and advocating for policy changes to rectify systemic inequalities.

Reducing Friction In Machine Oil Via Cesium-Hybridized Graphene Oxide Quantum Dot Additives, Islam Gomaa, Sherief Elsoudy, Maryam Galal, Ahmed Azim

Nanotechnology Research Centre

Friction and wear are among the most common causes of energy loss and component failure in mechanical systems, accounting for around 20–30% of total global energy consumption. Conventional lubricants fail to provide consistent performance in harsh conditions due to inadequate additive dispersion, agglomeration, and restricted surface reactivity. Recent advances in nanomaterial-based lubricants have shown promise, but it remains difficult to achieve significant friction and wear reduction at low additive concentrations while preserving stability. In this study, we synthesized and tested cesium-hybridized graphene oxide quantum dots (Cs-GOQDs) as novel lubricant additives. When incorporated into machine oil at 0.1 wt%, Cs-GOQDs reduced …

Geological And Environmental Sciences - 2025, Dept. Of Geological And Environmental Sciences

Geological and Environmental Sciences News

• Greetings from the Department Chair
• Faculty Updates
• 2025 Geological and Environmental Sciences Department Alumni Achievement Awardee Mr. Thomas Hanna
• 60 Years - Telling Our Story
• Empowering the next generation of geoscientists

Insects, Ai Systems, And The Future Of Legal Personhood, Jeff Sebo

Animal Law Review

This Article makes a case for insect and AI legal personhood. Humans share the world not only with large animals like chimpanzees and elephants but also with small animals like ants and bees. In the future, we might also share the world with sentient or otherwise morally significant AI systems. These realities raise questions about what kind of legal status insects, AI systems, and other nonhumans should have in the future. At present, debates about legal personhood mostly exclude these kinds of individuals. However, I argue that our current framework for assessing legal personhood, coupled with our current framework for …

What Amino Acid Residue Is Responsible For The Interaction Of Atg11 With Its Autophagy Partner Atg9?, Patricia Omoyemwen Woghiren

Senior Honors Theses and Projects

Macroautophagy is a cellular function that involves the formation of a double membrane vesicle that isolates and transports cellular materials to the vacuole or lysosome for degradation and recycling. It is divided into selective and non-selective macroautophagy. Atg11 and Atg9 are two key proteins involved in selective macroautophagy, and their interaction is critical for selective macroautophagy. Specific residues on Atg9 critical for Atg11 binding have been identified, but similar residues on Atg11 have not been identified. The aim of my research was to identify a specific residue critical for Atg11’s interaction with Atg9. To this end, we carried out Yeast-twohybrid …

Analysis Of Errors In The Management Of Cutaneous Disorders, Robert J. Pariser, Sarah Alnaif

Department Dermatology Faculty Publications

In this study, we prospectively and retrospectively evaluated the occurrence of errors in the management of cutaneous disorders from patient visits and medical records in a single dermatology practice in southeast Virginia over a 3-year period (June 2020-July 2023). Providers should be able to improve diagnostic accuracy by utilizing established rapid bedside diagnostic techniques.

Ex Vivo Single-Molecule Analysis Of Ryanodine Receptor 2 Assembly In Cardiac And Neuronal Tissue, Qianye Yin, Christopher I. Richards

Chemistry Faculty Publications

Understanding receptor assembly is critical for elucidating the mechanisms underlying their function and regulation in physiological processes. While traditional in vitro single-molecule studies rely on isolating proteins from heterologous expression systems, they often fail to capture the in vivo physiological complexity involved in the organization and assembly of cell surface proteins. This protocol employs Total Internal Reflection Fluorescence Microscopy (TIRFM) to study GFP-tagged Ryanodine Receptor 2 (RyR2) molecules encapsulated within nanoscale vesicles. These vesicles, generated from organs rapidly extracted from the animal, effectively provide a snapshot of the receptor's assembly state at the time of extraction, enabling detailed analysis of …

Exploiting Artificial Intelligence And Optimization For Smart Agriculture, Jackson K. Butcher

