Digital Commons Network^™

Improving Cancer Diagnosis And Patient Outcomes With Deep Learning Models, Mariana Arriz-Jorquiera

USF Tampa Graduate Theses and Dissertations

Cancer care depends on timely and reliable decisions, from detection and diagnosis to treatment planning and patient monitoring. These decisions are often made under uncertainty because medical images and healthcare data may be noisy, incomplete, or difficult to interpret. In breast cancer imaging, ultrasound is widely used because it is safe, accessible, and complementary to other imaging modalities. However, variations in image quality, acquisition conditions, and noise can obscure lesion boundaries and texture, affecting human interpretation and artificial intelligence reliability. This dissertation develops deep learning, image-analysis, and optimization methods to improve healthcare decisions under imperfect information. Its primary focus is …

Volatility Spillovers Between Stock Prices And Exchange Rates: Insights For Risk Management And Investment Strategies: Evidence From China, India, And Pakistan Using Bekk-Garch Models, Samreen Fatima, Humera Sultana, Muhammad Najamuddin Dr., Saba Naz

The Indonesian Capital Market Review

This study investigates the dynamics of volatility and its spillover effects between the stock markets of China, India, and Pakistan, and their respective exchange rates (USD/CNY, USD/INR, and USD/ PKR). Volatility is modeled using the Symmetric and Asymmetric BEKK-GARCH (1,1) and DCCGARCH (1,1) models, based on daily return series covering the period from January 1, 2019, to January 31, 2025. The empirical results indicate that both the employed models are adequate for capturing the volatility dynamics. The findings reveal that the highest value of portfolio weights and hedging efficiency of KSE-100 Index–USD/PKR provide optimal portfolio allocation and highest hedging performance …

Deciphering The Potential Of Monopterus Albus Protein Hydrolysate As A Therapeutic Candidate Against Cervical Cancer By Integrating Content Analysis, Network Pharmacology, And Molecular Docking, Okid Parama Astirin, Widya Mega Rahmawati, Elisa Herawati, Tetri Widiyani, Lili Pandan Sari, Sherly Octaviana

Karbala International Journal of Modern Science

Cervical cancer has a high incidence rate in women, making the development of cancer drugs increasingly urgent. Asian swamp eel protein hydrolysate shows great promise as an anticancer candidate. This study aimed to reveal the potential of Asian swamp eel protein hydrolysate as an anticancer candidate in the cervix. Asian swamp eel protein hydrolysate was produced by hydrolyzing flesh with the enzyme alcalase. Compounds and peptides were identified using LC-HRMS. These compounds and peptides were analyzed using network pharmacology, gene ontology, and molecular docking. The results identified 153 endogenous compounds, including fatty acids and peptides. The key proteins targeted by …

Compressed Cinema As A Study In Llm Latent Spaces, Mallen Clifton

ELO (un)supervised 2026

In his article “Spec Acts” (2021), Matthew Kirschenbaum analyzes the AI-generated novel 1 the Road to develop his titular concept of the spec act, “the future in its multitudes collapsing into an actionable present.” With the proliferation of texts produced by generative AI and subsequent critical analyses of them, one element in particular calls for further theorization: “the future in its multitudes,” or more directly, the latent space. This echoes arguments by critics such as Antonio Somaini, who offered his own “Theory of Latent Spaces” last year. However, where Somaini’s attention is towards visual culture, I turn mine to the …

A Late Holocene (Late Bronze Age) Record Of The Syrian Elephant (Elephas Maximus Asurus) From Gavur Lake Swamp (Kahramanmaraş, Türkiye), Serdar Mayda, Yarenkür Alkan

