Digital Commons Network^™

Balancing Accuracy And Discovery: A Bias-Aware Evaluation Framework For Music Recommendation, Jose Luis Maidana

ICT

Music recommender systems play an important role in helping users navigate large catalogues, but their reliance on historical interaction data can reinforce popularity bias and limit the visibility of less popular, long-tail items. This research develops and evaluates a bias-aware framework for assessing and mitigating popularity bias in music recommendation using implicit user-item interaction data. The study first quantifies popularity bias through inequality and long-tail metrics, before evaluating two baseline recommender approaches: a non-personalised Most-Popular model and a personalised Matrix Factorisation model. Their performance is assessed using both predictive accuracy measures, including Precision, Recall and NDCG, and beyond-accuracy measures relating …

Comparative Economic Impact Modelling Of Floods Vs Drought On A Global Scale, Diogo Lemos Aguiar, Paulo Henrique Oliveira Machado

ICT

Climate change is generating unprecedented economic losses through extreme weather events, yet comparative predictive analysis between different hazard types remains limited. This report presents a Machine Learning–Based Comparative Economic Impact Modelling System designed to predict and compare the economic damages caused by floods and droughts on a global scale. The system integrates historical disaster records from the EM-DAT International Disaster Database with country-level socioeconomic indicators from the World Bank's World Development Indicators, applying supervised regression modelling to a unified dataset of 1,301 disaster events across 133 countries from 2000 to 2025. XGBoost and a Multi-Layer Perceptron Neural Network were evaluated …

The Sub-Lethal Effects Of Trematode Parasites On The Migratory Behavior Of Lesser Scaup (Aythya Affinis), Scott Alan Herman

Graduate Research Theses & Dissertations

The introduction of the invasive freshwater faucet snail (Bithynia tentaculata) and its associated parasites in the Upper Mississippi River and Great Lakes Region provides the opportunity to investigate how anthropogenic stressors impact the life history of lesser scaup (Aythya affinis) using the Mississippi Flyway. To understand the life histories and interactions between lesser scaup and faucet snails we examined historical records, research, and ecology textbooks. Our literature review identified critical knowledge gaps in lesser scaup literature surrounding population dynamics, reproduction, and migration. Specifically, the sub-lethal effects of invasive trematodes on the migratory behavior of lesser scaup in the Upper Mississippi …

Artificial Elections: How Artificial Intelligence Can Affect Elections And Decide Our Future, Ryan D. Granger

Honors Undergraduate Theses

This thesis examines the growing role of artificial intelligence (AI) in democratic elections, highlighting both its transformative potential and its associated risks. Drawing on a qualitative analysis of existing literature, the study explores how AI is increasingly integrated into political campaigns, election administration, and voter engagement. Key benefits include enhanced data analysis, personalized political messaging, and improved efficiency in campaign operations. AI also supports real-time fact-checking and more accurate vote tabulation, which can strengthen transparency and trust in electoral processes. However, the thesis emphasizes that these advantages are accompanied by significant challenges. AI technologies enable the rapid creation and dissemination …

A Conceptual Framework For Cognitive Engagement And Human Agency In Ai-Mediated Learning, Sam Rhodes, Zuhal Yilmaz, Terrie Galanti, Younggon Bae, Victoria Delaney, Zareen Gul Aga, Stephen Hutt

School of Mathematical & Statistical Sciences Faculty Publications

The purpose of this chapter is to propose a conceptual framework that unpacks AI use in instructional practice across three interrelated dimensions: human agency, cognitive demand, and AI orchestration. We ground this work in historical perspectives on technology's mediating role in education. We then propose the conceptual framework and three characterizations of the use of AI in school instruction: cognitive load reducer, cognitive capacity builder, and cognitive companion. We then illustrate a worked example of each, including a curricular example and sample student prompts, and conclude with questions that educators might ask themselves as they consider if and how to …

Workshop Outcomes Report: 2nd International Workshop On Seismic Resilience Of Arctic Infrastructure And Social Systems, Majid Ghayoomi, Daniela Morganti

Faculty Publications

The report provides an overview of the second international workshop on Seismic Resilience of Arctic Infrastructure and Social Systems. The report discusses agenda, workshop activities, interdisciplinary working groups, and results. It ends with several strategic questions and investigation plans that were developed as part of the workshop activities.

