Digital Commons Network^™

Fig-Gan: Fundus Image Generation Via Deep Learning Based Generative Adversarial Network For Amd Disease Diagnosis, Kailasa Thrishul, Ahed Abugabah, Amina Salhi, Manel Ayadi, Mohamed M. Sithik, D. Jayaprakash, A. Ahilan

All Works

Globally, age-related macular degeneration (AMD) remains a main cause of irreversible vision loss. Recently, deep learning models have primarily focused on classifying fundus images for early detection of AMD progression. However, existing models rarely address the generation of future progression-aware fundus images, particularly when complete real longitudinal follow-up scans are unavailable. This limitation makes it difficult to track retinal changes over time and highlights the need for generative models capable of producing realistic drusen-level structural variations. To address these issues, a novel deep learning-based FIG-GAN model is to generate synthetic future fundus images from baseline inputs. Multi-Attention U-Net (MAU-Net) is …

Reimagining Sustainable Sulfur Concrete: A Systematic Review Of Sulfur, Waste Integration, And Durability, Vasilia Al Khaldi, Abdel Hamid I. Mourad, Maisa Elgamal

All Works

Sulfur concrete (SC) - a thermoplastic, waterless composite in which molten sulfur-based binder replaces Portland cement - is attracting growing research attention as a sustainable construction alternative capable of superior performance in chemically aggressive environments. This systematic literature review synthesises evidence from 127 sources (2000–2025), examining three interlinked dimensions: (i) the role of waste and industrial by-product materials as aggregate and filler substitutes; (ii) the influence of aggregate type, morphology, and grading on mechanical and microstructural performance; and (iii) durability under acid, saline, and freeze-thaw exposures. A transparent, PRISMA-aligned screening and classification protocol - here used as a structured review …

A Performance-Optimized V2v Task Offloading Framework For Real-Time Vehicular Communication, Tariq Qayyum, Asadullah Tariq, Ikbal Taleb, Mohamed Adel Serhani, Zouheir Trabelsi

All Works

As vehicular applications become increasingly complex, their computational demands often exceed the capabilities of individual vehicles. Vehicular Edge Computing (VEC) alleviates this limitation by enabling task delegation to nearby edge resources; however, high mobility, dynamic topology, and fluctuating vehicle density make real-time offloading decisions challenging. To address these issues, we propose a performance-optimized Vehicle-to-Vehicle (V2V) task offloading framework for dense and dynamic Vehicular Ad-hoc Networks (VANETs). The framework follows a two-stage design: (i) context-aware edge-node selection based on live topology capture via periodic beaconing, and (ii) cumulative score-based dynamic priority queuing at the selected edge node. The priority score jointly …

Smart Medical System Integrating Clinical Workflows For Robust Skin Cancer Detection Across Heterogeneous Pathologies, Ahed Abugabah, Prashant Kumar Shukla, Suchi Mishra, Abhishek Dwivedi

All Works

Skin cancer is among the most prevalent and life-threatening dermatological diseases worldwide, with melanoma responsible for a substantial proportion of skin cancer–related deaths due to delayed and unreliable diagnosis. Conventional clinical screening based on visual inspection and expert interpretation is inherently subjective and often affected by inter-observer variability, lesion heterogeneity, and imaging artifacts, highlighting the need for accurate and generalizable automated diagnostic systems. This study proposes a novel hybrid deep learning architecture for skin cancer classification that integrates an attention-guided autoencoder with a transformer-inspired global context modeling module, forming a unified and robust representation learning framework. The encoder–decoder structure is …

Temporally Rigorous And Traceable Predictive Maintenance Via Joint Labeler-Model Optimization, Maytha Al-Ali, Ahmad Alharbi

All Works

Predictive maintenance (PdM) is a critical enabler of intelligent asset management in Industry 4.0, yet many existing frameworks remain difficult to operationalize due to methodological fragmentation. Common limitations include sacrificing temporal realism and class granularity for computational expediency, decoupling labeling strategy design from model hyperparameter optimization, and insufficient support for reproducibility and deployment traceability; particularly in rare-failure regimes. To address these challenges, we propose a unified, end-to-end, and fully traceable PdM framework that jointly optimizes labeling and model parameters while enforcing strict temporal fidelity. The proposed pipeline co-optimizes the failure lookahead window () and LightGBM hyperparameters within a single Bayesian …