Turkish Journal of Earth Sciences

The Syrian elephant (Elephas maximus asurus Deraniyagala, 1951) constitutes the extinct westernmost population of the Asian elephant and occupied parts of the Near East until the early first millennium BCE. Although historical, iconographic, and dental evidence for this population has been discussed extensively, its postcranial anatomy remains poorly documented. We present a revised osteological and morphometric study of cranial and postcranial remains recovered from the Late Bronze Age Gavur Lake Swamp assemblage (ca. 1650–1400 cal BCE) in Kahramanmaraş, southeastern Türkiye, during rescue excavations conducted in 2021 and 2022. The material derives from a natural swamp deposit rather than from an …

Paleoseismological Study Of The Active Faults Of Northern Cyprus​​, Hasan Elmaci, Şule Gürboğa, Seli̇m Özalp, Hasret Ozan Avci, Hakan Aydoğan, Ayhan Yavuzoğlu, Ali̇ Atalay Yüce, Meryem Kara, Ahmet Rasi̇mcan Öztürker

Turkish Journal of Earth Sciences

The tectonic framework of Northern Cyprus is presented in this study based on integrated fieldwork and paleoseismology. We identified multiple fault systems including the 214-km Dardere (Ovgos) Fault Zone (with seven segments), the Haspolat Transfer Fault, Mersinlik Fault, Yamaçköy Fault Zone, Boğazköy Fault, Alsancak Fault, and Geçitköy-Koruçam Fault Zone. Eleven paleoseismological trenches were excavated, with six yielding reliable results in terms of dating and stratigraphy. The results indicate recurrence intervals exceeding ~2500 years across different fault segments. The Dardere (Ovgos) Fault Zone shows the potential to generate earthquakes of up to Mw 7.80 with evidence of Holocene activity. The Haspolat …

Harmful Algal Blooms: Risks For Food In Utah, Jose Brandao, Sarah Erwin, Stephanie Vaughn, Clare Entwistle

All Current Publications

Harmful algal blooms (HABs) are a problem because they can produce toxins that make water unsafe for people, animals, and the environment. In recent years, HABs have emerged as a growing concern in freshwater systems throughout Utah, including irrigation canals, reservoirs, and livestock ponds. HABs in freshwater are caused by cyanobacteria, also called blue-green algae. These microorganisms can release dangerous toxins that can harm swimmers, pets, and the food supply. Unlike foodborne pathogens, these toxins cannot be removed by boiling, cooking, or washing the food. Therefore, regular monitoring is essential to detect HABs early and reduce exposure risks. This fact …

Integrated Edge Detection Of Gravity Data And Seismicity Approach For Mapping Potential Faults In The Bolu Region, Hazel Deni̇z Toktay, Burçi̇n Di̇dem Tamtaş

Turkish Journal of Earth Sciences

The Bolu region, situated along the western–central segment of the North Anatolian Fault Zone (NAFZ), is characterized by a complex fault architecture in which multiple overlapping strike-slip segments and associated subsurface structures accommodate active crustal deformation. Although the principal fault strands of the NAFZ have been well mapped, several clusters of seismicity are observed in areas without clear surface fault expression, indicating the presence of subsurface or poorly expressed fault zones. In this study, we integrated edge detection methods with a seismicity approach to delineate active and buried structural features across the Bolu region. Bouguer gravity anomalies derived from the …

The Harmancık “Purple Jade”: A Unique Blueschist-Facies Metatrachyte With Significant Geoarchaeological Value, Gülteki̇n Topuz, Aral I. Okay, Constantinos Mavrogonatos, Osman Candan, Michael Brandl, Onur Bamyaci, Serap Ala Çeli̇k, Frederik Vingaard, Warren Thompson, Peter Christian Toft, Benjamin Dominguez Heredia, Tonny Bernt Thomsen, Lasse Vilien Sørensen

Turkish Journal of Earth Sciences

The so-called Harmancık “purple jade” from the Bursa region of northwestern Türkiye has attracted attention as a gemstone; however, its geological characteristics and provenance have long remained uncertain. This short communication presents new field observations along with mineralogical and petrological data concerning the provenance, metamorphic evolution, and geoarchaeological relevance of this unique rock type. The rock occurs as loose boulders scattered across cultivated fields in the villages of Akpınar, Kocapınar, and Gedikören, where it was previously interpreted either as part of Neogene sedimentary successions or as a high-pressure metamorphic rock affected by contact metamorphism. Our detailed mapping and field observations …

