Computer Sciences Commons^™

Machine Learning Research On Time Series Data, Zeyi Fan

Lingnan Theses (MPhil & PhD)

Time series generated by complex systems, such as industrial IoT and user behavior systems, confront two core challenges: structured missingness (e.g., continuous or periodic gaps) that disrupt temporal dependencies, and the difficulty in effectively modeling dynamic long- and short-term temporal dependencies inherent in evolving patterns (e.g., user interests). Traditional approaches struggle to balance the preservation of local dependency continuity and the rational association of global long-range dependencies in structured missing scenarios, often incurring high computational costs. In temporal pattern modeling, the lack of adaptive mechanisms to fuse evolving long- and recent behavior trends (e.g., stable interest inertia vs. short-term preference …

Educational Opportunities Of Participatory Gis For Accessibility On A College Campus, Shiya Cao, Heather Rosenfeld, Sarah Susnea

Statistical and Data Sciences: Faculty Publications

The educational benefits of Participatory GIS (PGIS) in geographic higher education have received limited direct attention, often because of the complexities of integrating PGIS into university curricula. While a few exceptions found important educational benefits of PGIS, extant studies focused primarily on the educational benefits for students who worked in the research teams, instead of participants who contributed their local knowledge and perspectives to mapping. Our research aims to understand the educational benefits of PGIS for participants in a campus accessibility mapping project using the modes of experiential learning, positionality, and service learning. Through this, we also provide strategies for …

Crop Yield Prediction At Multiple Spatial Scales With Statistical Machine Learning, Vaibhav Charan, Pratishtha Poudel

Discovery Undergraduate Interdisciplinary Research Internship

Understanding and accurately predicting crop yield is becoming increasingly important today in the face of global food security challenges, and thus, the availability of standardized data and scalable models is the need of the hour. To support this, researchers have developed CY-Bench (Crop Yield Benchmark), a comprehensive dataset that helps forecast maize and wheat yields on a global scale. This research project primarily involved working with the CY-Bench dataset aiming to improve crop yield prediction through machine learning. Initially, papers explaining the CY-Bench dataset and other papers for agriculture modeling were studied and analyzed in detail. The research then progressed …

Online Prediction Of Streaming Data, Aleena Chanda

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

We present two new approaches for point prediction with streaming data based on a) the Count-Min sketch and b) Gaussian Process Priors with random bias. The methods are intended for the most general case where no true model can be usefully formulated for the data stream. In statistical contexts, this is often called the M open problem class. For the Count Min Sketch method we show that the predicted distribution function ^F converges to F under the assumption that the data consists of i.i.d samples from a fixed distribution function F. To implement the Gaussian Process Prior methods, we used …

Rethinking Iterative Proportional Fitting: Scalable And Hybrid Approaches To Joint Distribution Fitting, William Ofosu Agyapong

Open Access Theses & Dissertations

The Iterative Proportional Fitting (IPF) algorithm is widely used in contingency table estimation, survey weighting, and synthetic population generation due to its simplicity and strong theoretical foundation for matching observed marginal distributions. However, in high-dimensional settings, IPF faces substantial computational and memory demands, as well as statistical instability caused by sparse contingency tables. Moreover, IPF is less useful in modern population synthesis tasks that require both scalability and realism because, despite its superiority in matching known marginal distributions, it cannot produce realistic out-of-sample data points. To address these limitations, we first propose a blockwise IPF framework, in which the feature …

Advancing Real-World Implementation Of The Well Optimized Linear Finder (Wolf) High-Speed Atmospheric Turbulence Compensation Method, Timothy Evan Coon

Theses and Dissertations

This dissertation advances the real-world implementation of the Well Optimized Linear Finder (WOLF) method for high-speed Atmospheric Turbulence Compensation (ATC). Atmospheric turbulence introduces phase aberrations into optical wavefronts and degrades image quality in terrestrial imaging systems. Traditional phase diversity methods are computationally intensive and poorly suited to real-time operation. The WOLF method addresses these limitations through a novel, point-wise formulation of the optical transfer function (OTF) as a structured autocorrelation of the generalized pupil function (GPF). This formulation enables the estimation of phase aberrations at individual spatial coordinates with distributed computational complexity.

