Digital Commons Network^™

An Extensive Analysis Of Match-Tracking Methods For Artmap, Niklas M. Melton, Leonardo Enzo Brito Da Silva, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

This paper identifies and studies five match-tracking (MT) methods in the adaptive resonance theory (ART) literature and conducts a detailed comparative analysis of these in ARTMAP applications. We focus on model performance for each MT method with respect to time and space efficiency as well as classification accuracy. Experimental results indicate that one MT variant, used in ARTMAP applications for the first time in this work, provides significant improvements in computational efficiency: depending on the ARTMAP variant, it was able to achieve up to one order of magnitude reduction in both time and space requirements, albeit with a compromise in …

Prediction Of Glass Transition Temperature Of Polymers Using Structure-Based Models, Nicholas Wolfe

Williams Honors College, Honors Research Projects

The focus for this study is prediction of glass transition temperatures of polymers using machine learning models. The preprocessing of the data included the generation of descriptors, the scaling of the data, the principal component analysis for dimensionality reduction, and the clustering of the data. Three methods of property predictions were utilized including Linear Regression, Random Forest, and a Feedforward Neural Network. The dataset consisted of over 7000 polymers each with their respective glass transition temperatures. This study found that the Random Forest model returned the best results followed by the Feedforward Neural Network then the Linear Regression model. Each …

Shaping Engineering Technology Students’ Perceptions Of Manufacturing Through Experiential Learning In A Flipped Classroom – A Case Study, Rustin Webster

School of Engineering Technology Faculty Publications

This study examined how an introductory, survey-based manufacturing systems and processes course – which uniquely integrated a flipped classroom structure and multiple experiential learning elements – influenced engineering technology (ET) students’ perceptions of careers, workforce expectations, workplace dynamics, and essential industry skills within manufacturing. Pooled qualitative data from 52 ET student’s pre- and post-course reflection surveys, administered across four cohorts, were analyzed using topic modeling, sentiment analysis, comparative assessments, keyword frequency analysis, and/or impact assessment. The data offered valuable insights into students understanding of essential job skills, definitions of a good job, and perceptions of factory work. Before the course, …

Quantifying The Effectiveness Of Rhamnolipid As A Biocide: Assessing Comparability Of A Modified Solution, Rosemary Sterling

Williams Honors College, Honors Research Projects

The CO2 induced corrosion of carbon steel in oil and gas pipelines, exacerbated by sulfate-reducing bacteria (SRB), poses a serious threat to infrastructure. This study evaluates the effectiveness of rhamnolipid (RhL), a biosurfactant, as a corrosion inhibitor and potential SRB biocide in simulated pipeline environments. Using a Postgate-C Modified Produced Water Simulant, which demonstrated electrochemical behavior comparable to industry-standard solutions while sustaining SRB, corrosion trials were conducted with and without RhL. Mass loss and electrochemical data revealed that RhL significantly reduced corrosion rates—by 85% on average and up to 99% instantaneously in a 4-day trial. Visual and analytical results from …

Delivery Method For Dissolvable Staples, Brian Nguyen, Colleen Kroah, Bethany Fogle, Sean Brown

Williams Honors College, Honors Research Projects

Surgical staples play a vital role in modern medicine by enabling efficient wound closure and tissue repair. However, traditional metal staples often require removal, increasing patient discomfort and the risk of infection. Dissolvable staples offer a promising alternative, eliminating the need for removal while maintaining secure wound closure. Despite their potential, current delivery systems for dissolvable staples face significant challenges, including inconsistent deployment, lack of precision, and inadequate integration with surgical workflows.

Developing an optimized delivery system is critical to maximizing the benefits of dissolvable staples. Such a system must ensure reliable performance, precision, and ease of use while maintaining …

Proceedings Of The Tenth Annual Indiana Stem Education Conference: Generational Advances Through Stem Education, William S. Walker Iii, Lynn A. Bryan, S Selcen Guzey

Indiana STEM Education Conference

The Proceedings of the Tenth Annual Indiana STEM Education Conference are edited by the Center for Advancing the Teaching and Learning of STEM (CATALYST, https://www.education.purdue.edu/catalyst/) at Purdue University. The theme for the 2025 conference is Generational Advances through STEM Education. This year’s conference provides opportunities to learn about effective STEM education strategies, curriculum, and resources to engage students by considering the advances and impact of STEM.