"Todo: Fix The Mess Gemini Created": Towards Understanding Genai-Induced Self-Admitted Technical Debt, Abdullah Al Mujahid, Mia Mohammad Imran

Computer Science Faculty Research & Creative Works

As large language models (LLMs) such as ChatGPT, Copilot, Claude, and Gemini become integrated into software development workflows, developers increasingly leave traces of AI involvement in their code comments. Among these, some comments explicitly acknowledge both the use of generative AI and the presence of technical shortcomings. Analyzing 6,540 LLM-referencing code comments from public Python and JavaScript-based GitHub repositories (November 2022-July 2025), we identified 81 that also self-admit technical debt (SATD). Developers most often describe postponed testing, incomplete adaptation, and limited understanding of AI-generated code, suggesting that AI assistance affects both when and why technical debt emerges. We term GenAI-Induced …

From Automation To Adjudication: Evaluating The Role Of Artificial Intelligence In Dispute Settlement, Karem Sayed Aboelazm, Muayad Ahmad Obeidat, Raghda Raafat, Nada Zuhair Alfil, Fady Tawakol

All Works

This paper explores the evolving transition from automation to adjudication by examining the role of artificial intelligence (AI) in dispute settlement processes. It assesses how AI can enhance procedural efficiency, support judicial reasoning, and improve access to justice. Adopting a qualitative and interpretive approach, the study analyzes academic scholarship, policy frameworks, and comparative international practices to understand the integration of AI within judicial and quasi-judicial settings (Abedi et al., 2025). The findings suggest that while AI significantly improves administrative processes and provides valuable decision-support tools, it also raises critical concerns regarding algorithmic bias, lack of transparency, and the risk of …

Determinants Of Home Composting Behavior In Supporting Sustainable Agriculture Among Smallholder Farmers: A Case Study In The Thai Nguyen Province Of Vietnam, Bac Ho Van, Hien Vu Thi, Xinh Ho Luong

Journal of Environmental Science and Sustainable Development

Home composting is a practical and sustainable approach for the management of organic waste generated in the home and agricultural production that contributes to both organic waste management and soil fertility enhancement. In the northern mountainous regions of Vietnam, smallholder farmers face limited adoption of sustainable waste management practices due to behavioral constraints, limited technical knowledge, and resource constraints affecting agricultural productivity.  This study applies and extends the Theory of Planned Behavior (TPB) by integrating behavioral and contextual determinants to examine home composting adoption among smallholder farmers in rural Vietnam. Principal Component Analysis (PCA) was used to reduce and structure …

Terrestrial Gamma‐Ray Flash Following Intense Negative Return Stroke Observed With Bimap‐3d, Daniel P. Jensen, David M. Smith, Xuan-Min Shao, Jeff L. Lapierre, Jeffrey M. Chaffin

Faculty Publications

We report ground‐based observations of a terrestrial gamma‐ray flash (TGF) associated with a strong negative cloud‐to‐ground lightning strike (‐CG) which occurred near Los Alamos National Laboratory (LANL) in New Mexico, USA. Gamma photons were detected by the Terrestrial High‐energy Observations of Radiation (THOR) instrument, developed at the University of California, Santa Cruz, which has been hosted at LANL since 2022. Simultaneous measurements were also made with the 3‐Dimensional Broadband Interferometric Mapping and Polarization (BIMAP‐3D) system, which includes 3D lightning mapping, two fast antennas, and an additional plastic scintillator. Additional field change waveforms were obtained from the Earth Networks Total Lightning …

Assessing Flaws In Captcha Security Through Progress In Ai, Jaydon Stanislowski

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Protecting the internet from the threat of malicious bot activity is an important problem as AI tools become more powerful and commonplace over time. To that end, security measures are employed across websites in the form of CAPTCHAs, short challenges designed to identify and block fake web traffic. Yet, they become less effective over time as AI becomes more powerful, and thus more capable of solving them. This paper examines recent research on the threat to CAPTCHA security posed by current AI models and how this security can be reinforced over time, focusing primarily on Google’s reCAPTCHA v3.