Leveraging Mammal Mycophagy To Determine Environmental Drivers Of Truffle Diversity, Brittany Hartsock

Electronic Theses and Dissertations

Many mycorrhizal fungi are hypogeous (truffle-forming), producing underground fruiting bodies. Studying truffles is inherently challenging due to their hidden nature. However, mycophagous mammals provide a unique opportunity to study hypogeous fungi because they rely on truffles as a food source. Although several truffle species have recently been described in the southern Appalachian region, their fruiting patterns remain poorly understood. To address this, we quantified truffle richness and spore loads from 670 Peromyscus scat samples collected across 42 sites spanning an environmental gradient during 2024 in the Blue Ridge Mountains of East Tennessee. We found that truffle richness and spore abundance …

An Assessment Of Accessibility And Affordability Of Inpatient Psychiatric Care In Tennessee, Kailee Havrda

Electronic Theses and Dissertations

Introduction: Access to mental health has seen changes over the past decade, but little research and attention have been given to access to inpatient psychiatric facilities. Inpatient psychiatric care is crucial for patients experiencing mental health emergencies who need immediate access to care. Gaps in spatial accessibility, affordability, and the access and assessment process were identified due to a lack of available information in the field.

Methods: Secondary data from the Tennessee Department of Health were used to assess financial accessibility through payer source charges and patient encounters, as well as through mapping of inpatient psychiatric facilities and conducting drive …

Kindergarten Teachers’ Perceptions Of Instructional Approaches For Teaching Sequencing Concepts: Worksheet, Hands-On, And Beebot-Integrated Lessons, Savannah P. Partin

Electronic Theses and Dissertations

The purpose of this qualitative multiple-case study was to explore kindergarten teachers’ perceptions of three instructional approaches for teaching sequencing concepts: worksheet-based instruction, hands-on manipulative instruction, and BeeBot-integrated instruction. Sequencing is a foundational early literacy skill that supports reading comprehension, story retelling, and understanding the order of events. Although sequencing is commonly taught through traditional instructional methods, limited research has examined how kindergarten teachers perceive the use of educational robotics as a tool for literacy instruction. The study was guided by constructivist theory, sociocultural theory, and developmental systems theory. Participants included six kindergarten teachers from a public elementary school in …

Understanding The Out-Of-Distribution Generalization Of Chain-Of-Thought Reasoning In Llms, Nuojing Liang, Xiaotong Yuan, Pan Zhou

Research Collection School Of Computing and Information Systems

Chain-of-Thought (CoT) reasoning substantially improves Large Language Models (LLMs), yet its out-of-distribution (OOD) generalization mechanism remains theoretically underexplored. We study CoT as compositional OOD generalization: the target task lacks complete reasoning trajectories or direct input-output pairs, while training provides only in-distribution (ID) atomic step data. We show that CoT generalizes by repeatedly applying a shared single-step predictor to compose reusable ID transitions. Theoretically, the OOD task risk is controlled by the sum of ID subtask risks, scaled by a depth-independent hard-decoding coefficient Bℓ b = O(k) that is independent of the reasoning depth T. A Rademachercomplexity analysis further gives an …

A Deep Learning Ensemble Framework For Multi-Subtype Renal Tumor Classification Using Contrast-Enhanced Ct, Hisham Abdeltawab, Ahmed Alksas, Mohamed Ghazal, Ashraf Khalil, Norah Saleh Alghamdi, Rasha T. Abouelkheir, Ahmed Elmahdy, Mohamed Abou El-Ghar, Sohail Contractor, Ayman El–Baz

All Works

Renal cell carcinoma (RCC) is considered the most aggressive and common form of renal cancer. Therefore, early detection is crucial to ensure appropriate and effective treatment planning. In our study, we propose a novel computer-aided diagnostic (CAD) approach which incorporates a deep learning ensemble to differentiate between five renal tumor subtypes, utilising the modality of contrast-enhanced computed tomography (CE-CT). The addressed renal lesions are malignant tumors (chromophobe RCC (chRCC), papillary RCC (pRCC), and clear cell RCC (ccRCC)) and benign tumors (renal oncocytoma (RO) and angiomyolipoma (AML)). Our study includes 280 patients who underwent renal biopsy, 112 patients were diagnosed with …