Development And Evaluation Of Machine Learning Models For Early Pediatric Sepsis Prediction, Ancita M. Andrade

Browse all Theses and Dissertations

Sepsis is a leading cause of pediatric mortality, claiming more lives in the United States annually than all childhood cancers combined. Early identification in Emergency Departments (EDs) remains challenging, as the current Phoenix criteria establishes an updated international consensus definition for sepsis, however is not designed for use as a screening tool. This study aimed to develop predictive models identifying pediatric patients at risk of sepsis within 24 hours of admission. Multiple tree-based and deep learning models were trained utilizing clinical and laboratory data from the initial four hours of presentation. Both the LightGBM and LSTM architectures demonstrated superior performance, …

Cellular Mechanisms Of Spinal Motoneuron Hypoexcitability Underlying Dynapenia In Aging, Ibrahim Abdul Halim

Browse all Theses and Dissertations

Age-related weakness remains poorly understood as the underlying mechanisms remain unclear. While synaptic input and muscular changes have been investigated with age, intrinsic motoneuron excitability alterations are often overlooked. This thesis provides the first direct assessment of intrinsic excitability and ion channel properties of spinal α-MNs from male and female mice across three ages: young, middle aged, and old. Our findings reveal a decline in intrinsic excitability of motoneurons with age in both sexes. Mechanistic analysis shows sex specific differences: female motoneurons exhibit increased dendritic size, hyperpolarized RMP, and SK channel overactivation, whereas males show only SK overactivation with age. …

Wearable Sensor Data Analysis For Machine Learning-Based Detection Of Posture And Autonomic Responses, Chaitanya Vardhini Anumula

Browse all Theses and Dissertations

This study investigates how Iyengar yoga postures influence autonomic nervous system (ANS) activity by analyzing multimodal physiological signals collected via wearable sensors. The physiological mechanisms underlying Iyengar yoga’s therapeutic effects remain under-explored at the granular, pose-level. Using data collected from 16 participants, this research evaluates whether machine learning models can distinguish between baseline, parasympathetic-dominant, and sympathetic-dominant states based on wrist-worn sensor data. The goals were to explore whether subtle postural variations elicit measurable autonomic responses and to identify which sensor features most effectively capture these changes. Participants performed a sequence of yoga poses while wearing synchronized sensors measuring electrodermal activity …

Computational Assessment Of Vitrimers Self-Healing For Renewable Energy And Aerospace Structures, Walaaeldin Mohamed Ahmed Derbala

Browse all Theses and Dissertations

Self-healing polymers, particularly vitrimers, are emerging as promising candidates in the development of advanced materials for renewable energy and aerospace structures. These materials exhibit dynamic covalent bond exchange mechanisms that enable reprocess ability, damage repair, and extended operational lifetime under harsh conditions. This study presents a density functional theory (DFT)-based computational investigation of the mechanistic pathways and energetics of bond exchange reactions in model vitrimer systems. We explore transition states, energy barriers, and thermodynamic features corresponding to associative and dissociative self-healing reactions in vitrimers. The study focuses on Diaminodiphenyl disulfide (AFD), a bifunctional molecule composed of two para-substituted aminophenyl rings …

Isometric Centroid Encoder (Ice) And Synthetic Data Generation Approaches For Biological Datasets, Prathyusha Kanakamalla

Browse all Theses and Dissertations

This thesis addressed two main challenges in biological data analysis: structure-preserving dimensionality reduction and synthetic data generation for small sample datasets. I proposed the Isometric Centroid Encoder (ICE), a supervised dimensionality reduction method that preserves pairwise distances between class centroids during dimension reduction. Unlike existing methods like Centroid Encoder and Super Encoder, ICE explicitly maintains geometric relationships between biological classes, achieving nearly perfect structure preservation at C dimensions (where C equals the number of classes) with strong performance even in 2D and 3D spaces. Additionally, I compared three generative models (VAE, LSH-GAN, and scDiffusion) for synthetic data generation on small …

A Novel Real-Time Threshold Algorithm For Closed-Loop Epilepsy Detection And Stimulation System, Liang Hung Wang, Zhen Nan Zhang, Chao Xin Xie, Hao Jiang, Tao Yang, Qi Peng Ran, Ming Hui Fan, I. Chun Kuo, Zne Jung Lee, Jian Bo Chen, Tsung Yi Chen, Shih Lun Chen, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Epilepsy, as a common brain disease, causes great pain and stress to patients around the world. At present, the main treatment methods are drug, surgical, and electrical stimulation therapies. Electrical stimulation has recently emerged as an alternative treatment for reducing symptomatic seizures. This study proposes a novel closed-loop epilepsy detection system and stimulation control chip. A time-domain detection algorithm based on amplitude, slope, line length, and signal energy characteristics is introduced. A new threshold calculation method is proposed; that is, the threshold is updated by means of the mean and standard deviation of four consecutive eigenvalues through parameter combination. Once …

Intercellular Stress Generation During 1d Collective Migration Of Cancer Cells, Logan Waddle, Jian Zhang

2025 Research Poster Competition

Physical forces drive many cellular processes such as migration and proliferation. A metastatic tumor will have invasive strands/chains that extend from the main tumor. These chains of cells collectively migrate away from the main tumor to establish new colonies elsewhere in the body. However, how physical forces drive this collective invasion and the required energy for this process is not well understood. Invasion of a metastatic tumor to surrounding tissues leads to a majority of cancer-associated death and is often a collective effort among cells, it is therefore important to fully understand the process behind collective cancer invasion.