Water Scarcity On Arizona’S Navajo Nation, As An Environmental Justice Issue, Chenoa Marks

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

For the Navajo–or Diné, meaning ‘the people’ in Diné Bizaad (Navajo language)–water is not only a resource. It is life, story, and relationship. It is tied to origin, movement, and balance within the natural and spiritual world. Water exists not only in rivers and rainfall, but in teachings, ceremonies, and the way knowledge is passed down from one generation to the next. In this sense, water is both physical and cultural, shaping how people live, understand the land, and connect to one another.

At the same time, water on the Navajo Nation–known by the Diné as Diné Bikéyah, also translated …

Improving Urban Planning Through Agent Based Modeling And Q-Learning, Tristan Kalvoda

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

This paper explores the use of agent-based modeling (ABM), enhanced by reinforcement learning techniques such as Q- learning, to optimize urban transportation systems. The focus is on modeling and improving aspects such as traffic design, vehicular flow, and pedestrian mobility. The central research question is how to effectively simulate realistic agent behavior in order to develop models that can inform and support policy-making for more efficient and adaptive urban planning. The paper presents and analyzes simulation-based case studies that demonstrate how learning agents can repro- duce realistic movement patterns and provide insights for larger-scale urban systems.

Zero Trust Architecture And Ransomware Mitigation, Ely Johnson

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Ransomware has become a critical threat to modern enterprises, exploiting excessive privileges and flat network architectures to spread rapidly. Traditional perimeter-based security models are insufficient, as they rely on implicit trust within internal networks. This paper examines how Zero Trust Architecture (ZTA) mitigates ransomware through least privilege access, continuous monitoring, and micro- segmentation. Experimental results show that ZTA can significantly reduce impact, limiting encryption to about 20% of targeted files while preserving most data. Continuous monitoring enables rapid detection (5.3 seconds) with high accuracy (up to 97.2%) and a 78% reduction in false positives. Micro-segmentation further restricts lateral movement, reducing …

Security Limitations Of The Can Bus And Detection Through Power Fingerprinting, Ken Broden

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

This paper examines the vulnerabilities of the Controller Area Network (CAN), the standard communication protocol used in most modern vehicles. It explains why CAN is widely adopted and outlines key security weaknesses in its design. The paper then reviews recent research efforts to detect and mitigate these vulnerabilities, with particular focus on an approach to origin authentication that relies on the unique power consumption patterns of each individual electronic control unit on a CAN bus.

Critical Assessment On Challenges And Advances In Coal Pillar Strength Estimation Techniques: A Focus On Geological Discontinuities, Abhishek Kumar Singh, Sahendra Ram

Journal of Sustainable Mining

Accurate estimation of coal pillar strength is essential for ensuring safety and operational efficiency in underground mining. Current assessment methods often face limitations in addressing time-dependent failure mechanisms, geological discontinuities, and dynamic loading conditions. This paper identifies future research directions aimed at enhancing the reliability of pillar strength evaluations. One important focus is the development of advanced numerical models that account for time-dependent behaviours such as creep and fatigue. Incorporating multi-scale modelling techniques, which connect micro-scale material responses to macro-scale structural performance, may lead to more precise predictions. The integration of real-time monitoring systems measuring stress, deformation, and environmental factors …

Toward The Significance Of Crevasse Orientation In Low And High Crevassed Regions On The Kennicott Glacier, Alaska, Usa, Claire A. Sturm