Multi-Timescale Monitoring And Modeling For Resilient Smart Grids: Pmu Anomaly Detection And Battery Digital Twins, Muhammad Imran Hossain

Graduate Theses, Dissertations, and Problem Reports (ETD)

Modern power systems face failures at very different timescales. Cyber-physical disturbances may emerge within seconds, while battery degradation develops over hundreds of operating cycles. Both monitoring problems share the same underlying difficulty: power systems produce measurement data in abundance, but reliably labeled examples of abnormal or degraded operation are scarce. Rare grid events are difficult to label, and battery degradation data are heterogeneous across cells, cycling protocols, and chemistries. This thesis addresses these challenges through two complementary domain-informed learning frameworks that constrain representation learning using information specific to each physical problem.

First, at the system level, T-BiGAN, a Transformer-augmented bidirectional …

Dataless Neural Networks For Boolean Satisfiability And Network Optimization, Andrew Evan Gautier

Graduate Theses, Dissertations, and Problem Reports (ETD)

Combinatorial optimization problems (COPs) require searching over a finite solution space subject to constraints, with the goal of satisfying an objective function. They arise in operations research, scheduling, resource allocation, circuit design, and many other fields. Many problems in combinatorial optimization (including satisfiability and network design) are NP-hard. Traditionally, researchers have built approximate solvers that return near- optimal solutions efficiently by developing increasingly sophisticated heuristics and meta- heuristics. Deep learning has provided new opportunities for improving combinatorial solvers by leveraging neural guidance to prune the search space. Traditional neural networks have distinct drawbacks in this context: separate training and …

Multimodal Representation Learning For Face Understanding: From Caption Supervision To Foundation Model Adaptation, Md Mahedi Hasan

Graduate Theses, Dissertations, and Problem Reports (ETD)

The rapid advancement of intelligent surveillance systems and the increasing demand for reliable biometric identification in border security, public safety, and digital forensics require robust face understanding under unconstrained conditions, including low resolution, pose variation, and occlusion. While Vision Transformer (ViT)-based foundation models have greatly improved visual representation learning, their patch-based tokenization and lack of spatial inductive bias limit their ability to capture fine-grained details in low-resolution inputs. This dissertation investigates multimodal representation learning for face understanding through natural language supervision, large-scale face-caption pre-training, and parameter-efficient foundation model adaptation. It hypothesizes that textual supervision provides complementary semantic cues that improve …

Dielectrophoretic Biomarkers For Cancer Detection And Cell Analysis: Integrating Microfluidics And Ai, Raphael Olumide Oladokun

Graduate Theses, Dissertations, and Problem Reports (ETD)

Pancreatic ductal adenocarcinoma (PDAC) carries a five-year survival rate of 13%, driven largely by late-stage diagnosis and the absence of sensitive noninvasive screening tools. Current diagnostic methods lack the sensitivity to detect disease-associated systemic changes at early and precancerous stages, representing a critical clinical gap. This dissertation addresses the central hypothesis that PDAC and its pathological subtypes induce measurable, disease-associated electrophysiological changes in circulating PBMCs that can serve as correlative liquid-biopsy biomarkers. To test this hypothesis, this work asks: can dielectrophoresis (DEP), impedance and zeta potential analysis with AI-assisted classification distinguish benign pancreatic conditions (non-malignant control), precancerous lesions (primarily IPMNs), …

Energy Partition And Heating Mechanisms In Asymmetric Antiparallel Magnetic Reconnection, Aleksandra Abova-Volkova