Theses and Dissertations--Computer Science

Dynamic integration of Cyber-Physical Systems (CPS) and Artificial Intelligence (AI) has become a vital component for unlocking the potential of smart agriculture. Currently, limitations such as limited computational resources, poor network connectivity, and rigid treatment strategies stifle optimal agricultural outcomes. This creates a challenge of leveraging the capabilities of modern artificial intelligence to combat the natural and artificial constraints of the smart agriculture environment. The primary contribution of this thesis is the development of frameworks to alleviate the overhead data and computational demand for AI within smart agriculture settings. The first framework, iCrop+, utilizes TinyML and LoRa to guarantee high-precision …

Assessing The Dallas-Fort Worth Urban Microclimate And Surface Ozone Variability Under Differing Drought Conditions, Patrick Sumner

Earth & Environmental Sciences Theses - Archive

The Dallas-Fort Worth metroplex in North Central Texas is the 4^th largest and fastest growing region in the United States. In this study, the response of the urban microclimate and ozone levels to drought conditions will be assessed. The urban heat island (UHI), defined as the temperature difference between an urban and rural weather station, was filtered for low wind speeds (≤ 3 m s^-1). An in-depth analysis of the UHI at 1200 CST was done from 2008-2023 to identify trends. A significant correlation exists between the Palmer drought severity index and the UHI at 1200 CST, …

Design And Implementation Of A Low-Cost Raspberry Pi And Ai-Based Intrusion Detection System For Surveillance, Metrine Nyaboke Osiemo

All Graduate Theses, Dissertations, and Other Capstone Projects

As security concerns continue to rise, there is a growing demand for affordable and intelligent surveillance solutions to ensure safety in homes, businesses, and other environments. Many individuals are embracing AI-driven technologies such as Closed-Circuit Television (CCTV), smart doorbells, and automated security systems to protect their properties. This project presents a design and implementation of a cost-effective AI-powered intrusion detection system utilizing Raspberry Pi 5 for home surveillance, with adaptability for broader applications. The system integrates a camera module and an LCD screen running on a Linux-based platform, with Python, and OpenCV as key software components. It employs dlib’s deep …

Estimating Per-Infection Cost And Burden For Dengue And Zika As A Function Of Antibody-Dependent Enhancement, Christopher M. Kribs

Mathematics Faculty Publications - Archive

The complex immune interactions produced by the tetravalent dengue vaccine Dengvaxia have foregrounded the important role of antibody-dependent enhancement (ADE) in dengue infection. Some evidence exists that ADE may extend beyond the four dengue serotypes to Zika, a closely related flavivirus transmitted by the same mosquito species as dengue, and may also account for the increased severity of some cases. Estimates of the public health impact of dengue vaccination may then need to include its effects on the transmission of Zika in addition to dengue. This study gathers primary references to build estimates of per-case economic cost and disease burden …

Utilizing Β-Gal To Visualize Selective Transport Of The Ssa4 Gene In S.Cerevisiae, Ian M. Staertow, Rebecca L. Adams Phd

Science University Research Symposium (SURS)

In eukaryotic cells such as Saccharomyces cerevisiae, protein synthesis begins with the transport of mRNA from the nucleus to the cytoplasm. In order for mRNA to leave the nucleus, it must first bind to specific transport proteins which can then facilitate transport via the nuclear pore complex (NPC), a selectively permeable membrane within the cell's nuclear envelope. Under environmental stress, such as heat shock, S. cerevisiae cells modulate transport rates. In this case, in heat stress or “heat shock” most mRNA transcripts will remain in the nucleus. The SSA4 transcript encodes for a chaperone protein which facilitates the subsequent export …

Impact Of Climate Change On North Central Texas, Diana K. T. Hansen

Earth & Environmental Sciences Dissertations - Archive

ABSTRACT

IMPACT OF CLIMATE CHANGE ON

NORTH CENTRAL TEXAS

Diana Kay Thomas Hansen, Ph.D.

The University of Texas at Arlington, 2025

Supervising Professor: Arne M.E. Winguth

The North Central Texas region is a rapidly expanding metropolitan area. One of the largest climate hazards that will affect human health in this region are extended heat waves and heavy precipitation. This study will examine how these hazards will change in response to climate change and the impact to human health due to weather extremes in a changing climate.

Coupled Model Intercomparison Project (Phase 6) simulations were used to evaluate future projected temperature …