Computer Sciences Commons^™

Adaptive Spectral Trust Gate For Physics- Constrained Operator Learning, Soham Chakraborty

Master’s Dissertations

Physics-informed machine learning improves the plausibility, data-efficiency and generalization of surrogate models by injecting prior physical knowledge into the learning process. The current approaches can be broadly divided into two main categories: soft constraints, which add a physics residual to the training loss but guarantee nothing at inference time, and hard constraints, which project the model output onto the constraint set exactly but apply the projection uniformly to every part of the signal — including parts that are dominated by noise, discretization error, or model mismatch, where the idealized physics is not actually trustworthy. This dissertation proposes the Adaptive Spectral …

Deep Reinforcement Learning With Directed Asymmetry And Kolmogorov-Arnold Networks For Dismantling Interdependent Multiplex Networks, Soumyajit Dev

Master’s Dissertations

Identifying the minimum-cost node-removal sequence that fragments a complex network - the network dismantling problem is NP-hard and central to infrastructure resilience. In interdependent multiplex networks, this difficulty is compounded by cascading cross-layer failures. While deep reinforcement learning (DRL) agents utilizing graph neural network (GNN) encoders achieve near-optimal dismantling, current state-of-the-art architectures suffer from two critical limitations. Topologically, existing agents strictly assume undirected edges, rendering them inapplicable to directed systems - such as supply chains or gene regulatory cascades - where failure propagation is fundamentally asymmetric. To resolve this, we propose Disassembling Directed Interdependent Networks (DDIN). DDIN introduces an asymmetric …

Load Profile Analysis And Forecasting For Rural Mini Grids In Uganda, Prossy Mutesi, Santos L. Kihwele, Emmanuel S. Matee

Tanzania Journal of Science

Accurate load forecasting is essential for the reliable and cost-effective operation of rural mini grids, where constrained generation capacity and high penetration of renewable energy resources require well-informed operational decisions. This study examines electricity demand characteristics and forecasting performance for the Buzaami and Ssenyondo mini grids in Uganda, with particular focus on diurnal load profiles, peak demand behavior, and seasonal variability. 2022 operational data show extended peak demand from early morning to late evening, driven by socio-economic activities that strain resource scheduling and reliability management. To address these challenges, the study evaluates and compares Long Short-Term Memory (LSTM) networks, fuzzy …

Robust Real-Time Uav Target Tracking With Onboard Vision-Based Yaw Control, Rylan Malarchick, Jose Castelblanco, Enrique Amaya, Carmen Dimario, Graysen Brinkman, Chirag Kumar, Kiwon Yoon, Sajid Berhane

Beyond: Undergraduate Research Journal

Autonomous tracking of agile unmanned aerial vehicles (UAVs) presents significant challenges for real-time perception and control systems. This work presents AIRHOUND (Autonomous Intelligent Rotorcraft for Hostile Object Unified Navigation and Detection), a UAV platform implementing vision-based yaw tracking through a modular ROS2 software architecture. The system employs YOLOv8 object detection optimized with NVIDIA TensorRT for embedded deployment on an NVIDIA Jetson Orin companion computer. Detected targets are processed through a geometric tracking module that converts pixel coordinates to angular yaw errors using pinhole camera intrinsics, with a proportional controller generating rate-limited yaw commands. These commands are streamed to a PX4 …

Spectral Unmixing Using Machine Learning, Debashis Dhar

Master’s Dissertations

Spectral Unmixing is an important field of study nowadays which focuses on gener ating fractional abundance of each pixel into constituent materials .In this thesis we have tried to unmix each pixel into three end members namely glacial lake,debris and others with primarily focusing on glacial lake.We have performed various meth ods of linear spectral unmixing and non linear spectral unmixing. These methods are applied on the collected LandSat Data of east Himalayan terrain .Experimental results demonstrate the effectiveness of the proposed approach in achieving high accuracy and efficiency in glacier lake tracking on LandSat data.

