Digital Commons Network^™

Analyzing Musical Emotions: A Multi-Dataset Approach To Sentiment And Mood Classification In Songs, Mahad Syed

SPARK Symposium Presentations

Music evokes a wide range of emotions, yet most music recommendation systems focus on sound and listening patterns rather than the meaning of lyrics. This project enhances lyric-based emotion recognition by applying Natural Language Processing (NLP) and Machine Learning (ML) to classify song lyrics into emotional categories.

I used eight datasets from Kaggle, including collections of lyrics, emotion labels, and audio features, providing a strong foundation for analysis. Our approach combines traditional NLP techniques (like TF-IDF and Word2Vec) with advanced deep learning models (such as BERT and XLNet) to classify lyrics into categories like happy, sad, angry, calm, romantic, and …

Profiting On The Kentucky Derby, Bailey Korfhage

Undergraduate Theses

This paper analyzes the quantitative data of horses that ran in the Kentucky Derby to recognize statistically significant variables to predict the horse that comes in first or in-the-money. This analysis is specific to the post-implementation of the points system that began for the 2013 Kentucky Derby. Churchill Downs, the host of the Kentucky Derby, changed the methodology of qualification for a horse to enter the race; instead of qualifying with highest earnings in lifetime starts, the institution implemented a points system that awarded different proportions of points depending on the value of various prep races leading up to the …

Identifying The Factors Affecting The Survival Of Trauma Patients Using Logistic Regression Analysis, Maggie Smith

Honors College Theses

There is a broad interest among researchers and clinicians in identifying factors affecting clinical outcomes of patients with physical trauma. Numerous factors affect Hospital Discharge Status (HDS), one of the main binary outcome variables of trauma patients. Logistic regression is one of the widely used methods to analyze relationships between a set of predictors with a binary outcome. In this study, a logistic regression model is built for HDS. Predictors include arrival time, age, trauma level, injury severity score, arrival heart rate, arrival blood pressure, length of hospital stay, time from injury to arrival at Billings Clinic (BC), patient transfer …

Algebraic Topics For Future Middle School Teachers, Leonard Van Wyk

Department of Mathematics and Statistics - Faculty Scholarship

This text contains algebraic concepts relevant to the middle school mathematics curriculum. Topics include the basics of number theory, functions, linear systems, matrices, and polynomials.

Wind Collapse Risk And Serviceability Drift Of Steel Concentrically Braced Frame Buildings, Sarah Corrinne Partington Cluff

Theses and Dissertations

Seismic design provisions use the ductility and reserve strength of the lateral structural system to reduce the loads used in design, making the structural design more economical while maintaining life safety. In contrast, current wind design provisions do not. Conventional wind design relies primarily on elastic behavior. The objective of this study is to determine a wind response modification factor for steel concentrically braced frames that could be applied to reduce wind design loads based on ductility and reserve strength, while still meeting drift requirements for serviceability of the structure. To achieve the objective, three types of ductile braced frames …

Steps Towards Effective Human-Robot Co-Manipulation Through Real-Time Modus Detection And Effects Of Stiffness Variation For Human-Soft-Robot Dyads, Shaden Moss

Theses and Dissertations

A group of individuals can coordinate very easily to carry a large or heavy object together. This act of collaborative carrying is called co-manipulation. Unlike human teammates, robots cannot easily detect and respond to the intent of human partners during co-manipulation tasks. This shortcoming can be compensated for via the physical design and the software design of robots. This work treats software design with a neural net that detects human modus (or the manner in which a team moves an object together) in real time. This work treats physical design with the use of a soft robot in human-robot co-manipulation, …

Improving Devices To Measure The Thermal Conductivity Of Molten Halide Salts, Ryan J. Ruth

Theses and Dissertations

Molten salts are of high interest for use in nuclear reactors, though their thermophysical properties are notoriously hard to measure due to the extreme conditions created by them. Significant gaps remain in thermal conductivity and heat capacity data, which this work seeks to fill by improving the Needle Probe-a modified transient hot wire probe originally used by Merritt et al to measure the thermal conductivity of FLiNaK- measuring two new salts, and exploring new materials for use with molten salts. Improvements made to the Needle Probe include automation to reduce human error, more accurate heat generation modeling, a more thorough …

Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning With Biosensor Signals, Narmatha Chellamani, Saleh Ali Albelwi, Manimurugan Shanmuganathan, Palanisamy Amirthalingam, Anand Paul

