Digital Commons Network^™

Leetquest, Sanvir Bal, Vladimir Ceban, Matty Herzig, Daryl Ho

Computer Science and Engineering Senior Theses

The technical interview process for software engineering position has drastically changed in recent times to focus on Data Structures and Algorithms (DSA). Although, data structures and algorithms are a foundational aspect of several programming languages, the questions asked in the technical interview process do not accurately reflect, in terms of style and difficulty, the experience students and professionals have with DSA from school and work respectively. As a result, many have looked to online resources in order sharpen their DSA problem solving skills. However, the existing solutions are riddled with flaws. In particular, the learning resources they provide are locked …

Statistical Programming For Adaptive Monitoring In Software Defined Networks Using Linear Programming, Fatemeh Amou Aghaei, Ruairí De Fréin

SAML-25 Workshop on Statistical and Machine Learning

Adaptive monitoring in Software Defined Networks (SDNs) is essential to reduce overhead and prioritize critical flows. This paper introduces AdaptMon, a Linear Programming-based model that dynamically allocates monitoring resources based on estimated error rates. By modeling allocation as a probability distribution and enforcing a fairness constraint using an ℓ1-style deviation bound, the approach maximizes expected monitoring utility while preserving balance across the network. Simulations show that AdaptMon reduces monitoring delay by up to 40% without sacrificing anomaly detection accuracy. The model is interpretable, lightweight, and grounded in statistical programming, making it a practical solution for real-time SDN environments.

A Transfer Learning Load Adjusted Approach For Video-On-Demand Systems Given Limited Training Data, Kangogo Kimeli, Ruairí De Fréin

SAML-25 Workshop on Statistical and Machine Learning

Inadequate data complicates planning and allocation of VoD resources, potentially hindering the scalability of VoD services. We propose a Transfer Learning Load Adjusted (TLLA) algorithm for resource management given limited VoD data. TLLA leverages the knowledge gained from pre-trained models by storing features and patterns that can be used to train Machine Learning (ML) related tasks. We model limitations in VoD data by proportionally freezing 50% of the neural layers in models trained from pre-trained and source domains. We evaluate the performance of the frozen neural layers by comparing them to unfrozen data. Freezing 50% of the neural layers in …

Investigation Of Maleic Anhydride In Organic Synthesis, Emma Nissen, Zhijun Wang, Qianli Rick Chu

Arts & Sciences Undergraduate Showcase

This research explores the synthetic utility of maleic anhydride; a versatile and reactive compound widely used in organic and industrial chemistry. The study focuses on the synthesis of N-allyl maleimide and 3-hexyl-1,2-cyclobutanedicarboxylic acid. N-allyl maleimide, confirmed via ^1H NMR spectroscopy, was synthesized in high yield and shows potential as a monomer or intermediate in organic synthesis. Additionally, the photochemical synthesis of a novel compound, 3-hexyl-1,2-cyclobutanedicarboxylic acid, was achieved and characterized. Its long aliphatic side chain contributes to decreased melting point and increased solubility. These findings demonstrate maleic anhydride’s utility in forming intermediates and bicyclic compounds under mild conditions, supporting its …

Real-Time 3d Automated Spotlight Tracking System, Francine Garcia, Mary Hemker

Computer Science and Engineering Senior Theses

Commercially available automated spotlight systems tend to be expensive and unattainable for smaller school or community theaters. This project provides a cheap alternative to automated spotlight systems on the market and is compatible with most stage lighting architecture by using the Digital Multiplex (DMX) Protocol.

Circuit boards with Ultra-Wideband (UWB) radio frequency track an actor’s coordinates in a 3D space defined by four UWB anchors. A Raspberry Pi single-board computer acts as a controller and converts the coordinates into pan and tilt angles and maps these calculations to values that the spotlight can read in order to move. These values …

The Effect Of Birthweight And Gestational Age On Cognitive Function In Midlife: The Bogalusa Heart Study, Eunsun Gill, David J Libon, Soo Jung Kang, Ileana De Anda-Duran, Lydia A Bazzano, Wei Chen, Camilo Fernandez-Alonso, Emily W Harville

Rowan-Virtua School of Osteopathic Medicine Departmental Research

BACKGROUND: Although the relationships between birthweight, gestational age (GA), and cognitive function (CF) before midlife have been demonstrated, the relationships after midlife and potential racial disparities remain inconclusive. This study examined the association between birthweight, GA, and midlife CF stratified by race.