The goal …

The Bacteriostatic, Regenerative, And Immunomodulatory Properties Of Extracellular Matrix Particles For Lung Injury, Keera P. Rhoads

Theses and Dissertations

Acute respiratory distress syndrome (ARDS) is a prevalent, life-threatening lung condition, affecting nearly 200,000 Americans annually, with a 40% international mortality rate. There is no cure for ARDS, and current pharmacological treatments have limited effectiveness. Symptoms can be mitigated with mechanical ventilation, though this often leads to ventilator-induced lung injuries (VILI) and puts critically ill patients at risk of infections, including ventilator-associated pneumonia (VAP). A promising therapeutic is the extracellular matrix (ECM), a complex network of structural proteins and bioactive molecules that has been shown to have anti-inflammatory properties and prevent fibrosis. We aim to utilize the regenerative and immunomodulatory …

Exploring The Stem Career Identity Development Of Black Women Across Their Lifespan, Veronica Hurd

Theses and Dissertations

Although STEM is the fastest-growing career sector, Black women are grossly underrepresented as they account for 2.5% of the workforce. Research highlights that this underrepresentation is due to racialized structures in K-12, postsecondary, and career settings that restrict Black girls’ and women’s STEM opportunities. While macrosystems such as hegemonic ideologies, attitudes, and social conditions shape Black girls’ and women’s opportunities in STEM, they continue to persist and achieve their career goals. To explore these barriers and Black women’s persistence in this industry, this study draws from the autobiographical memories of 10 Black women in the field or formerly in the …

Patient Subset Classification Using Encoded Embeddings And Knowledge Graph Retrieval-Augmented Generation, Benjamin A. Holmes

Browse all Theses and Dissertations

The widespread adoption of electronic medical records has created a vast reservoir of clinical data that can be leveraged to better understand how interventions relate to patient outcomes. Much of this information, however, exists as unstructured free-text, posing significant challenges for traditional statistical and machine-learning methods. Solving these challenges would allow the extraction of specific patient subpopulations (clinically relevant cohorts of individuals who share overlapping symptoms, risk factors, or diagnostic criteria), which could be used in precision medicine. Despite this promise, extracting these subpopulations from unstructured medical notes is an ongoing challenge due to the variability of clinical language and …

Vagus Nerve Stimulation Ameliorates Cognitive Impairment Caused By Hypoxia, Birendra Sharma

Browse all Theses and Dissertations

Hypoxia disrupts brain function due to the high demand for oxygen, leading to significant cognitive impairments. While vagus nerve stimulation (VNS) has been shown to enhance cognition, its ability to counteract hypoxia-induced deficits remains unclear. In this study, male Sprague–Dawley rats were assigned to sham, hypoxia, or VNS + hypoxia groups, with VNS delivered during hypoxia (8% oxygen) using biphasic pulses (100 μs, 30 Hz, 0.8 mA). Cognitive performance was evaluated using multiple behavioral paradigms, and hippocampal tissue was analyzed for neurotrophin expression through quantitative PCR and immunohistochemistry. Among the behavioral measures, hypoxia specifically impaired performance on the passive avoidance …

Utilizing Optimization Tools For Passive Flow Control Passage Loss Reduction In Low-Pressure Turbines, Bryant Robert Duane Burton

Browse all Theses and Dissertations

Low-pressure turbines (LPTs) play a crucial role in fuel efficiency and thrust generation of aero-engines. Traditional LPT designs, however, involve multiple stages and numerous blades, resulting in increased weight and manufacturing costs. The challenge of modern- day researchers is to reduce the weight and cost but maintain the high efficiency of LPTs. To address this, one approach is to increase the aerodynamic loading of individual blades, reducing the blade count. However, this can lead to increased secondary losses caused by flow separation, particularly in the endwall regions. This research focuses on optimizing the blade profile at the junction with the …

Generative Adversarial Networks (Gans) For High-Dimensional Biological Data, Harigovind Harikumar