Integrating Machine Learning And Explainable Ai For Employee Attrition Prediction In Hr Analytics, Maytha Al-Ali, Majed Alwateer, Shatha Abed Alsaedi, Hossam Magdy Balaha, Mahmoud Badawy, Mostafa A. Elhosseini

All Works

Employee attrition poses significant challenges to organizations, impacting productivity, morale, and financial stability. Predicting attrition and understanding its underlying drivers are critical for implementing effective retention strategies. In this study, we propose a comprehensive framework that utilizes advanced machine learning techniques to predict employee attrition and job change likelihood. The framework integrates robust preprocessing pipelines, state-of-the-art predictive models, and explainability tools such as SHAP (SHapley Additive exPlanations) to ensure transparency and fairness in HR analytics. By addressing key challenges such as class imbalance, feature selection, and model interpretability, our approach provides actionable insights for proactive talent management. We evaluate the …

A Robust Approach For Olive Leaf Disease Detection In Uncontrolled Environments, Rima Grati, Khouloud Boukadi, Emna Ben Abdallah, Ahmed Seffah

All Works

Detecting diseases in olive leaves is crucial for maintaining tree health and ensuring stable olive production. Early signs of infection often appear on the leaves, making them a key indicator for timely disease detection and intervention. Traditionally, farmers rely on visual inspection or laboratory tests to diagnose plant diseases. However, recent advancements in deep learning (DL) have significantly improved the accuracy and efficiency of olive leaf disease diagnosis. Numerous studies in the literature have explored this task using CNN-based architectures and, more recently, Vision Transformers. While these models have shown promising performance on benchmark datasets, they are often trained and …

Ai-Driven Collision Risk Prediction And Debris Optimization In Low Earth Orbit, Emad Alkhazraji, Mohamed E. Yahia, R. E. Tolba, N. S. Alharthi

All Works

Debris congestion and collision in low Earth orbit have become a major point of concern due to the rapid expansion of activities in that region. In this work, an AI-driven framework is developed and deployed to predict, analyze, and optimize collision risk across the altitude inclination space. Local debris object population, mass density distribution, and conjunction derived risk are computed. Then, an AI surrogate model, viz., gradient-boosted decision trees, was trained to predict collision conjunction relative probabilities and risk. Thereafter, data analysis and explain ability techniques are utilized to uncover underlying risk drivers and reveal how altitude, inclination, mass loading, …

Utilizing The Invasive Fruitwood Pyrus Calleryana As Substrate For Mushroom Cultivation, An Experimental Study In Practical Sustainability, Matthew D. Helton

Masters Theses and Doctoral Dissertations

This study evaluated the feasibility of using woodchips from the invasive Pyrus calleryana (Callery pear) as substrate for mushroom cultivation. Pleurotus ostreatus, Hericium erinaceus, and Ganoderma lucidum were grown on a pear wood substrate and on a conventional oak substrate to compare, yield, sensory attributes, and metabolite production. P. ostreatus showed no significant differences in yield or biological efficiency (p > 0.05), only sweetness (p = 0.022) differed significantly. H. erinaceus yield and efficiency were similar (p > 0.05), with greater second-flush yields in oak controls (p = 0.034) but no sensory differences (p > 0.05). G. lucidum performance was comparable across treatments …

Writing Assessment In Tennessee Community Colleges, Joshua Tucker

Masters Theses and Doctoral Dissertations

This mixed-methods study examined how composition faculty at Tennessee community colleges used margin comments to support student writing, whether those comments reflected principled or novice feedback language, and how instructors understood and described their own commenting practices. Marginal feedback remains the most widely used yet least theoretically examined form of response in first-year writing instruction, and the legislative reforms reshaping Tennessee's community college system, including the corequisite model, TNPromise, and TNReconnect have intensified questions about the pedagogical practices used to support an increasingly diverse student population. Eight full-time English instructors at Tennessee community colleges participated in the study, submitting 771 …

A Projector-Rank Partition Theorem For Exact Degrees Of Freedom In Experimental Design, K. G. Nagananda