METHOD: 1,032 subjects from the Bogalusa Heart Study (67% Whites, 33% Blacks, mean age 48.1 ± 5.3 years) were studied. Cognition was assessed with tests measuring verbal episodic memory, working memory, attention, graphomotor information processing speed, and global CF. Each test was standardized by sex and age, then averaged. The global CF was computed by averaging all cognitive …

What’S Troubling You? Examining How Biology Teaching Assistants Talk About Teaching Concerns, Lorelei E. Patrick, Hillary A. Barron, Julie C. Brown, Sehoya Cotner

Biological Sciences Faculty Publications

Undergraduate students in science classes are more engaged and demonstrate increased performance when instructional methods include authentic science practices and active learning strategies. Non-majors students (i.e., those enrolled in science classes to fulfill a degree requirement) typically receive instruction that is more lecture-based and prescribed, however, which contributes to disinterest, diminished self-expectations, and lower performance. Teaching assistants (TAs) often interact with undergraduate students more closely in science classes than faculty and thus could potentially have far-reaching impacts on these students. Therefore, understanding how TAs think about their science teaching and the concerns they have about their methods can lead to …

Examining The Legal And Educational Implications Of School Resource Officers In Education, Tanvi Desai

Florida Atlantic University Undergraduate Law Journal

Predominantly serving the youth in schools, some states across the United States have implemented full-time sworn law enforcement officers, known as School Resource Officers (SROs), who are specially and specifically trained to promote safety within schools. Succeeding an increase in concern surrounding the juvenile justice system and juvenile crime, funding for school-based law enforcement programs has increased in conjunction, allowing for over 45% of public schools in the country to have implemented SROs within their walls. However, concerns surrounding the excessive use of force surrounding SROs have instigated debates regarding the necessity of a police presence on campus, as instances …

Beyond The White Coat: The Fight For Equal Healthcare By Minorities, Morgan Robinson

Florida Atlantic University Undergraduate Law Journal

Systematic oppression through medical discrimination has left a high rate of death in the minority community, with Black women having 2.6 times the rate of maternal mortality than White women. Medical professionals ignore minorities at a higher rate than White people. People of Color have been used as testers for medical professionals and reap the generational trauma of it, such as subjects of the Tuskegee Syphilis experiment passing it to their children. Even more, doctors today are taught that Black people have a “higher pain tolerance than other races,” so their symptoms are often dismissed. Legal solutions must be implemented …

Tripping Over "Trips"; International Inequities In Critical Phamaceutical Access, Michael Gomez

Florida Atlantic University Undergraduate Law Journal

Directed by the World Trade Organization (WTO), the Agreement on Trade-Related Aspects of Intellectual Property Right (TRIPS) of 1995 is the most comprehensive international policy on the creation, protection, definition, and transfer of International Property Rights (IPR). This policy was particularly damaging for underdeveloped countries when it came to the trade and importation of name-brand drugs, as TRIPS inherently expedited the unethical process of evergreening drug patents. As a result, the agreement forced many vulnerable regions— such as the Southern African Development Community (SADC)— to become dangerously dependent on foreign generic drug imports, predominantly from India. This paper analyzes the …

Serial Killer Terminology And Its Effect On Criminal Trials, Alice Gnesin

Florida Atlantic University Undergraduate Law Journal

The terminology used during court proceedings plays a pivotal role in shaping the legal outcomes and sentencing for serial killers. This study examines how specific language, mainly terms such as "serial killer," impacts sentencing severity. By analyzing cases involving serial killers and the terminology used, there is a proven correlation between terminology and sentencing. For example, Ted Bundy (30 confirmed murders) and Jeffrey Dahmer (17 confirmed murders) were both investigated by Robert Ressler—who pioneered FBI profiling and coined the term "serial killer." The term was extensively used within their trials, impacting their sentencing. This can be compared to John Wayne …

Reexamining The Second Amendment: The Impact Of Police Militarization On Civilian Gun Ownership, Merin Ajith

Florida Atlantic University Undergraduate Law Journal

The increasing militarization of police forces in the United States contains profound implications on citizens’ Second Amendment rights, specifically concerning the ownership of weapons capable of mass violence. The original intent of the Second Amendment was not only to guarantee self-defense but also to safeguard citizens’ ability to resist a potentially tyrannical government. As police forces acquire military grade weaponry, some argue that civilians should have access to similar arms to maintain the balance of power between the state and its citizens, as outlined by the purpose of the Second Amendment. The historic use of violent police force to suppress …

Evaluating Machine Learningworkloads Inwebassembly: A Comparison Of Browser-Based Runtimes Using Python, Sallar Khan, Tania Malik