A Switch-Point-Aware Contrastive Approach To Sentiment Analysis Of Hinglish Code-Mixed Text, Prasant Kumar Sahoo

Master’s Dissertations

With the increasing use of social media in non-English-speaking regions, especially in India, people often use Romanized Hindi and English together in their online communication. In a single sentence, they frequently mix Romanized Hindi and English, creating code-mixed text. However, most multilingual transformer models are pre-trained primarily on monolingual data. As a result, NLP systems face challenges when processing code-mixed text, as a single word may be fragmented into meaningless subword pieces, making it difficult for the model to capture its semantic meaning accurately. In this dissertation, we propose a parameter efficient neural architecture consisting of three main components to …

Synthetic-Chicken-Fillets, Chirantan Sen Mukherjee, Seung-Chul Yoon, William J. Beksi

Agriculture

This Synthetic-Chicken-Fillets dataset contains 1,000 synthetic 3D meshes designed to capture the natural variance and size diversity of real broiler fillets. The collection was developed to test automated woody breast detection algorithms within a physics-based simulation environment. We utilized a seed dataset of 2D depth maps derived from 40 real-world RGBD point cloud scans. These real depth maps were fed into a few-shot transfer learning pipeline using a generative adversarial network architecture. The resulting generated depth maps were reconstructed back into 3D meshes. The length and thickness of each mesh were randomly scaled based on physical measurements of real broiler …

Extending Unibreak: Semantic Retrieval And Harmful-Intent Direction Suppression For Token-Level Llm Jailbreaking, Sanket Saha

Master’s Dissertations

Token-level adversarial perturbations remain one of the most efficient known attacks against the safety alignment of instruction-tuned large language models (LLMs). Among recent works, the UniBreak framework (You et al., 2026) stands out for unifying gradient-based optimization with an evolutionary perturbation repository. However, its repository relies solely on accumulated success frequency without utilizing query content, and its fitness function implicitly assumes that suppressing refusal tokens is sufficient to elicit harmful responses. In this dissertation, we extend UniBreak along both axes and re-evaluates the framework under stricter generalization and judgment protocols. Specifically, we introduce a semantic perturbation repository that replaces frequency-only …

Simultaneous Tumor Delineation And Report Generation From Brain Mr Images, Adish Mallik

Master’s Dissertations

Brain tumor analysis is an important application of medical image computing, where accurate segmentation and interpretation of tumor regions can support diagnosis and treatment planning. However, existing methods often address tumor segmentation and radiology report generation as separate tasks. Moreover, one of the major challenges in report generation tasks from MRI is accurate tumor localization. Most models fail to locate the lobe and hemisphere in which the tumor is located, causing incorrect report generation. In this regard, a unified 3D vision-language framework is proposed for simultaneous brain tumor segmentation and report generation from multi-modal MRI. Given T1, T2, T1C, and …

Automatic Glossing In Under-Resourced Languages: Case Studies In Bribri And Cook Islands Māori, Carter D. Anderson

Linguistics Undergraduate Senior Theses

Interlinear glossing is a major task in Indigenous language documentation. In this paper, I explore how effectively two Large Language Models, ByT5 and Gemini 2.5 Flash, can produce interlinear glossed text. I also examine how prompting an LLM with different types of information (dictionary entries, other training samples, and translations) can augment model performance. I apply these models to two under-resourced Indigenous languages: Bribri, which is morphologically complex from Costa Rica, and Cook Islands Māori, which has a simpler morphology and is from the Cook Islands in the Pacific Ocean. ByT5 exhibits much better performance when glossing Cook Islands Māori …

Custom Sbc Gps Tracking And Geocaching Carputer Software Development And Implementation, Joshua A. Davis

University Honors Theses

This thesis argues that hardware-integrated capstone projects develop software engineering skills that traditional coursework cannot replicate. A team of eight developers built a GPS tracking system on a Raspberry Pi 4 over two academic terms, integrating real-time position streaming, the APRS amateur radio protocol for network-independent location sharing, and PostGIS spatial queries for "new road" detection. The system implements SmartBeaconing for adaptive GPS data reduction, achieving approximately 80% storage savings while preserving route fidelity. The project exposed challenges absent from classroom assignments: hardware debugging without stack traces, cross-layer integration failures, and coordination overhead when deploying to unfamiliar architecture; demonstrating that …

Beyond The Best Prompt: A Coverage View Of Multilingual Reasoning, Harshiv Mistry

University Honors Theses

Multilingual LLMs reason more accurately in English than in other languages, and recent work links part of this gap to reasoning behavior: native-language traces contain fewer cognitive behaviors (verification, backtracking, subgoal setting, backward chaining) that support effective problem solving. We test whether prompting for these behaviors at inference time narrows the gap, across seven conditions varying chain-of-thought, instruction and reasoning language, and cognitive-behavior descriptions, on two models, three languages. We find that English-scaffolded reasoning is the strongest single strategy on both models, closing the Hindi gap on Qwen, though the explicit scaffold's value over plain chain-of-thought is model-dependent. Beyond aggregate …

Digital Bodily Autonomy: Consent Issues, Labor Displacement, And Legal Understandings Of Ai Generated Deepfake Pornography, Mariah Barrett