School of Public Health Faculty Publications

Diabetes is a growing global health concern, affecting millions and leading to severe complications if not properly managed. The primary challenge in diabetes management is maintaining blood glucose levels (BGLs) within a safe range to prevent complications such as renal failure, cardiovascular disease, and neuropathy. Traditional methods, such as finger-prick testing, often result in low patient adherence due to discomfort, invasiveness, and inconvenience. Consequently, there is an increasing need for non-invasive techniques that provide accurate BGL measurements. Photoplethysmography (PPG), a photosensitive method that detects blood volume variations, has shown promise for non-invasive glucose monitoring. Deep neural networks (DNNs) applied to …

Using Video Models Plus Feedback To Teach Interview Skills, Zoe Odom

Honors Theses

Autism is a neurodevelopmental disorder that is partially characterized by deficits in social communication and interaction. These deficits can be displayed by struggles in developing relationships and social-emotional reciprocity (American Psychiatric Association [APA], 2022). In the context of competitive employment, social skill deficits can impose challenges in securing and maintaining an employment position, with 8.1% of adults with disabilities between the ages of 16-65 unemployed (U.S. Bureau of Labor Statistics, 2024). Video-based instruction (i.e., video models and prompts) has been used to teach adults with autism a wide variety of skills up to 100% accuracy, including vocational skills such as …

Human Capital And Lifetime Income Gains Of Scaling-Up Small-Quantity Lipid Nutrient Supplements Among Children Under 2 Years: A Modelling Analysis, Nandita Perumal Phd, Goodrarz Danaei, Günther Fink, Mark Lambiris, Christopher R. Sudfeld

Faculty Publications

Undernutrition in early childhood is associated with adverse health and developmental outcomes later in life and remains a persistent global public health problem. Providing small-quantity lipid nutrient supplements (SQ-LNS) to children aged 6-24 months improves child growth and neurodevelopmental outcomes, but the potential long-term benefits to human capital have not been previously estimated. We estimated the potential returns to schooling and lifetime income attributable to increasing coverage of SQ-LNS for children < 2 years of age from 0% to 50% or 90% per five-year birth cohort in five countries (Bangladesh, Burkina Faso, Ethiopia, Pakistan, and Uganda) with a high burden of undernutrition. Random-effects meta-analyses were used to estimate the effect of SQ-LNS on child development using evidence from randomized controlled trials, and to estimate the returns to lifetime income as a function of change in development based on a de novo meta-analysis of observational economic studies. Gains in school years attributable to scaling-up SQ-LNS to 90% coverage ranged from 0.14 million school years (95% uncertainty interval [UI]: 0.064, …

Nursing Educators’ Perceptions Of Using Virtual Simulated Games In Nursing Education, Ruhee Waheeda Mir

Walden Dissertations and Doctoral Studies

Nursing educators of Trinidad and Tobago have limited experience with virtual simulated games (VSGs) as a part of their teaching methodology. This lack of experience was highlighted during the COVID-19 pandemic as educators had to use virtual approaches in their classrooms and struggled with unfamiliar technologies. The purpose of this qualitative descriptive study, guided by the extended technology acceptance model, was to explore the perceptions of Trinidadian and Tobagonian nursing educators regarding the use of a VSG as a teaching tool. The sample consisted of eight nursing educators from an educational institute in Trinidad who met the criteria of being …

Knowledge Distillation For Efficient Object Detection: Toward Scalable And Deployable Vision Models, Qizhen Lan

All ETDs from UAB

Object detection is a critical component of autonomous driving, requiring real-time, robust perception to ensure safety. However, state-of-the-art deep neural network object detectors typically incur high computational cost and memory footprint, hindering their deployment in resource-constrained environments such as self-driving vehicles. This dissertation addresses the need for efficient yet accurate detectors by leveraging knowledge distillation (KD), a model compression technique that transfers knowledge from a high-capacity teacher model to a lightweight student model. While KD has seen success in image classification, its application to object detection poses unique challenges due to multiple instances per image and complex output structures. To …

Spartan Daily, April 16, 2025, San Jose State University, School Of Journalism And Mass Communications

Spartan Daily, 2025

Volume 164, Issue 33

Ligo Detector Characterization In The First Half Of The Fourth Observing Run, S. Soni, B. K. Berger, D. Davis, F. Di Renzo, A. Effler, T. Ferreira, E. Goetz, Francisco Llamas Villarreal, Volker Quetschke, J. Glanzer

Physics & Astronomy Faculty Publications

Progress in gravitational-wave (GW) astronomy depends upon having sensitive detectors with good data quality. Since the end of the Laser Interferometer Gravitational-Wave Observatory-Virgo-KAGRA third Observing run in March 2020, detector-characterization efforts have lead to increased sensitivity of the detectors, swifter validation of GW candidates and improved tools used for data-quality products. In this article, we discuss these efforts in detail and their impact on our ability to detect and study GWs. These include the multiple instrumental investigations that led to reduction in transient noise, along with the work to improve software tools used to examine the detectors data-quality. We end …