SAML-25 Workshop on Statistical and Machine Learning

WebAssembly (WASM) has emerged as a transformative technology, enabling the deployment of high-performance applications across diverse platforms, including web environments traditionally unsuited for computationally intensive tasks. Despite extensive research on its general performance characteristics, the execution of machine learning (ML) workloads in browser-based Python runtimes is still in an early exploratory phase. This study presents a systematic evaluation of three ML models, K-Means, Logistic Regression, and Naïve Bayes—executed in-browser using two Pythonbased WASM runtimes: Pyodide and PyScript. The findings highlight the practicality of deploying ML workloads in browser-based environments using WASM and provide insights into the trade-offs between runtime efficiency …

Shape-Based Nanoparticle Classification Using Machine Learning, Caitlin Caitlin Robertson, Hender Lopez

SAML-25 Workshop on Statistical and Machine Learning

The accurate classification of nanoparticles (NPs) based on their shapes is crucial for understanding their physical-chemical properties and predict their bioactivity. Nowadays, synthesis method are able to produce a broad range of shapes, such as spheres, cubes and branched NPs and commonly these NP shapes are only described qualitative. This study presents NP descriptors obtained from NPs contours extracted from electron microscopy images. Descriptors such as Fourier descriptors, aspect ratio, and compactness are then used as input for machine learning classifiers. In particular, XGBoost, Random Forest, and neural networks are explored and the their performances are compared and discussed.

Enhancing Dermatological Skin Lesion Classification With Multi-Modal Attention-Based Models And Explainability, Conan Oreilly

SAML-25 Workshop on Statistical and Machine Learning

Accurate classification of skin lesions is critical for early detection of melanoma and other malignancies, particularly in resource-limited settings. This study presents a novel multi-modal machine learning framework that integrates dermoscopic images and structured clinical metadata to improve diagnostic performance. Leveraging the PAD-UFES-20 dataset, which includes over 2,000 smartphonecaptured lesion images and associated patient metadata, we benchmark a series of unimodal and multimodal models. Our results demonstrate that modality attention fusion (MAF) applied to a frozen SwinV2-Tiny vision transformer and metadata multi-layer perceptron (MLP), augmented with focal loss, yields a state-ofthe- art weighted F1-score of 0.84 and balanced accuracy of …

Analyzing Option Chain Bid–Ask Spreads With Machine Learning, Brian Byrne, Qianru Shang

SAML-25 Workshop on Statistical and Machine Learning

This paper investigates the determinants of option bid–ask spreads using machine learning techniques. We analyze a cross-sectional dataset of Apple Inc. (AAPL) call options, focusing on the relative bid–ask spread as the target variable. By comparing linear models with ensemble methods such as Random Forests and XGBoost, we find that nonlinear machine learning methods significantly outperform traditional OLS regression. The most influential factors are moneyness, implied volatility, and time to expiration, while volume and open interest have limited predictive power. Results suggest that spreads are driven by a mix of market microstructure dynamics, capital constraints, and regulatory requirements such as …

Intention To Commute By Public Transportation And/Or By Foot: Findings From A Pls Structural Equation Model, Simona Balzano, Houyem Demni,, Edoardo Pascucci,, Luisa Natale, Giuseppe Cappelli, Sofia Nardoianni, Giovanni C. Porzio

SAML-25 Workshop on Statistical and Machine Learning

Sustainable mobility stands at the forefront of contemporary discussions, driven by the clear imperative to transition towards more environmentally friendly transportation and patterns. This shift is widely recognized as a crucial opportunity to address the challenges and inherent dangers posed by climate change. It is then crucial to introduce attitudes to encourage voluntary behavioral changes toward different sustainable solutions. In this perspective, to foster a future where sustainable personal mobility options are widely embraced and integrated, it is crucial to comprehend the inclination of younger generations to use them. For this reason, a survey on the use of sustainable mobility …

Shedding Light On Cellular Glycolysis Pathway Kinetics Using A Spectralomics Approach, Integrating Multivariate Statistical And Machine Learning Analytical Approaches, Nitin Patil, Zohreh Mirveis, Hugh Byrne

SAML-25 Workshop on Statistical and Machine Learning

The potential of time resolved label-free Raman microspectroscopy to elucidate the kinetics of cellular and subcellular glycolysis pathway was explored in this study. A549, human lung cells were cultured in an unbuffered minimal medium with glucose as a sole carbon source under three different modulated conditions. Modulator drugs oligomycin and 2-deoxyglucose were used to stimulate and inhibit the glycolysis pathway. Initially the kinetic glycolysis assay was used to monitor the glycolysis end-point kinetics followed by development of a numerical model capable of simulating the end-point kinetics. For Raman spectroscopy, samples at different timepoints from the experiments with similar conditions as …