Mathematics and Statistics Faculty Publications and Presentations

In many experimental designs—split-plots, blocked or nested layouts, fractional factorials, and studies with missing or unequal replication—standard ANOVA procedures no longer tell us exactly how many independent pieces of information each effect truly contributes. We provide a general degrees of freedom (df) partition theorem that resolves this ambiguity. For N observations, we show that the total information in the data (i.e., N −1 df) can be split exactly across experimental effects and randomization strata by projecting the data onto each stratum and counting the df each effect contributes there. This yields integer df—not approximations—for any mix of fixed and random …

Serotonin 1b/1a Receptor Modulation On Probabilistic Reversal Learning In The Btbr Mouse Model Of Autism Spectrum Disorder, Magdalena R. Gonzales

Electronic Theses, Projects, and Dissertations

Autism spectrum disorder (ASD) is known for developmental disability that typically emerges around infancy and early childhood due to a possible combination of genetics, environment or a combination of both. A diagnosis of ASD is determined by behavioral measures due to the lack of reliable biomarkers. Such symptoms include social impairment, and restricted and repetitive behaviors. Restricted and repetitive behaviors often present as rigid behavior or behavioral inflexibility. Behavioral flexibility is often described as the ability to adapt to changing environments. Previous research has shown that serotonin (5-HT) 1B and 1A receptor upregulation may attenuate restricted, repetitive behaviors found in …

Switching Configurations For Reconfigurable Battery Packs: A Review, Kenneth Tetteh Akiti, Quoc Viet Phung, Iftekhar Ahmad, Daryoush Habibi

Research outputs 2022 to 2026

Conventional Battery Energy Storage Systems (BESS) are designed with fixed cell topologies, where the electrical connection between cells remains unchanged throughout their life. Although Battery Management Systems (BMS) and conventional cell-balancing techniques are employed to monitor and maintain performance, they often fail to address key challenges such as uneven cell aging, capacity mismatch, and fault isolation that arise especially during the second life of a battery pack. These limitations can result in reduced efficiency, reduced reliability, and shortened battery life. As large-scale battery packs become increasingly common in Electric Vehicles (EVs), smart grids, robotics, and renewable energy systems, the limitations …

Effect Of Preheating Palm Oil Biodiesel Fuel On The Performance And Emissions Of Diesel Engine Common Rail Direct Injection, Nanang Romandoni, Achmad Aminudin, Hari Setiapraja, Bima Randi Wardiasaputra, Kelvin Dwi Wardana, Ahmad Yusril Aminullah, Deni Nur Fauzi, Kholis Nur Faizin, Nur Ihda Farikhatin Nisa

Journal of Mechanical Engineering Science and Technology (JMEST)

Fossil fuel consumption continues to increase while its reserves continue to decrease and produce high emissions that trigger global warming. Therefore, more environmentally friendly alternative energy is needed. Biodiesel is a sustainable choice because it is biodegradable, low in sulphur, and can replace fossil fuels. This study investigates the influence of biodiesel fuel preheating temperature on engine performance, fuel consumption, and emissions in a Common Rail Direct Injection (CRDI) diesel engine. The experimental method was carried out by heating B40 and B50 fuels at temperatures of 40°C to 60°C at intervals of 10 °C. Engine performance was evaluated using a …

Structural And Electrochemical Characterization Of Na2co3/ Γ- Al2o3 Electrodes For Supercapacitor, Wiwin Dwiana, Jeniva Dinta Nanda Fahreza, Anissa Chairani Alfin Nadhira, Fatimatuz Zahra, Erma Surya Yuliana, Muhammad Safwan Abd Aziz, Nandang Mufti

Journal of Mechanical Engineering Science and Technology (JMEST)

The development of electrode materials with suitable structural and surface properties is crucial for improving electrochemical energy storage systems. Gamma alumina (𝛾-Al₂O₃) has attracted considerable interest in electrochemical research due to its unique structural and surface properties. However, its charge-storage capacity is still limited, highlighting the need for structural and compositional modifications to improve its electrochemical performance. In this study, Na₂CO₃ was introduced into 𝛾-Al₂O₃ as a sodium precursor to induce phase modification and enhance the electrochemical activity. The systematic incorporation of Na₂CO₃ also provides an opportunity …

A Systematic Review Of Alkali-Treated Polylactic Acid Biocomposites Relevant To Pineapple Leaf And Water Hyacinth Hybrid Design, Muhammad Rizky Adrianto Subandi, Tri Hartutuk Ningsih, Hanna Zakiyya