Browse all Theses and Dissertations

This thesis investigates the application of Generative AI models, mainly Generative Adversarial Network (GAN) models to high dimensional and low sample size biological datasets like Motion Sickness, Breast Cancer, Crohn, and Melanoma. We utilized and compared three generative AI frameworks: Vanilla GAN, Wasserstein GAN (WGAN), Locality-Sensitive Hashing GAN (LSH-GAN) and Omics GAN. To address the challenges associated with high-dimensionality and low sample size, which was leading to very poor outputs of biological synthetic samples, we came up with an approach to stop the model when it reaches its saturation level. That is, we printed the loss plots to see where …

The Role Of Trpm7 In Mouse Development And Immune Cell Function, Jananie Rockwood

Browse all Theses and Dissertations

Transient receptor melastatin 7 (TRPM7) functions both as an ion channel and a protein kinase. TRPM7 has been implicated in Mg2+ homeostasis, embryogenesis, cardiac automaticity, and immunity. The purpose of this research was to deepen our understanding of TRPM7 channel and kinase functions. To this end, we used two transgenic mouse models: the TRPM7 gain-of-function (GOF) and TRPM7 kinase-dead (KD) mice to address the consequences of increased channel activity and kinase inactivation, respectively. Global deletion of TRPM7 or the kinase domain alone are embryonic lethal, therefore, we used the TRPM7 GOF mouse to investigate germline transmission. We examined embryo development …

Induced Reduction Of N-Glycosylation Leads To Heart Failure, Anthony M. Young

Browse all Theses and Dissertations

Cardiovascular disease is the leading cause of death and contributes to the increasing global prevalence of heart failure (HF). N-glycosylation is a common co-/post-translational modification where branching oligosaccharides are bound to the extracellular domain of membrane proteins. This creates a diverse range of glycan structures and requires the coordination of hundreds of regulated genes. Inherited mutations in glycan synthesis frequently present with cardiomyopathies leading to HF with reduced ejection fraction (HFrEF). Additionally, gene expression studies of HFrEF patients have shown altered expression of glycosylation-related genes, including alpha-1,3-mannosyl-glycoproten 2-beta-N acetlyglucosaminyltransferase (Mgat1). This gene encodes N-acetylglucosaminyl transferase 1 (GlcNAcT1) which is required …

The Impact Of Ahr And Hs1.2 Enhancer Genetic Variations On Igh Expression And Antibody Production In Human B Cells, Mili Santosh Bhakta-Yadav

Browse all Theses and Dissertations

Antibody production is an essential component of the immune response against pathogens. The immunoglobulin heavy chain (IgH) gene codes for the heavy chain of antibodies. The IgH constant regions Cμ, Cδ, Cγ1-4, Cα1-2, and Cε encode the five major classes of antibodies, i.e., IgM, IgD, IgG1-4, IgA1-2, and IgE, respectively. The transcription of the IgH gene and class switch from IgM to other isotypes is regulated by two 3’ IgH regulatory regions (3’IgHRRs), each of which is a cluster of three enhancer regions (hs3, hs1.2 and hs4). The genetic variations in the hs1.2 enhancer have been identified; a ~53 bp …

Effects Of Invigorating And Relaxing Music On Heart Rate, Blood Pressure, And Heart Rate Variability, Matthew Joshua Faur

Honors Undergraduate Theses

Heart-rate variability (HRV) has been documented to correlate with several health measures, including autonomic nervous system longevity and athletic performance (Zulfiqar, 2010). While increasing age does not affect heart rate, there is a steady decline in HRV, which is a biological marker of aging and the decline of autonomic nervous system function. Furthermore, men who exercise regularly tend to have increased HRV, suggesting a mitigation of the typical age-dependent loss of HRV (Kristal-Boneh et al., 1995). Previous studies have suggested that music may have a physiological effect (e.g., fluctuating vitals, emotional changes) on cardiovascular parameters. However, little is known about …

Measuring Achilles Tendon Stiffness And Kinetics In-Vivo, Chloe L. Pinkston

Honors Undergraduate Theses

This study aims to measure the gastrocnemii Achilles subtendon passive stiffness and energy storage during walking. Stiffness was first determined using a noninvasive method that combines ultrasound, motion capture, musculoskeletal modeling, and a force transducer. Eight healthy participants were tested using this method to obtain the passive force-displacement relationship of the Achilles tendon at two different knee angles to calculate stiffness of the gastrocnemii subtendon. A gait analysis session was then performed using ultrasound, motion capture, and an instrumented treadmill at self-selected slow, normal, and fast walking speeds, using stiffness to calculate the subtendon’s force and energy storage. Gastrocnemii Achilles …