Ai-Driven Personalized Radiotherapy Planning, Nithin Venkatesh, Marco Pota, Maged Shaban

SAML-25 Workshop on Statistical and Machine Learning

The planning of radiation oncology treatment is made more dynamic and individualized by Artificial Intelligence (AI). Routine radiotherapy practice applies normative procedures indifferent to patient-specific parameters such as tumor volume, patient anatomy, and heterogeneity in the delineation of treatment response. Inadequate and over-radiation treatment is the most prevalent outcome. Further, with the inclusion of AI, it can facilitate enhancing the healthcare industry through optimizing radiotherapy using an array of patient information such as molecular profiles and imaging data. The product offers an end-to-end AI-driven solution to all aspects of radiotherapy, from initial consultation (diagnosis) to adaptive treatment planning. All the …

Early Lane Change Prediction For Mixed Traffic With V2x Communication, Muhammed Fatih Koc, Nouman Ashraf, Pramod Pathak, Sachin Sharma

SAML-25 Workshop on Statistical and Machine Learning

Lane change prediction is essential for ensuring road safety and effective decision-making in autonomous vehicles (AVs). AVs will probably take several decades to penetrate new vehicle sales. As AVs and human-driven vehicles (HDVs) will coexist in traffic for the long term, AVs must understand the lane change intentions of surrounding HDVs. Lane changing is a critical manoeuvre that can cause a crash if it is performed late or if incorrect lane adjustments are made. Therefore, forecasting surrounding vehicles’ lane change intentions in advance is essential to ensure safe driving in mixed traffic environments having both AVs and HDVs. The unpredictability …

A Machine Learning Approach To Improve Prediction In Chemical Exposure Risk Assessment, Michele Marro, Cédric Koller, Hasnaa Chettou, David Vernez

SAML-25 Workshop on Statistical and Machine Learning

Exposure models play a crucial role in predicting chemical exposure in workplaces, offering an essential alternative to measurements, which are resource-intensive and time-consuming and sometimes not possible. Despite their widespread use and continuous development, significant challenges persist, including variability in predictions, limited model updates, and difficulties in accessing the required input data. In this study, we investigate how modern machine learning techniques can contribute to the improvement of exposure models by addressing these limitations. To overcome the frequent lack of data, we explore the use of synthetic datasets generated through existing exposure models. This approach allows for the study of …

Interpretable Ai In Education: A Comparison Of Glass-Box Models For Predicting Student Success, Jan Glazenborg

SAML-25 Workshop on Statistical and Machine Learning

This Master’s thesis addresses early identification of first-year Computer Science students at risk of underperformance by comparing inherently interpretable (“glass-box”) predictive models with the existing Naïve Bayes–based PreSS tool. The PreSS dataset was originally compiled by Quille & Bergin from 692 first-year CS1 students across eleven institutions in Ireland and Denmark, who completed surveys on programming and mathematics backgrounds, gaming habits and a short programming test four to six hours into the course. Seventeen normalized features capturing demographic, academic and behavioural factors were extracted. In this thesis, four machine learning models are evaluated: Naïve Bayes, explainable boosting machines, automatic piecewise …

Pros & Cons Of Reinforcement Learning - Illustrated By The Problem Of Controlling Gantry Robots, Horst Zisgen

SAML-25 Workshop on Statistical and Machine Learning

In this talk a solution for the dynamic scheduling of flexible flow shop systems using gantry robots for material handling by means of simulation and Reinforcement Learning (RL) is presented. Subsequently the pros and cons of a RL approach are briefly discussed and illustrated at the robot control problem.

Survival Predictions From Classification Algorithms – Concepts And Application To Graft And Patient Survival After Kidney Transplantation, Antje Jahn

SAML-25 Workshop on Statistical and Machine Learning

Clinical prediction models are developed to predict long-term patient outcomes following medical interventions. One example motivating this research is the prediction of graft and patient survival after kidney transplantation, using data from the German organ transplantation registry. A practical issue in this context is to deal with incomplete information due to right-censoring, which arises when patients are lost to follow-up or enter the study at different times, resulting in varying durations of observation. This is particularly relevant in the registry data, where follow-up is frequently incomplete or irregular. While traditional survival analysis methods handle censoring by modeling the hazard function, …

Pathology’S Place In Understanding The Bias And Inequalities In Women’S Healthcare, Andrea Heaney, Eugene Hickey, Emma Murphy