The research begins by developing a MATLAB-based simulation …

Predicting Sleep And Sleep Stage In Children Using Actigraphy And Heartrate Via A Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation, Robert Weaver Med, Phd, James White, Olivia Finnegan, Hongpeng Yang, Zifei Zhong, Keagan Kiely, Catherine Jones, Yan Tong, Srihari Nelakuditi, Rahul Ghosal, David E. Brown, Russell R. Pate Ph.D., Gregory J. Welk, Massimiliano De Zambotti, Yuan Wang, Sarah Burkart, Elizabeth L. Adams Phd, Bridget Armstrong, Michael Beets Med, Mph, Phd

Faculty Publications

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years,52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred be-cause of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables(i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Exact Sampling Of The Six-Vertex Model Using Coupling From The Past, Malaeka Amir

DePaul Discoveries

This paper aims to explore the six-vertex model through simulations designed to investigate the behavior of configurations under specific domain wall boundary conditions. To generate random configurations, we employ the Markov Chain Monte Carlo method while addressing the challenge of mixing times by utilizing the Coupling from the Past (CFTP) algorithm. Implemented in Python, our approach leverages CFTP to ensure exact sampling, avoiding the uncertainty of convergence in traditional Monte Carlo methods. We explore the monotonicity property within this framework and prove that it is only maintained by the steps of this algorithm for very particular values of the parameters.

Syntax-Enhanced Boundary-Aware Named Entity Recognition Model, Chuanming Yu, Bin Deng, Zhengang Zhang

Journal of Scientific Information Research

[Purpose/significance] This study addresses the issue of inadequate perception of entity boundaries in traditional character-level modeling-based named entity recognition models by integrating syntax information containing entity boundary features into the task using a multi-head graph attention network with dense connections. This integration enhances the effectiveness of named entity recognition.

[Method/process] This study proposes a Syntax-enhanced Boundary-aware Named Entity Recognition Model (SynBNER), which utilizes BERT for text semantic representation and integrates syntax information using a dense-connected graph attention network. This integration incorporates implicit entity boundary information from syntax information into word representations, thereby enhancing the model's entity boundary perception capability.

[Result/conclusion] …

How’S It Growing? Tools For Observing Snow And Sea Ice In A Changing Arctic Ocean, Ian Alexander Raphael

Dartmouth College Ph.D Dissertations

September Arctic sea ice extent has diminished by roughly 50% in the 45 years since satellite observations began. The Arctic Ocean may experience ice-free summers within the next decade, with implications for habitat, resource extraction, geopolitics, and local and global climate change. To predict how Arctic sea ice will change in the future, we need to understand its behavior in the present. In situ sea ice mass balance measurements (snow accumulation, ice growth, snow and ice surface melt, and bottom melt) are essential for studying the processes driving rapid changes in the ice pack, and for validating remote sensing measurements …

A Comparative Study Of Neural Networks And Xgboost Models For Flight Time Prediction, Ioannis Paraschos, Taryn E. Trimble, Eshna Bhargava, Jake Klingler, Benjamin R. Nicolai

Beyond: Undergraduate Research Journal

Flight time prediction plays a crucial role in modern air travel, benefiting airlines and passengers alike. Accurate predictions enable airlines to optimize schedules, allocate resources effectively, and ensure passenger safety and satisfaction. In recent years, machine learning models, such as neural networks and XGBoost, have gained popularity for predicting flight times. This study aims to compare the performance of neural network and XGBoost models in predicting flight times, considering factors such as weather conditions, air traffic control, and aircraft performance. The results indicate that both models are effective, with XGBoost achieving slightly higher accuracy. However, neural networks offer advantages in …

Forecasting Influenza Rates Using Machine Learning: A Study Of Chatgpt's Predictive Accuracy, Sara Saleh

University Honors Theses

This study evaluates ChatGPT's ability to forecast influenza rates, such as the number of flu cases, hospitalizations, and death during peak season periods using CDC data, and comparing forecasts against actual results to calculate statistical accuracy and consistency. Influenza forecasting is essential for public health planning, but traditional methods may not always provide timely or accurate predictions. In this research study, ChatGPT was utilized to predict the influenza rates for the following week based on the previous week's data obtained from the FluView surveillance system. The predicted rates were compared to the actual influenza rates to assess the model's overall …

Opening The Black Box With Regal: A Novel Explainable Ai Approach To Uncover Key Predictors In Search And Rescue Success, Brandon Hyunjun Kim

Master's Theses

The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL …

Property Testing Ai: An Efficient Frontier, Paul Sopher Lintilhac

Dartmouth College Ph.D Dissertations

In this dissertation, we take a step towards addressing the major problem of a lack of standardized and rigorous approaches to testing and evaluation of AI systems. Taking inspiration from both the fields of Property Testing and Property Based Testing (for programs), we develop a novel taxonomy of partially overlapping classes of properties of AI systems, including simple properties, compound properties, higher order properties, data relation properties, and architecture-utility properties. We argue that this taxonomy categorizes a diverse set of AI traits -- including accuracy, fairness, robustness, monotonicity, point-wise and global privacy properties, sensitivity, and more -- according to the …

Topodino: Self-Supervised Topological Representation Learning For Neuronal Morphologies, Yasser Binbisher