Effect Of Metal Ions On The Reactive Oxygen Species Scavenging Capabilities Of Cerium Oxide For Biological Applications, Agastya Mittal

Honors Undergraduate Theses

Ceria nanoparticles' capabilities to defend cells against oxidative stress through superoxide dismutase activity are well-documented. Ceria nanoparticles demonstrate a ratio between 3⁺/4⁺ oxidative states on the surface of the particles to exhibit oxygen vacancies, a feature that allows these particles to scavenge Reactive Oxygen Species (ROS) in times of Oxidative Stress. Oxidative stress arises from many wounds in the body, such as wounds in the skin, and can have significant impacts on the health of an individual. Even when receiving treatment for the skin wound, ROS can circulate from around the wound, be generated from an imbalance …

Synthesis And Characterization Of Multifunctional Cerium Oxide Containing Nanoparticles For Biomedical Applications, Ishaan Patel

Honors Undergraduate Theses

This study presents the synthesis and comprehensive characterization of a novel core-shell nanoparticle composed of a maghemite (γ-Fe₂O₃) core and a europium-doped cerium oxide (EuCNP) shell, developed for potential use in cancer theranostics. Using a co-precipitation method, Fe₂O₃–EuCNP core-shell nanoparticles were synthesized and compared against control samples of CNPs, EuCNPs, and Fe₂O₃. A variety of characterization techniques, including UV-Vis spectroscopy, fluorescence spectroscopy, TEM, XRD, XPS, DLS, TGA, and DSC confirmed the successful synthesis of core-shell architecture and europium doping. Moreover, Fe₂O₃–EuCNPs demonstrating strong colloidal …

Utilizing Pneumatic Artificial Muscles To Simulate Wingbeat Kinematics For Morphing Uav Wings, Vireli S. Anbarasu

Honors Undergraduate Theses

The controlling muscles of a bird wing change stiffness and length to provide high efficiency when executing a flight maneuver. This variable stiffness allows the muscles to cycle between increasing energy, transmitting it, and restoring it, allowing an overall increase in mechanical and aerodynamic efficiency. Inspired by this, we have developed a system that uses pneumatic artificial muscles (PAMs) to actuate a morphing wing. The stiffness in the PAMS can be controlled to mimic the changes bird flight muscles undergo when executing a forward flapping maneuver. We will evaluate the performance of the PAMs in actuating a morphing wing through …

Effects Of Changes In Strouhal And Reynolds Numbers On Beetle Wing Aerodynamics, Keith L. Thiha

Honors Undergraduate Theses

Insect flight has long been a subject of interest across the scientific community, largely due to the exceptional aerodynamic performance insects demonstrate relative to their size. Insects tend to have very high aerodynamic performance characteristics like thrust and lift generation compared to their size. This has many potential applications in improving aircraft performance, however the flow phenomena concerning insect wing aerodynamics is still an area of ongoing research. This study aims to investigate how variations in key nondimensional flow parameters—specifically the Reynolds number and Strouhal number—affect the aerodynamic performance of beetle wings. Strouhal numbers ranging from 0.2 to 0.6 were …

Coral Vision – Crustose Coralline Algae Detection With Computer Vision, Ryan Tseng

Master's Projects

Crustose coralline algae (CCA) are a group of red algae that are vital contributors to the health of coral reef ecosystems. Monitoring CCA abundance can serve as an indicator for coral reef health and improve reef conservation efforts. Autonomous Reef Monitoring Structures (ARMS) are artificial structures that can be deployed into coral reef ecosystems and retrieved to gather ecological data without harming reef structures. Traditional methods of calculating CCA abundance require manual analysis and are labor-intensive. Recent developments in computer vision and deep learning technology have provided an avenue to fully automate this task. This research aims to train a …

Microplastics Detection, Characterization, And Cytotoxicity Evaluation Via Lab-On-Chip, Liyuan Gong

Open Access Dissertations

Microplastics (MPs) pose a growing challenge to the ecological system, prompting increasing research efforts in diverse directions. Accurate characterization of MPs is essential for understanding their properties, relying on efficient sampling and detection techniques. Additionally, studying the cytotoxic effects of MPs is critical for evaluating their impact on biological systems. Lab-on-chip (LoC) systems offer significant advantages for precise particle manipulation and compatibility with advanced analytical instrumentation, making them valuable for MP detection and characterization. Microfluidic-based on-chip cell-culturing systems provide a controllable, physiologically relevant microenvironment for more realistic in vitro tissue modeling. By leveraging advanced LoC concepts and integrating state-of-the-art machine …