Graduate Theses, Dissertations, and Problem Reports (ETD)

Magnetic reconnection is a fundamental plasma physics process whereby a change in magnetic field connectivity drives the conversion of magnetic energy into energy of the surrounding plasma, often explosively. One of the many settings where it occurs is at the dayside magnetopause of Earth and other planets, where the magnetic field, number density, and/or temperature in the plasmas on the two sides upstream of the reconnection site are asymmetric. How the incoming magnetic energy gets partitioned into outgoing energies during asymmetric reconnection remains an outstanding question; of special interest is the fraction that gets converted into internal energy of ions …

A Digital Calibration Source For 21 Cm Cosmology Telescopes, Kalyani Balkrishna Bhopi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Precise calibration of radio telescope beams and gains is a central requirement for 21 cm intensity mapping experiments, which aim to measure large scale cosmological structure through the redshifted emission line of neutral hydrogen. Bright astrophysical foregrounds dominate the sky at these frequencies, and separating them from the cosmological signal demands precise control over instrumental systematics, particularly the telescope beam and its frequency-dependent response. Existing aerial calibration sources are incoherent broadband emitters, detectable only as total power. They provide no direct phase information and suffer from poor sensitivity in low signal-to-noise regimes.

We present the Precision Emitter for 21cm Array …

New Fossil Mygalomorph Spiders (?Idiopidae, Pycnothelidae) From The Lower Cretaceous Crato Formation Of Brazil, Elis Maria Gomes Santana

Graduate Theses, Dissertations, and Problem Reports (ETD)

The infraorder Mygalomorphae represents one of the earliest-diverging lineages of spiders, but its fossil record remains sparse relative to the modern diversity of the group. This is a reflection of both ecological and preservational biases, such as the predominantly fossorial habits of many mygalomorphs and the strong bias of the spider fossil record toward amber deposits. Compression fossils from rock deposits are therefore especially important for documenting the evolutionary history of the group. Here, two new mygalomorph fossils from the Lower Cretaceous Crato Formation, Araripe Basin (Brazil) are described. The first specimen is tentatively referred to ?Idiopidae based on male …

Student Conceptions Of Summation And Limits In The Definite Integral Following Quantitatively Focused Instruction, Caleb Daniel Holloway

2026 Scholarly Teaching Conference: Concurrent Session Papers

Recent studies have examined how students form productive conceptions of the definite integral and discussed techniques for promoting such conceptions. In this paper I present findings from interviews held with six students enrolled in second-semester calculus, four of whom had received quantitatively focused instruction on the definite integral. All six were chosen for their observed use of summation conceptions on definite integral problems, and here their conceptions are explored further. Additionally, we gain insight on their thinking regarding limits as related to the definite integral. The findings presented here add to our understanding of student thinking regarding the integral and …

Techniques For Inclusive College Mathematics Classrooms, Christopher Anderson Davis, Josh Hiller, Anil Venkatesh

Journal of Mathematics and Science: Collaborative Explorations

Creating a welcoming and inclusive mathematics classroom is an important responsibility for all college mathematics faculty. But where do we begin? In this paper we present several techniques based on White’s (2024) building inclusive classrooms strategies framework, which the authors have found to be successful in making their own classrooms more inclusive. The techniques include the inclusion of contemporary diverse voices, exploring the history of applications of mathematical concepts, elevating the diverse intellectual history of mathematics, bringing diverse guest speakers into the classroom, and mentoring students as they engage in doing research. For each strategy we provide narrative comments based …

Challenges And Applications Of Fine-Grained Temporal Action Understanding: Modeling Temporal Granularity And Data Efficiency, Halil I. Helvaci