(Un)Becoming-Scientist-With: Mapping Material-Discursive Forces That Shape Undergraduate Student's Science Identity Development Across The Stemm Learning Ecosystem, Katherine Ayers

Electronic Theses and Dissertations Archive

This dissertation examines the material and discursive agents that shape undergraduate students’ science identity development within a science, technology, engineering, math and medicine (STEMM) ecosystem in the Southern United States. Using Karen Barad’s agential realism as a theoretical framework, the study conceptualizes science identity as a dynamic process of (un)becoming-scientist-with, emphasizing the intra-actions of material and discursive agents across formal and informal STEMM learning spaces. Drawing on narrative inquiry methods and graphic elicitation (ecomaps) interviews, this postqualitative study maps the entanglements of racism, discrimination, and systemic barriers that affect science identity construction. Four undergraduate participants engaged in STEMM programs affiliated …

A Dual Perspective On Fault Mechanics: Insights From Laboratory Acoustic Emissions And Induced Seismicity, Roshan Koirala

Electronic Theses and Dissertations Archive

Earthquakes occur across multiple spatial scales depending on fault zone characteristics and mechanics. Fault failure, the mechanism responsible for earthquakes, is driven by the complex interaction of stress, material properties, fault structure, and fluids. Understanding how these factors impact fault stability is key to seismic hazard assessment. Seismological observations provide crucial information about fault mechanics. However, directly measuring the influence of fault properties on earthquake nucleation and fault rupture remains a significant challenge. This dissertation investigates the multi-scale processes of earthquake nucleation and fault failure. This involves integrating high-precision locations of acoustic emission events (AEs) in laboratory fault gouge experiments …

On The Determinant Of Up On Mk(P,Χ), Xingyu Huang, Timothy J. Huber, Dongxi Ye

School of Mathematical & Statistical Sciences Faculty Publications

In this work, for p a prime, we compute the absolute value of the determinant of the UpUp-operator on the vector space Mk(p,χ)Mk(p,χ) of holomorphic modular forms of weight k and level Γ0(p)Γ0(p) with character χχ. As an implication, we confirm a number of conjectures of the second author.

The Kemp Foundation’S Teaching Excellence Award Ceremony (2025 Program And Video), Illinois Wesleyan University

The Kemp Foundation's Teaching Excellence Award Ceremony Programs

No abstract provided.

Development Scenarios And Wildfire Risk In Central Oregon, Samantha Hall

Dissertations and Theses

Risk from natural hazards occurs where areas vulnerable to natural hazards and development intersect. Development in vulnerable areas is a societal choice that has a lasting impact as our built environment is relatively permanent. Development patterns that contribute to increased wildfire risk mostly occur within the wildland urban interface, a land use type where development is at the fringes or intercept of wildland areas and is more flammable due to surrounding vegetation, slope, local climate, and other factors. To understand how past and future development potentials may impact fire risk in wildfire prone areas, a case study of Deschutes County, …

A Concrete Naming Convention For Small Intervals, Laurence S. Willis

Gamut: Online Journal of the Music Theory Society of the Mid-Atlantic

In tuning theory, names proliferate for the bewildering array of intervals available to theorists and scholars. Of particular difficulty is the naming of small intervals: as a group these are generally referred to as commas, following the Greek practice. The various names used for small intervals derive from many different sources, some etymologically related to the ancient practice and some to the origin of the interval in more recent music theory. The problem with this situation is that while they remain fascinating from a scholarly perspective, these names are unwieldy for technical usage, sometimes barely understandable for an informed audience, …

2025 Sfa Undergraduate Research Conference, Honors, School Of

Undergraduate Research Conference

Event Program for the 2025 Undergraduate Research Conference (URC) at SFASU.

Exploring Graphs And Chromatic Symmetric Functions, Olivia Payne

Undergraduate Research Conference

We consider graphs with a small number of vertices and analyze the coefficients of hook partitions of their chromatic symmetric function, which is a generalization of the chromatic polynomial of a graph. Some of these coefficients can hold information about the graphs themselves and, in this research, we find a combinatorial formula for coefficients of hook partitions. This research is motivated by Stanley's Tree Conjecture.

Antioxidant Properties Of Phytochemicals In Watercress And Mint Extracts In Serum Albumin, Perla Tovar

Undergraduate Research Conference

Hypothesis: Phytochemicals present in mint and watercress help stabilize protein under oxidative stress. Main Objective: Analyze the interaction of HSA with different phytochemicals present in mint extract.