Journal of Mechanical Engineering Science and Technology (JMEST)

The increasing demand for sustainable materials has accelerated the development of biodegradable polymer composites. Polylactic acid (PLA)-based natural fiber composites have attracted significant attention due to their renewable characteristics; however, their performance remains limited by weak fiber–matrix compatibility, moisture sensitivity, and inconsistent interfacial behavior. Alkali treatment has been widely applied to modify lignocellulosic fibers by removing non-cellulosic components and improving surface characteristics, although its effectiveness remains dependent on treatment conditions and fiber properties. This systematic review evaluates the influence of alkali treatment on PLA-based natural fiber composites and assesses the available evidence supporting future pineapple leaf fiber (PALF) and water …

The Benefits And Barriers To Expanding Crna Programs In Michigan, Grace Van Zweden

Honors Theses

The demand for Certified Registered Nurse Anesthetists (CRNAs) and their delivery of safe, high-quality anesthesia care has increased significantly due to nationwide anesthesia provider shortages and the growing reliance on CRNAs to meet healthcare system needs. This demand underscores the importance of expanding nurse anesthesia programs in Michigan and across the United States to support nurses pursuing advanced education and to improve patient access to essential care within their communities. The CRNA profession has evolved over time to meet the changing needs of the healthcare system, and current CRNA programs require applicants to satisfy rigorous and highly specific admission criteria. …

Design Of Automatic Security System Based Internet Of Things At The Museum, Rahmat Ageng Yuwana, Nuryake Fajaryati, Ferry Jie

Elinvo (Electronics, Informatics, and Vocational Education)

This research aims to determine the procedures for developing an Internet of Things (IoT)-based Automatic Security System as a security device for museum objects and to test its feasibility based on user feedback in museums. The Design Thinking model used consists of five stages: Empathize (understanding the user’s perspective), Define (gathering information on the encountered problems), Ideate (generating innovative ideas), Prototype (creating a prototype of the obtained ideas, ensuring the functionality of each device feature, and validating the product through expert judgment for feedback and product revision), and Testing (evaluating the system’s feasibility using Usability standards based on ISO/IEC 9241-11, …

Caribou Migration And Non-Local Hunting In Northwest Alaska: A Gis Analysis Of Hunting Activity And Its Relationship With Caribou Migration Corridors, Brittney L. Jiménezszabo

Geography and the Environment: Graduate Student Capstones

Indigenous Alaskans rely on subsistence hunting for food, with Barren-ground caribou making up approximately 27% of their diet. It is believed by subsistence hunters that non-local hunting is forcing a change in caribou migration behavior. This study examined non-local harvesting records from 2013 – 2025 in the northwest and interior Game Management Units (GMU) and Alaksa’s Western Arctic Caribou Herd (WACH) migration range data to answer the question, is there a spatial relationship between non-local harvests and WACH migration behavior. Mixed methods included spatial autocorrelation and local statistics. Findings led to the rejection of the null hypothesis which will help …

The Two Fridas: How The Use Of Semiotics Reflects The Social History Of Mexico In Frida Kahlo’S Work, Raquel Maria Botteon Martins

SPARK Symposium Presentations

Frida Kahlo and Diego Rivera are often credited as having played a crucial role in establishing a Mexican avant-garde. According to the Denver Art Museum’s statement for the exhibition Frida Kahlo, Diego Rivera, and Mexican Modernism, their body of work often incorporated portrayals of mexicanidad, an identity born of Mexico’s ancient cultures and its colonial past that projected a visionary future. The use of mexicanidad imagery started with the efforts to create a new national art, following the Mexican revolution, when the country used public and socially effective art to communicate new ideals of identity.  Through the analysis of …

Lithium Titanate-Functionalized Mixed Matrix Polymer Membrane For High-Performance Osmotic Energy Conversion, Rockson Kwesi Tonnah, Yasaman Boroumand, Milad Razbin, Mostafa Vahdani, Amir Razmjou, Mohsen Asadnia