DePaul Discoveries

Supraglacial landforms serve as potential indicators of underlying bedrock morphology and glacier dynamics. The distribution and morphology of crevasses are closely associated with stress fields and ice-flow regimes, representing processes of stable glaciers, in contrast to their reduced occurrence in stagnant or receding ice masses. The orientation and density of crevasses influence a glacier’s ability to absorb solar energy, as they facilitate movement of meltwater down to subglacial rivers. Beyond the meltwater acting as a lubricant for basal sliding, the slope of the bedrock further impacts the local velocity and ice deformation of a glacier. The study of ice-fracturing mechanics …

Healthcare Access And The Persistent Racial Disparities In Low Birth Weight, Zaheda A. Hussain, Yadanar Moe

DePaul Discoveries

Low birth weight (LBW), defined as less than 2,500 grams, is an influential factor contributing to infant mortality in the United States, with significant racial disparities between Black and White mothers. This study analyzed data from 3,054 Black and White mothers collected from the 2018 National Health Interview Survey to explore the association between access to medical care and LBW within different racial groups. The prevalence of LBW was 8.0%. Overall, mothers without a usual place of medical care had, on average, an 18% higher risk of LBW than those with a usual place (OR = 1.18, 95% CI: 0.80–1.74). …

From Landfill To Ladle: Using Open Lca To Calculate Food Diversion Impacts, Samantha Rodriguez

DePaul Discoveries

Food waste contributes to climate change because discarded food results in wasting embodied carbon from producing food. In addition to wasting embodied carbon, food that ends up in landfills emits methane, a powerful greenhouse gas that contributes to climate change. This life cycle assessment quantifies the carbon equivalent footprint of food donations from Costco to the Seton Soup Kitchen using OpenLCA. Two functional units were analyzed in this study. The first functional unit is one meal consisting of 500 grams of donated food that would otherwise be landfilled served to a Seton Soup Kitchen patron during one meal service. The …

Fish Tissue Digestion And Microplastic Polymer Identification Protocol Using Open-Source Ftir Database, Shawn L. Kissinger, Vick-Ariel Privert, Jason Bystriansky, Kyle A. Grice

DePaul Discoveries

Microplastic (MP) contamination in aquatic ecosystems poses significant concerns for environmental and public health, as seafood represents a critical food source worldwide. Despite increasing evidence of MP presence in marine organisms, efficient and accessible detection methods remain essential for characterizing contamination patterns and informing regulatory frameworks. This study extracted MPs from brain, gill, intestine, liver, and muscle tissues of gilt-head bream (Sparus aurata) and European sea bass (Dicentrarchus labrax), two commercially important species from the Gulf of Cádiz, Spain, using a NaOH–HNO₃ chemical digestion protocol. Isolated particles were characterized by Fourier Transform Infrared (FTIR) spectroscopy, with …

Crystal Structural Analysis Of Medieval Human Bones Using Wide-Angle X-Ray Scattering, Selly Altangerel, Leslie Gracia

DePaul Discoveries

Female human second metacarpal (mc2) bones from a medieval cemetery at Wharram Percy, England, were studied using high-energy Wide-Angle X-ray Scattering (WAXS) at beamline 1-ID of the Advanced Photon Source at Argonne National Laboratory. The age-at-death of 33 samples was determined from molar wear and classified into 3 groups:  18-30, 30-50, and 50+ years old.  Rietveld refinements of the WAXS data were performed to obtain lattice parameters of the hexagonal carbonated apatite phase (cAp). Individual fittings for cAp peaks 00.2, 00.4, and 31.0 were performed to obtain their widths and correlate them to collagen retention. For the three samples described …

Clearing The Air: Tracking Spatial And Temporal Pm2.5 Variability Along A Biking Transect In Chicago, Beau R. Rass