Undergraduate Theses, Capstones, and Recitals

In the United States, nonconsensual pornographic deepfakes are becoming an increasingly prevalent problem as AI deepfake creation software improves and becomes widely available. Despite this, patchwork legislation across the country is inconsistent and conflicting regarding this issue. In this paper, I explore the background of pornography and obscenity laws and demonstrate how these frameworks are not properly constructed to apply to the digital sphere. Then, I address major themes within deepfake literature such as consent issues, bodily autonomy, labor displacement, and verifiable identity as a commodity through the case study of OnlyFans. I explore current and proposed legislation within the …

A Novel, Embedding-Based Approach To Longitudinal Survey Data Imputation, Julia Rezvani

University Honors Theses

Longitudinal surveys are ubiquitous in the social sciences as a means of tracking changes in behavior and opinions with time and identifying potential causal mechanisms. These surveys are frequently plagued by missing data and semantic drift, both of which limit their effectiveness and scientific utility. Imputation algorithms allow researchers to fill gaps in collected survey datasets, imperfectly reconstructing lost data. Although deep learning algorithms have been used in imputation to great success, approaches which simultaneously leverage the semantic and temporal structure of longitudinal surveys have not yet been developed. We propose a novel imputation architecture which is capable of leveraging …

Geospatial Governance Failures In The Department Of Defense: Contractor Noncompliance, Ai Adoption, And The Parallel Treatment Of Gis And Cybersecurity, Lyndsey Olmstead

Geography and the Environment: Graduate Student Capstones

The Department of Defense's treatment of geographic information systems and cybersecurity as parallel rather than integrated policy domains produces geographically predictable vulnerability patterns across its global military installation footprint. This capstone investigates that conclusion through original spatial analysis, constructing a five-variable composite geospatial vulnerability index across the six U.S. Combatant Command regions using publicly available unclassified data. EUCOM ranked highest overall, driven by GPS/PNT spoofing density, commercial satellite coverage, and cyber incident frequency; CENTCOM ranked second, driven by OSINT exposure incidents and governance risk. The null hypothesis of random geographic distribution is rejected. Findings confirm the structural governance gap documented …

Data Governance Maturity, Ai Integration, And Equity In Colorado K-12 Public Schools, John R. Curtin

Electronic Theses and Dissertations

Colorado's 179 K-12 public school districts operate as autonomous governance units, each responsible for securing and managing student data assets that span health, financial, residential, and academic records. The accelerating integration of artificial intelligence (AI) and machine learning (ML) tools into administrative workflows, productivity software, and instructional platforms has fundamentally altered the risk landscape for student data, yet governance frameworks at the state, district, and school levels have not kept pace. This dissertation investigates whether Colorado's decentralized educational governance structure is institutionally capable of producing equitable, secure, and sustainable data governance outcomes in the AI era.

Drawing on Institutional Theory …

Evaluation And Distillation Of Source Code Generation Tasks By Large Language Models, Danny Brahman

Electronic Theses and Dissertations

Large Language Models (LLMs) are predominantly assessed based on their common sense reasoning, language comprehension, and logical reasoning abilities. While models trained in specialized domains like mathematics or coding have demonstrated remarkable advancements in logical reasoning, there remains a significant gap in evaluating their code generation capabilities. Existing benchmark datasets fall short in pinpointing specific strengths and weaknesses, impeding targeted enhancements in models’ reasoning abilities to synthesize code.

To bridge this gap, this thesis introduces two novel contributions: CodeEval and CodeQual. CodeEval is an innovative, pedagogical benchmarking method that mirrors the evaluation processes encountered in academic programming courses. It comprises …

Medical Image Integrity Protection Through U-Net Based Roi Segmentation And Hybrid Integer Wavelet–Quadtree Embedding, Muna M. Jawad, Rasha F. Nadhim, Noor A. Yousif, Ashwaq T. Hashim

Journal of Intelligent Informatics, Networking, and Cybersecurity

For decades, secure techniques in medical images have focused on securing the sensitive information through limiting direct access to the images themselves. Nonetheless, these methods tend to cause distortion on the images that can affect the diagnostic value and cause loss of crucial information. There arises the fundamental problem of secure embedding of medical data in such a way that does not affect the diagnostic integrity of the image. To overcome this limitation, a secure yet hidden data-hiding mechanism is introduced that is exploited U-Net-based deep learning for accurate Region of Interest (ROI) segmentation. Therefore U-Net architecture is used for …