Theses and Dissertations--Electrical and Computer Engineering

Fine-grained Temporal Action Segmentation (TAS) has become a cornerstone of video understanding, offering dense frame-level predictions essential for clinical assessment, surgical skill evaluation, and human-computer interaction. While TAS methods have delivered strong results on coarse-grained benchmarks, two fundamental challenges persist: (1) global attention mechanisms dilute boundary information critical for subsecond precision, a phenomenon we term the temporal granularity bottleneck, and (2) dense frame-level annotation remains prohibitively expensive, with most datasets requiring exhaustive labeling of lengthy untrimmed videos. These challenges are particularly pronounced in medical domains, where sub-second primitives define clinical outcomes while expert annotation remains scarce. In this dissertation, we …

Improving Pid Control With Bayesian Optimization For Adversarially Robust Federated Learning, Adrian Pena, Sergei Chuprov, Raman Zatsarenko, Leon Reznik

Computer Science Faculty Publications

Federated Learning (FL) often suffers from unstable convergence and reduced robustness under non-IID data and malicious attacks. In this paper, we present FedPIDAvg_tuned, a control-theoretic aggregation framework for improving stability and adversarial robustness in FL. In particular, our approach combines a server-side Proportional–Integral–Derivative (PID) controller with Bayesian optimization to tune controller gains for different data and attack conditions. The PID controller regulates global model updates through feedback on loss dynamics, providing adaptive scaling that improves stability and convergence. The tuned gains are applied within a trust-weighted trimmed-mean mechanism to remove adversarial or outlier updates. Using the Flower framework, we evaluate …

Redefining Educational Technology: A Critical Collaborative Inquiry, Aras Bozkurt, Helen Crompton, Robert Farrow, Agnes Kukulska-Hulme, Jon Dron, Richard West, Agnieszka (Aga) Palalas, Matth Bower, Junhong Xiao, Ahmed Tlili, Danah Henriksen, Angelica Pazurek, Henk Huijser, Thomas K. F. Chiu, Petar Jandrić, Katy Jordan, John Curry, Royce Kimmons, Mutlu Cukurova, Thomas Reeves, Gwo-Jen Hwang, Peter Shea, Jason Lodge, Martin Weller, Davy Ng, Tutaleni Iita Asino

STEMPS Faculty Publications

Educational technologists have not settled on a fixed definition of the field and likely never will. However, attempting to define the field helps to understand the epistemological meanings that shape what the field sees, values, and considers worth pursuing. Through a critical historical review spanning over a century, alongside theoretical engagement with the concepts of entanglement and distributed agency, this paper identifies three key insufficiencies in current educational technology frameworks. These are the persistence of an instrumental-facilitative paradigm that treats technology as a resource deployed by human agents; the theoretical dissolution of the pedagogy-technology dichotomy that existing definitions have not …

Multimodal Emotion Detection System, Shubhankar Sameer Munshi

Master's Projects

Trying to understand emotion from speech is a problem that is present in human computer interaction. Nevertheless, there are still some shortcomings in current SER methods. Text-based systems may miss vital vocal cues, such as sarcasm, tone changes, and delivery. On the other hand, purely audio-based systems are prone to noise and unstable acoustic features. The combination of linguistic and acoustic features in multimodal approaches partially solves this problem, but many existing approaches use inflexible multimodal fusion techniques that cannot adjust their behaviors according to the quality of input signals. In this work, we propose a multimodal approach based on …

Ordo Ab Chao: Crystallographic Disorder As A Window Into Ionic Liquid Structure, Joseph Cooper, Marija Scheuren, Lara I. Teodoro, Christopher M. Butch, Raychell A. Jerdo, Kylie M. Allen, Mariana E. Toner, Matthias Zeller, Arsalan Mirjafari, Patrick C. Hillesheim

Faculty Publications – Chemistry

Despite being intended to resist crystallization, ionic liquids (ILs) quite frequently form solids, albeit with low melting points. The design motifs that lower melting points can leave measurable signatures in the solid state, manifesting as crystallographic disorder, and often give rise to metastable liquid states. While sometimes treated as experimental complications, such features provide a valuable window into the structural origins of IL phase behavior. Herein, we report a crystallographic study of a series of benzylated ILs that crystallize either directly or from long-lived supercooled melts. Single-crystal X-ray diffraction, supported by computational modeling and statistical analyses, provides structural evidence that …