Master's Theses

Neuronal cell types are categorized by transcriptomic identity, yet their morphological heterogeneity defies this classification. In response, researchers have adopted unsupervised graph representation learning as a tool to reveal morphological variation within single-class transcriptomic types. However, the complex geometry of neuronal morphology—especially long axons and dense dendrites—challenges graph neural networks, which struggle with message propagation across extended structures. To mitigate this, current approaches enforce sub-sampling on neuronal graphs and omit axons entirely, sacrificing critical biological features for computational efficiency. To overcome this trade-off, this thesis introduces TopoDINO, a self-supervised, topology-aware representation learning model designed to preserve the full hierarchical organization …

Mat 301 - Applied Statistics And Data Analysis, Eric Aragundi

Open Educational Resources

Data analysis using standard statistical methods and relevant computer software. Emphasis on real-world data, interpretation, and misinterpretation of computer output.

This syllabus contains open source notebook about data analysis content.

Hybrid Graph-Recurrent Architecture For Citation Recommendation Via Future Embedding Forecasting, Mohammad Ausaf Ali Haqqani

Computer Science and Engineering Theses and Dissertations

The rapid expansion of scientific literature has intensified the challenge of identifying relevant citations, particularly for newly published or under-cited papers. Traditional citation recommendation systems typically model static relationships or respond to past citation activity, offering limited predictive power for emerging works. In response, this thesis presents a temporal modeling framework for citation recommendation that anticipates future scholarly relevance by forecasting the latent representations of academic papers.

Building on prior work that utilized Temporal Graph Networks (TGNs) to model dynamic citation flows, we propose Graph-Time, a hybrid architecture that integrates a Graph Transformer with a GRU-based time series predictor. The …

Modeling Literary Connections: Exploring Transregional Resistance In Dalit Poetry, Antara Bhattacharyay

Mathematics, Statistics, and Computer Science Honors Projects

Structuring socio-political identities, the caste system (a graded form of hierarchy) remains entrenched in contemporary Indian society. Dalits, marginalized by the caste system, have expressed their resistance through literature, envisioning substantive equality and social change. In this thesis, I draw on digital humanities methods to examine regional variation in translated Dalit poetry from Bengali, Hindi/Urdu, Marathi, and Tamil languages. I utilize topic modeling—a machine learning algorithm that detects latent semantic structures in a text—as a point of departure for poetry analysis. I observe how topic modeling enables newer readings of the poems, revealing regionally resonant and broader Dalit themes.

Using Gaussian Process Regression To Learn Thermodynamic Equations Of State With Uncertainty Quantification, Austen T. Lee

Chemical Engineering Undergraduate Honors Theses

This study investigates the use of derivative-informed Gaussian Process (GP) models to estimate thermodynamic behavior across temperature and density by building a Helmholtz-based equation of state. Argon, a stable monatomic gas, was chosen as a case study within the vapor region. The GP model was trained using values of experimentally measurable properties found by taking first and second derivatives of the original potential function. Results show that while the GP model offered uncertainty quantification and informed thermodynamic behavior, it predicted values that deviated from the ground truth depending on the property. The model exhibited high confidence in regions with substantial …

Computer Vision In Soccer: Yolov11 Analytics Engine For Quantifying Game Strategy, Connor S. Maurer

Data Science Undergraduate Honors Theses

Single-shot object detection capabilities significantly reduce computational overhead for real-time computer vision in sports analytics at 60 FPS. YOLO11’s lightweight CNN gives promising accuracy while meeting the low-latency demand of dynamic soccer matches. As data-driven approaches take over the sport of soccer, efficient player tracking systems become critical for informing coach’s strategies. I prototype the ETL (Extract, Transform, Load) process of data collected from a single- shot detection program and evaluate its viability for estimating player fatigue. YOLO11 detects players, the ball, and other characteristics, with the output transformed by homography to estimate the positions in the real world. These …

Reinforcement Learning, Modeling Markets, And Professional Basketball Free Agency, Jacob Cohn

Computational and Data Sciences (PhD) Dissertations

This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.

Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study …

Multimodal Benchmarking For Ncaa Basketball, Brendan Barnett

Honors Scholar Theses

We present the first multimodal, multitask benchmark for NCAA basketball, synthesizing structured statistical features with large language model (LLM)-generated game summaries across 19,739 games spanning four NCAA Division I seasons (2021--2025). We evaluate three model families---XGBoost, deep neural networks, and Transformers---under tabular-only and early-fusion settings to measure the impact of LLM-derived textual embeddings. To assess practical utility, we simulate fixed-stake and Kelly criterion-based betting strategies using historical bookmaker odds, analyzing both profitability and downside risk via Monte Carlo simulation. Our results show that XGBoost with early-fusion achieves the highest return on investment and the lowest risk of loss. This work …

Investigating Students’ Proficiency Across Statistical Software And Preferences Of Statistical Software Design, Sabrina White