Uniform Stability Of Katyusha In Strongly-Convex Settings, Don Li

University Honors Theses

Acceleration of convergence and reduction of variance constitute a trade-off in the design of stochastic optimization machine learning algorithms. Katyusha was introduced to address this trade-off, synthesizing Nesterov Accelerated Gradient (NAG) and Stochastic Variance-Reduced Gradient (SVRG) into a single first-order optimizer with promising empirical performance. However, the generalization properties of Katyusha remain largely unexplored. We conjecture that, in the smooth quadratic regime (i.e., under assumptions of strong convexity and smoothness of the loss function, and boundedness of gradients), Katyusha is uniformly stable in the sense of Bousquet and Elisseeff. Instantiating our framework for NAG, we extend the use of Lyapunov …

Data-Driven Qoe Inference For Htttp Adaptive Streaming, Tisa Selma

Thesis/ Dissertation Defenses

In HTTP adaptive streaming, accurately inferring user Quality of Experience (QoE) remains challenging due to dynamic network conditions, content variations, end-to-end encryption, intrusive advertisement interruptions, and diverse user engagement behaviors. Conventional approaches, such as ITU-T P.1203, fall short in capturing real-time user perception, accounting for ad related disruptions, or adapting to model drift over time. This dissertation therefore aims to develop a multimodal face emotion recognition (FER) based inference model that predicts QoE under encryption and advertisement conditions while being interpretable, robust, resilient to drift, and highly accurate. To achieve these objectives, a unified framework is designed and implemented. The …

Enhanced Uav Surveillance With Rf-Based Drone Identification Using Transfer Learning, Prajoy Podder, Maciej Jan Zawodniok, Sanjay Madria

Electrical and Computer Engineering Faculty Research & Creative Works

With the development of technology and the decrease in costs, drones are now becoming easily accessible to the public. As the accessibility of this technology continues to grow, the concerns of security and surveillance increase, and to ensure a sense of security, the need to have reliable drone detection and identification systems is more urgent than ever. Besides, many civilian applications have been found for drones, which play a huge role in modern security and warfare. Unauthorized drones can be very dangerous regarding security issues, as they can be used for spying, smuggling, or even attacks against critical infrastructure. We …

Comparative Analysis Of Leaflet Materials, Stent Materials, And Stent Cell Density For Bileaflet Transcatheter Mitral Valve Design, Joseph Chibuike Nwokeafor, Joshua D. Hofmeister, Breandan B. Yeats, Lakshmi Prasad Dasi, Charanjit S. Rihal, Juan A. Crestanello, Leigh Griffiths, Mohamad A. Alkhouli, Hoda Hatoum

Michigan Tech Publications

Background: The biomechanical performance of bileaflet transcatheter mitral valves (TMVs) depends on complex interactions between leaflet material behavior and stent design. However, the contributions of leaflet materials and constitutive models, stent materials, and stent geometry to valve function and durability remain poorly understood. Methods: A parametric finite element study was conducted using a CAD model of a bileaflet TMV subjected to physiological pressure loading. Five leaflet material models were evaluated: 3 glutaraldehyde-fixed tissues—bovine pericardium (BP; FBP1, FBP2) and porcine pericardium (PP; FPP)—and 2 unfixed tissues—bovine (UBP) and porcine pericardium (UPP). BP was modeled as a linear elastic (FBP1) and Ogden …

Ai In Education And Information: Tool, Threat, Or Teammate? How Academia Is Shaping The Future Of Intelligent Work, Essraa Nawar

Library Presentations, Posters, and Audiovisual Materials

Artificial intelligence is rapidly changing the future of intelligent work across education, healthcare, leadership, communication, workplace culture, and health information management. Yet while AI adoption continues accelerating, institutions and professionals are still trying to understand what this transformation actually means for people, learning, careers, ethics, trust, governance, and human judgment. This interactive and forward-thinking panel brings together voices from higher education and healthcare information management to explore how AI is reshaping classrooms, workplaces, healthcare systems, professional identity, and future workforce expectations across generations.