Cogram: A Computational Pipeline For Genome Assembly And Reconstruction Using Graph Neural Networks, William Coggins

College of Graduate Studies: Theses & Dissertations

Genome assembly — the reconstruction of a complete DNA sequence from short, overlapping reads — remains a fundamental challenge in computational biology. A central difficulty is distinguishing true genomic overlaps from spurious connections arising from repetitive sequences, a task that traditional assemblers address through hand-tuned heuristic rules applied to de Bruijn or overlap graphs. This thesis introduces COGRAM (Coggins–Ramasamy Assembly Method), a genome assembly pipeline that reframes sequence reconstruction as an edge classification task on a k-mer overlap graph, replacing heuristic graph cleaning with a learned model.

COGRAM constructs a directed overlap graph from raw sequencing reads using a k-mer …

Examining The Spatial Variability Of Summer Heat In New York City Using Landsat Land Surface Temperature, Ryan Kabir

Dissertations and Theses

Extreme heat is the leading weather-related cause of death in the United States, and in New York City (NYC) approximately 370 heat-related deaths occur annually on average. The spatial distribution of surface heat exposure across NYC is highly uneven, low-income neighborhoods and communities of color consistently face higher temperatures, yet the intraurban spatial structure of land surface temperature (LST) during heatwave events has not been systematically characterized at high resolution. The New York City Panel on Climate Change Fourth Assessment (NPCC4) identifies this as an explicit research gap, noting that its own projections, based on global climate models downscaled to …

Optimizing Markov Chain Monte Carlo Algorithms For Fairness, Scalability, And Interpretability In Electoral Redistricting, Madhukara Kekulandara

Open Access Dissertations

Gerrymandering undermines democratic representation by manipulating electoral district boundaries to dilute the political influence of targeted communities. While Markov Chain Monte Carlo (MCMC) based redistricting algorithms have become a standard computational tool for detecting partisan gerrymandering, their effectiveness in addressing racial gerrymandering and their scalability on modern computing systems remain limited. This dissertation advances the theory and practice of algorithmic redistricting by optimizing MCMC-based approaches across three dimensions: racial fairness, computational efficiency, and interpretability.

First, this work introduces the Partial Map MCMC algorithm, a novel redistricting method designed specifically to address racial gerrymandering under the legal framework of Section 2 …

Machine Learning-Based Intrusion Detection System For Iot Networks Using The Rt-Iot 2022 Dataset, Bukunmi Ebenezer Afolabi

Theses, Dissertations and Capstones

The rapid expansion of the Internet of Things (IoT) has transformed modern computing by enabling seamless connectivity among heterogeneous devices across diverse application domains. However, this increased interconnectivity has significantly enlarged the attack surface of IoT networks, exposing them to a wide range of sophisticated cyber threats. Conventional security mechanisms often lack the capability to detect emerging attacks in real time, thereby necessitating the development of intelligent Intrusion Detection Systems (IDS) capable of accurately identifying malicious network activities. This study developed and evaluated a machine learning-based intrusion detection framework for multiclass IoT attack detection using the RT-IoT2022 dataset. The dataset …

Critical Success Factors For An Effective Security Risk Management Program: An Exploratory Case Study, Jason A. Williams, Humayun Zafar, Saurabh Gupta

Faculty Articles

This paper evaluates the perceived effectiveness of the security risk management (SRM) programs at a Fortune 500 firm. Layers of management and staff participated in the study. Perceived effectiveness of their SRM programs was based on nine critical success factors (CSFs). Interviews confirmed six initial CSFs (Executive Management Support, Organizational Maturity, Open Communication, Risk Management Stakeholders, Team Member Empowerment, and Holistic View of an Organization) that were extracted from the literature. They were confirmed and synthesized with three additional CSFs (Security Maintenance, Corporate Security Strategy, and Human Resource Development). Implications for SRM are discussed.