Honors College Theses

This paper investigated students’ perceptions of their proficiency with statistical software applications and their preferences regarding software features. Results indicated that students’ statistical and coding experience, as well as the specific application used, did not significantly influence their self-perceived proficiency. This suggests that it may be more effective to focus on building student skills within a chosen application, rather than tailoring the application to match existing student capabilities. While students showed clear preferences for certain features, favoring clarity over depth, flexibility over safeguards, and built-in checks over unrestricted freedom, these preferences generally leaned toward balanced design rather than extremes. This …

Maximal Independent Set Algorithms Within Procedural Planar Maps: A Large-Scale Evaluation, Chaucer Ihrig

Honors College Theses

Analysis of a childhood game has led us to the problem of maximum independent sets in planar graphs. We wrote a graph creation utility using R to generate a random planar map and its dual graph. This utility then finds a graph’s maximal independent set using a variety of six algorithms. We investigate statistical connections between graph structure, colorability, and the maximal independent sets found using these algorithms over an incredibly large and procedurally generated dataset. We find one can always win the coloring game if the resultant graph is two-colorable. The algorithms perform statistically and practically significantly better on …

Expressive And Interpretable User Engagement Prediction Using Multivariate Survival Processes, Akshay Aravamudan

Theses and Dissertations

The ability to characterize how information diffuses online is of paramount importance to stakeholders that are interested in tasks such as proposing solutions for mitigating and countering dis/misinformation, predicting user engagement of content in social media, planning marketing campaigns to roll-out products and planning dissemination of political campaign messaging among others. One such facet of learning the dynamics of information diffusion is the ability to predict user engagement or the popularity of a single piece of information as it spreads through an online medium. Existing works in this regard mainly either obfuscate user level information or utilize frameworks that are …

A System And Method For Measuring Spatially Varying Surface Appearances With A Study Of Feathers, Jessica Baron-Lis

All Dissertations

Real-world materials, particularly biological structures such as feathers exhibit complex appearances that vary spatially across their surfaces. The field of computer graphics provides a means of understanding such surfaces through material modeling which uses both analytical models and data acquired from light-surface interactions. There are many efforts within the past decade in measuring materials for graphics, but common limitations in these works include not accounting for spatially varying properties and reliance on neural networks and synthetic datasets.

Feathers from modern birds present diverse appearances due to how light interacts with their unique hierarchical microstructures. Variations in those structures lead to …

Analyzing The Sentiment Of Feminist And Non-Feminist Works, Jasmine Borie, Megan G. Falschlehner

Mathematics, Computer Science & Statistics Presentations

This presentation focuses on a group of texts that advocate for a change in the current belief system. These texts are the Feminist Manifesto, Sojourner Truth: Ain’t I a Woman?, and Civilization and Its Discontents. These first two texts advocate for women’s rights, while Freud’s book is focused on civilization’s decline and how our understanding of community can affect this. Through our presentation, we want to examine the differences in sentiment and language between the feminist texts and Freud’s texts to pinpoint whether or not sentiment changes when advocating for different beliefs.

A Text Mining And Sentiment Analysis Of Valuable Cie Texts Using R, Eric Sugarman, Ethan Turber-Ortiz, Hannah Quinn

Mathematics, Computer Science & Statistics Presentations

The purpose of this project was to perform a sentiment analysis of three texts used in Ursinus College's Common Intellectual Experience (CIE) course: Between the World and Me by Ta-Nehisi Coates, The New Jim Crow by Michelle Alexander and Discourse on Method by Rene Descartes. Word count and word cloud analysis were also performed on the texts as well as term frequency and bigram analysis.

Leveraging Benford’S Law And Machine Learning For Financial Fraud Detection, Benjamin R. Fu

Cybersecurity Undergraduate Research Showcase

Financial fraud, particularly credit card fraud, continues to pose substantial challenges to financial institutions due to its increasing frequency and impact on consumer trust. While traditional rule-based methods have provided foundational defenses, their limitations in scalability and adaptability have accelerated the adoption of machine learning (ML) techniques. Concurrently, Benford’s Law—a statistical principle often used in forensic accounting—has demonstrated efficacy in detecting anomalies within naturally occurring numerical datasets. This study explores a hybrid fraud detection approach that integrates Benford’s Law with supervised machine learning algorithms, including Logistic Regression, Random Forest, and k-Nearest Neighbors. Using the publicly available European credit card fraud …

A Machine-Learning Tool-Supported Methodology For Nonprofit Donor Analysis, Corbin Weiss

Campus Research Month

We developed a machine-learning tool-supported methodology for modeling the nonprofit donor relationship. This approach was demonstrated in the case of a US-based nonprofit. Conclusions were drawn from this example and tool-support provided for use by other nonprofits.