Research outputs 2022 to 2026

Reverse electrodialysis (RED) offers a promising route to harvest osmotic energy from salinity gradients, yet practical implementation is hindered by the lack of scalable, high-performance ion-selective membranes that combine efficient ion transport with mechanical robustness and environmental sustainability. Here, we report a mixed matrix membrane composed of polyethersulfone (PES), polyvinylpyrrolidone (PVP), and lithium titanium oxide (Li₂TiO₃, LTO) that addresses these challenges through biomimetic ion transport channels. The strategic integration of LTO nanoparticles introduces ion-exchange sites and oxygen-rich PES ether linkages to create preferential cation transport pathways that mimic biological ion channels. This mixed matrix design delivers over three-fold cation conduction, …

Peakon Solutions And Analytical Properties For The Camassa–Holm-Type Equations With Quadratic Nonlinearities, Yonghong Chen, Zhijun Qiao, Mingxuan Zhu

School of Mathematical & Statistical Sciences Faculty Publications

In this paper, we derive the multi-peakon dynamical system of a class of Camassa-Holm-type equations with quadratic nonlinearities. We also consider the analytical properties for the Cauchy problem. Firstly, we establish local well-posedness of solutions in Besov spaces and then provide the blow-up criteria. Subsequently, we impose appropriate sufficient conditions on the initial data to guarantee that the corresponding solution either exists globally or blows up in a finite time. Finally, we prove the ill-posedness in the Besov space B2,∞^3/2 by utilizing the non-traveling wave solutions.

Application Of Artificial Intelligence (Ai) In Cancer Symptom Management For Adult Cancer Survivors: A Scoping Review, Tao Wang, Haiying Wang, Mengyuan Li, Daniel Bressington, Daniel Terry, Guanjin Wang, Wai Hang Kwok, Jing Yu (Benjamin) Tan

Research outputs 2022 to 2026

Background and aim: Artificial Intelligence (AI) has been increasingly used in cancer survivorship to support symptom management. This scoping review aimed to map existing evidence on AI applications in cancer symptom management for adult cancer survivors, including AI model development, AI-enabled intervention delivery and adoption, symptom targets, key features of the AI approaches used, reported outcomes, influencing factors, and research gaps to inform future priorities.

Method: This scoping review was conducted in accordance with the Joanna Briggs Institute methodology for scoping reviews. Eight electronic databases were comprehensively searched in November 2025 and updated in March 2026. Empirical studies published in …

Mechanically Stabilized Porous Aerophilicity Unlocks Ampere-Rate Transport-Limited Co2 Electroreduction To Ethylene, Ahmed Badreldin, Lanxin Guo, Carter Racine, Gabriella Smith, Shaoqin Chen, Shengyao Wang, Baiyu Zhang, Mohammed Majdoub, Ahmed Al-Ostaz, Yun Hang Hu, Qingsheng Wang, Ying Li

Michigan Tech Publications

Gas-fed electrochemical CO2 reduction (CO2R) to multicarbon products is fundamentally constrained by mass-transport limitations that suppress selectivity and stability at industrially relevant current densities. Here, we demonstrate that these bottlenecks can be overcome by engineering a porous aerophilic polymer microenvironment around a simple CuxO electrocatalyst without altering the intrinsic catalyst. By systematically replacing conventional PFSA ionomers with mixed aerophilic binders and applying a mild thermal treatment, we construct mechanically stabilized, gas-accessible overlayers that regulate the local gas-liquid microenvironment balance at the three-phase boundary (TPB). This approach drives a dramatic enhancement in ethylene production, increasing the partial current density from 135 …

Ncf Sensor Coated With Cofe1.96la0.04o4/Lafeo3 Heterostructures For Room-Temperature Detection Of Liquefied Petroleum Gas Concentration, Ziqiang Liu, Fujian Tang, Yufang He, Jie Huang

Electrical and Computer Engineering Faculty Research & Creative Works

Liquefied petroleum gas (LPG) is a highly flammable fuel widely used for cooking, heating and transportation, making real-time leak detection essential for preventing fire, explosion, and suffocation hazards. In this study, a room-temperature no-core fiber (NCF) sensor coated with CoFe_1.96La_0.04O₄/LaFeO₃ heterostructures was developed for LPG detection. The heterostructures were characterized using XRD, Raman spectroscopy, SEM, TEM, XPS, PL spectroscopy, and UV–vis spectroscopy. Experimental results showed that La incorporation and heterostructure formation refined the particles size, improved surface accessibility, and modulated the electronic structure and band gap, thereby enhancing LPG adsorption, carrier redistribution, and …