Rather than focusing only on technology itself, the conversation will examine the broader cultural and organizational shift …

A Study On Culturally Sensitive Ai-Based Conversational Interfaces To Enhance Digital Service Accessibility For Senior Citizens In The Uae, Salma Eisa Alkhyeli

Thesis/ Dissertation Defenses

The UAE is steadfast in its digitalization process due to the Vision 2031, but the aging population encounters several barriers in its efforts to use essential services like subsidized food and fodder markets through an online platform. This thesis developed and validated an AI-based conversational system that focused on helping the elderly group to acquire digital services. The challenges here are associated with lack of knowledge on digital interfaces, language barrier because of dialects and lack of digital literacy in a majority of older adults. The Study addressed these challenges by considering the diverse dialect, cultural and technological needs of …

New Results On Three-Sided Skyline Range Counting And Reporting, Suruchi Kushwaha, Yakov Nekrich

Michigan Tech Publications

In the orthogonal skyline range counting (resp. reporting) problem we store the set of points P in a data structure so that for any query range Q the number of points (resp. the list of all points) on the skyline of Q∩P can be found efficiently. In this paper we study two-dimensional range counting and reporting problems in the case when the query range is bounded on three sides. We describe a linear-space data structure that answers top-open three-sided skyline counting queries in O(log log N) time, where N is the number of points stored in the data structure. We …

Predicting Cybermindfulness With The Cyber-Health Belief Model, James Robinson, Yan Tian, Thomas Skill

Journal of Cybersecurity Education, Research and Practice

This study describes the development of a Cyber-Health Belief Model (CHBM). The health belief model (HBM) is a message strategy that is widely and successfully used in public health research [1] and has been extended into phish training. Most phish training programs assume  end users are victimized because they have insufficient information to defend themselves. While near-term training effectiveness has shown to be effective, evidence for sustained behavioral change is thin [4]-[7].  This problem indicates that the traditional approaches need to be reconsidered and that new models are needed.  Recent research suggests attentional deficits, cyber-fatigue and fatalism and a sense …

Parent Cultural Wealth: How Beliefs, Curriculum Familiarity, And Community Awareness Facilitate Home-Based Cs Conversations, Nicol Howard, Leiny Y. Garcia, Jean Ryoo, Julie Flapan, Michelle Choi, Paula Nazario, Wei Wei

Mathematics, Physics, and Computer Science Faculty Articles and Research

Parents are critical influences on children's computer science (CS) pathways, yet families’ involvement remains understudied. Guided by parental involvement and community cultural wealth frameworks, this work-in-progress examined survey data from 53 parents representing families historically underrepresented in computing within California (71% women; 54% Hispanic/Latin/x/e). Findings revealed that CS school curriculum familiarity and awareness of CS community events significantly predicted parent-child CS conversations, while parent CS confidence and attitudes did not, suggesting that curriculum transparency and community connections can promote equitable involvement. Future work will integrate qualitative interviews to examine how families draw upon their cultural wealth.

Describing Hidden Curriculum In An Undergraduate Computing Context, Joseph R. Teahen, Briana C. Bettin, Leo Ureel

Michigan Tech Publications

Hidden Curriculum (HC) is the set of essential knowledge, skills, and norms students are expected to know, but never explicitly taught. HC is disproportionately experienced across identities and communities. In computing education, most research addresses immediately identifiable HC within the researcher's context. While such work is important, without proper HC descriptive studies, we could miss more subtle HC that affects student success. This work presents results from interviews with undergraduate computing faculty, students, and peer mentors on their HC experiences. The results demonstrate several categories of HC including development tools, professional skills, institutional navigation, social well-being, and physical well-being. These …

A Comprehensive Review Of Optimization Techniques For Healthcare Using Cancer Datasets, Dina Tbaishat, Mohammad Tubishat, Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar

All Works

This study presents a systematic review of metaheuristic optimization techniques applied to healthcare problems using cancer datasets. A structured search of recently published peer-reviewed literature was carried out, focusing on five major application areas: feature selection, classification, image segmentation, hyperparameter tuning, and early detection. For each eligible study, the optimization strategy, dataset characteristics, data modality, learning model, validation protocol, and reported outcomes are provided. The reviewed works were organized into a taxonomy of original, modified, and hybridized algorithms, and a descriptive analysis was performed to assess algorithm prevalence and dataset utilization. The findings highlight that feature selection remains the most …

The Intersection Between Mindfulness And Cybersecurity: A Tool To Reduce Burnout And Improve Operational Effectiveness, Ivo Ricardo Dias Rosa

Journal of Cybersecurity Education, Research and Practice

Abstract: This paper offers a conceptual discussion of how mindfulness, understood as present moment awareness and deliberate attention regulation, can support cybersecurity professionals. Drawing on a narrative synthesis of workplace mindfulness, burnout, and high pressure decision making literature, we map plausible self regulation mechanisms to typical cyber defense tasks. Rather than presenting new empirical data, we develop an explanatory framework linking attention, reactivity, and recovery to decision quality, team communication, and adherence to incident playbooks. We focus on two connected outcomes: reducing burnout in roles with sustained cognitive and emotional demands, and improving operational effectiveness during critical situations such as …