SAML-25 Workshop on Statistical and Machine Learning

Women’s healthcare is a complex, multifaceted issue with both historic and implicit biases, along with biological differences between men and women. With the advancement of AI tools in healthcare and the potential for biased data to create biased models, it is vital to consider how women are represented in data. Previously conducted semi-structured semantic interviews with clinicians were analysed via Braun and Clark’s method of thematic analysis. The analysis of these interviews yielded the following themes: Gender Influencing Health, Pregnancy, Social Factors, General Health, Treatment, Training, and Research. These themes highlight that context is key to understanding the biases in …

Impact Of Spatial Diversity And Subject Variability On Wifi-Based Human Activity Recognition, Amany Elkelany, Robert J. Ross, Susan Mckeever

SAML-25 Workshop on Statistical and Machine Learning

In recent years, WiFi-based Human Activity Recognition (HAR) has gained substantial attention due to the ubiquity of WiFi infrastructure and advancements in wireless communication. Unlike camera-based systems that raise privacy concerns or wearable sensors that require user compliance, WiFi-based HAR provides a noninvasive and practical alternative that operates seamlessly with existing infrastructure. WiFi-based HAR leverages fluctuations in wireless signals, particularly Channel State Information (CSI), to passively detect and classify human activities. WiFi-based HAR models often achieve high accuracy in a single environment but suffer significant performance drops when applied to new environments due to variations in spatial settings, human movement, …

Optimising Ai For Chemical Imaging: Benchmarking Performance Against Foundation Models For Task-Specific Applications In Histopathology, Rahul Suresh, Mohd Rifqi Rafsanjani, Karin Jirstrom, Arman Rahman, William M. Gallagher, Aidan Meade

SAML-25 Workshop on Statistical and Machine Learning

The integration of chemical imaging with artificial intelligence presents a compelling route toward fully digital, label-free histopathology, yet it also introduces notable challenges. While deep learning models from domains like machine vision, digital pathology, and remote sensing are readily accessible, they frequently struggle to generalize effectively to chemical imaging data, as highlighted in recent research [1]. Additionally, although foundational pathological models show potential for advancing AI-based histopathological diagnostics and prognostics, our preliminary assessments suggest they may fall short in addressing the broad spectrum of classification tasks encountered in clinical settings. In this presentation, we highlight some recent published work from …

Transient Voltage Instability Identification Based On Koopman Operator In Power Grid With A High Proportion Of Renewables, Xiuqi Zhang, Hongqing Liu, Liqiang Wang, Yong Li, Han Gao

Journal of Electric Power Science and Technology

Transient voltage instability is one of the important factors that threaten the stability of power system. The dynamic reactive power reserve and supporting capacity of the power grid with a high proportion of renewables decrease sharply, and the control models and operation characteristics of grid-connected renewables are diverse. Thus, the reactive power voltage of the system often fluctuates rapidly after a fault occurs, which leads to a more prominent voltage stability problem. In response, a transient voltage instability identification method based on the Koopman operator is proposed in this paper to avoid power system outage accidents caused by voltage instability …

Relay Protection Setting Calculation Method For Power Grid Based On Spark, Chuang Song, Wei Han, Xingwei Du, Jingjun Wang

Journal of Electric Power Science and Technology

To adapt the grid to the requirements of intelligentization and the dispatching and control cloud technology route, this paper proposes a relay protection setting calculation method for power grid based on distributed parallel computing. First, the cluster architecture of the Spark distributed computing platform is introduced, and the key issues of distributed parallel computing, such as load balancing, system fault tolerance, etc. are analyzed. On this basis, a computing system for relay protection setting calculation based on Spark is designed. Secondly, the extra-high-voltage power grid setting calculation in the computing system is analyzed, and the principles of protection and setting …

A Novel Distance Protection Method For High‑Voltage Line In Substation With Integration Of Inverter‑Interfaced Distributed Generator, Zhengfei Lu, Minghao Wen, Yu Zhou, Longxing Jin, Shuai Ma

Journal of Electric Power Science and Technology

The strong variability, spatiotemporal randomness, and nonlinear controlled characteristics during faults of inverter-interfaced distributed generators (IIDGs) such as direct-drive wind turbines and photovoltaic generators pose significant challenges to the existing relay protection systems in power grids. When faults occur in high-voltage lines of substations with integration of IIDGs, the fault characteristics are more complex compared to those in the case of the access of traditional synchronous machine sources to high-voltage lines, which makes it difficult for conventional positive-sequence voltage-polarized phase-comparison distance protection to adapt to. As a result, the performance of protection for power grids deteriorates. This paper analyzes the …