DePaul Discoveries

Fine particulate matter (PM₂.₅) poses significant risks to human health and disproportionately affects marginalized communities in urban environments (World Health Organization [WHO], 2021; Tessum et al., 2021). Using low-cost mobile sensors, this study explored spatiotemporal PM₂.₅ concentration patterns along a north–south transect of Halsted Street in Chicago. A 2B Technologies Portable Aerosol Monitor (PAM) mounted on a bicycle was used to continuously record PM₂.₅ concentrations with associated GPS coordinates at approximately two-second intervals during 16 sampling events between 08-12-2025 and 10-05-2025. PM₂.₅ concentrations did not differ significantly among the South Side, West Loop, and North Side regions, contrary to the …

Depaul Discoveries Volume 15 Cover Art, Dina Khdair

DePaul Discoveries

No abstract provided.

Efficient Edge Implementation Of Midasnet For Real-Time Depth Estimation In Indoor Robotics, Muhammed Yasi̇n Adiyaman, İsmai̇l Fai̇k Başkaya

Turkish Journal of Electrical Engineering and Computer Sciences

Real-time depth estimation is crucial in many vision-related tasks, including autonomous driving, 3D reconstruction, robotics, and simultaneous localization and mapping. In recent years, many methods have been proposed to solve depth maps from images by utilizing different modality setups like monocular vision, binocular vision, or sensor fusion. However, for real-time deployment on edge devices, complex methods are not suitable due to latency constraints and limited computation capacity. For edge implementation, models should be simple, minimal in size, and hardware-friendly. Considering these factors, we implemented MiDaSNet, which works on the simplest setup of monocular vision and utilizes hardware-friendly convolutional neural network-based …

Evolutionary Neural Architecture Search: A Survey, Ferda Nur Özçeli̇k, Mehmet Önder Efe

Turkish Journal of Electrical Engineering and Computer Sciences

Deep Neural Networks (DNNs) have achieved remarkable success across diverse machine learning applications, yet designing effective architectures remains a laborious, expert-driven process. Neural Architecture Search (NAS) was introduced to automate this process, with Evolutionary NAS (ENAS) emerging as one of the most effective and widely adopted NAS paradigms. This survey provides a comprehensive and systematic review of 164 ENAS studies published between 2020 and 2024, categorized according to the specific evolutionary algorithm employed as the search strategy. Unlike prior surveys—which either treat evolutionary methods at a high level or focus on general NAS pipelines—this study is, to the best of …

A Holistic Approach For Workforce Scheduling And Routing, Kerem Can Manalp, Ansel Kaplan Erol, Kutluhan Erol, Cem Evrendi̇lek

Turkish Journal of Electrical Engineering and Computer Sciences

The workforce scheduling and routing problem (WSRP) involves assigning tasks across multiple locations while accounting for varying travel times, service durations, time windows, and skill requirements in a wide range of industries, from healthcare to telecommunications. This paper presents a mixed-integer programming model for the WSRP that balances the trade-off between cost and customer satisfaction using a score-generation function and subsequently evaluates the trade-off between solution quality and computation time for several algorithms on well-known datasets. We demonstrate that our model effectively balances cost, service-level agreement satisfaction, and task priorities while providing high-quality solutions in a timely manner. Observing that …

Cnkg: Harnessing Large Language Models For Cognitive Neuroscience Knowledge Graph Construction, Ali Sarabadani, Kheirollah Rahsepar Fard, Hamid Dalvand

Turkish Journal of Electrical Engineering and Computer Sciences

Textual resources are among the most valuable sources of information in cognitive neuroscience (CN) for understanding and investigating brain activity and cognitive processes. Extracting and constructing knowledge graphs (KGs) from these texts can facilitate medical research by providing deeper insights into neurological diseases and brain function. In recent years, the use of large language models (LLMs) in natural language processing (NLP) has become increasingly widespread, significantly enhancing the extraction of meaningful information from large volumes of text. This study proposes a novel approach for constructing and evaluating a specialized knowledge graph, termed the cognitive neuroscience knowledge graph (CNKG), from scientific …