Grp-082 Ready Cluster One: Optimizing Film Success With Data Science, Mohsin Md Abdul Karim, Joseph Richardson

C-Day Computing Showcase

This study presents a novel approach to predicting and optimizing screenplay investments by combining graph theory and finite mixture modeling (FMM) techniques. We construct a k-partite graph representing movies, genres, subgenres, production companies, directors, actors, and directors of photography, to explore the interconnectedness between these entities. Using FMM, we identify clusters within budget tiers, enabling a deeper understanding of how similar films perform based on their creative team and production characteristics. By balancing profit potential with risk-adjusted profit, the model suggests the most viable budget tiers for unproduced screenplays. This approach incorporates confidence intervals and evaluates the accuracy of budget …

Gc-074 Real-Time Object Detection, Rohit Malik

C-Day Computing Showcase

This project explores the implementation of real-time object detection using the You Only Look Once (YOLO) architecture. Leveraging its speed and accuracy, we developed a system capable of identifying and localizing multiple objects within live video streams. Our implementation focused on optimizing YOLO's performance for real-time applications, specifically addressing the trade-off between speed and accuracy. We employed a pre-trained YOLO model and fine-tuned it on a custom dataset tailored to specific object classes. This fine-tuning process aimed to enhance the model's ability to recognize objects in our target environment. The system was implemented using Python and the OpenCV library, enabling …

Gc-079 Nibbleai, Ryan Deem, Zeynep Birgili, Austin Cook

C-Day Computing Showcase

Ever looked into your fridge or pantry and wondered, “What can I make with this?” NibbleAI is a mobile app designed to solve exactly that. Using artificial intelligence, the app identifies ingredients from user-uploaded images and suggests recipes based on what’s available. Built with React Native and powered by a DenseNet169 model for image recognition, NibbleAI seamlessly analyzes photos and returns curated recipe ideas — all within a few taps. This intuitive approach helps users reduce food waste, save time, and get creative with the ingredients they already have.

Grm-076 Assessing The Performance Of Intelligent Agents In Visual Food Recognition Relative To Manual Data Entry, El Arbi Belfarsi, Henry Ekeocha

C-Day Computing Showcase

Accurate dietary assessment remains a critical yet time-consuming task in health and nutrition monitoring. This study benchmarks the macronutrient estimation capabilities of three intelligent vision agents: GPT Vision, Claude, and Gemini against manually logged food data. We unify two distinct datasets: MenuMatch, annotated by a professional nutritionist, and CGMacros, populated through user entries on MyFitnessPal. After flattening and cleaning both datasets, we first assess each model’s performance in calorie estimation. GPT Vision outperforms the others with the lowest percentage error 13.83% and is subsequently used to benchmark the macro estimations of Claude and Gemini. While Claude shows higher carbohydrate and …

Grm-109 Quantum Machine Learning For Science And Engineering Research, Andrew Polisetty

C-Day Computing Showcase

This research project aims to understand and explore the practical applications of Quantum Machine Learning (QML) in solving real-world challenges. By comparing classical machine learning models such as Support Vector Machines (SVM), Neural Networks, Logistic Regression, and Naive Bayes, with their quantum counterparts. Quantum Support Vector Machines (QSVM), Quantum Neural Networks (QNN), Quantum Logistic Regression (QLR), Quantum Deep Neural Networks (QDNN), and Hybrid Quantum Models, we gain hands-on experience in advanced machine learning techniques. The project cover diverse domains including cybersecurity, healthcare, industrial engineering, energy management, and supply chain optimization. Each part of project involves working with real-world datasets, preprocessing, …

Grp-021 Shap-Explainable Image-To-Topology Regression, Charles Fanning

C-Day Computing Showcase

We evaluated whether deep regression models predicting vectorized topological features (in the form of persistence landscapes) actually learn the underlying persistent homology of the image. A DenseNet-121 is trained to regress 300-dimensional persistence landscapes from grayscale scene images. Using SHAP, we evaluate the contribution of pixels in the original images to the persistence landscapes. Across all six classes, SHAP-feature overlap is consistently lower than the baseline, implying that DenseNet may not be truly learning the underlying persistent homology.

Uc-040 Security Lookup Interface Project, Alhasan Mohsen, Alejandro Albarran, Ethan Lan, Jerrat Jester

C-Day Computing Showcase

The "Security Lookup Interface" capstone project aims to create a streamlined tool for COX's cybersecurity team, enabling analysts to efficiently perform IP address and hostname lookups while providing actionable, data-driven insights to enhance security investigations. The project will develop a user-friendly interface that simplifies the lookup process, allowing cybersecurity analysts to quickly retrieve relevant data and make informed decisions during security investigations. One of the key features of the tool is its seamless integration with both internal APIs and external resources. This integration will ensure that analysts have quick and easy access to valuable information, minimizing manual effort and enabling …