Student Familiarity With The Periodic Table Of The Elements: Results From Cued-Recall And Eye-Tracking Assessments On Memory, Victor A. Okuo

Theses and Dissertations--Chemistry

Learning element symbol–name associations and the spatial organization of elements on the periodic table is a foundational step in learning chemistry, supporting later understanding of chemical formulas, equations, bonding, and stoichiometry. Although students often rely on memorization strategies to learn periodic table content, this task is challenging due to the large number of elements and the apparent ambiguity in matching some element symbols to their names.

This study explores students’ recall of element names when given element symbols as cues and their knowledge of element locations on the periodic table when given element names as cues. The study also examines …

Application Of Paper Spray Mass Spectrometry For Screening Acetylcholinesterase Inhibitors, Diksha Gautam

Graduate Research Theses & Dissertations

Paper spray mass spectrometry (PS-MS) is a novel ambient ionization method that allows chemical and biological samples to be rapidly analyzed with little preparation being required. In this paper, PS-MS was set up and streamlined as an acetylcholinesterase (AChE)-monitoring platform in addition to screening an existing and newly produced AChE-inhibitors. The detection of the substrate, acetylcholine (m/z 146), and the AChE catalysis product, choline (m/z 104) was performed without applying chromatographic separation or derivatization to the dried paper substrates. Assay conditions were optimized in a systematic way, to develop a robust MS-compatible enzymatic workflow.

Calibration curves for both, acetylcholine and …

Rntuple For Atlas Analysis Workflow, Fatima Ariana Rodriguez

Graduate Research Theses & Dissertations

RNTuple is the new data storage format set to replace TTree at the start of the High-Luminosity LHC. An investigation was conducted to evaluate how analysis workflows for ATLAS researchers will change with RNTuple, using reading speed, writing speed, disk space, and memory consumption as metrics. In this study, all metrics were measured using converted RNTuple inputs from ATLAS Open Data, compared to their TTree equivalents. Additionally, RNTuples produced with the LZ4 compression algorithm were generated and compared with those produced using ZSTD. Finally, two new versions of the Analysis Grand Challenge (AGC) using ATLAS Open Data were completed for …

Quantum Mechanics As A Framework For Data Assimilation And Its Application To Atmospheric Parameterization, David Freeman

Dartmouth College Ph.D Dissertations

Quantum mechanics, as a mathematical system, can be understood as a generalization of classical probability theory. Quantum Mechanical Data Assimilation (QMDA) is a method in which classical dynamical systems are embedded into a quantum mechanical setting, with an associated data assimilation scheme leveraging the operator algebraic setting. In this dissertation, the algebraic structure underlying the operator theoretic formulation of QMDA is discussed. A procedure for closure of dynamical systems based on QMDA, known as Quantum Mechanical Closure (QMCl), is then constructed, and the procedures for constructing the quantum embeddings and implementing QMCl in practice are laid out and implemented for …

Attribution Post ‘Aura’ Loss: A Qualitative Discourse Analysis Of The Nigerian Scam Label And Fraud Attribution, Emaediong Akpan

International Journal of Cybersecurity Intelligence & Cybercrime

In this essay, I employ qualitative discourse analysis of eleven purposively selected literature to examine how “Nigerian scam” became an established yet detached signifier of advance-fee fraud in global discourse. I do not treat this association as a reflection of offender identity or national inclination. Instead, the analysis traces how attribution is produced through representational repetition, institu tional uptake, and the circulation of familiar narrative cues. Using qualitative discourse analysis and an interpretive approach, this paper distinguishes among the socio-technical conditions that enable fraud, the institutional processes that stabilize attribution, and the semiotic dynamics through which national categories acquire durability. …