Computer Sciences Commons^™

Bayesian Network: An Explainable Artificial Intelligence (Xai) Approach To Human Performance Modelling For Control Room Operations, Houda Briwa

Theses

Alarm systems in process industry control rooms routinely exceed the performance targets set by standards such as EEMUA 191, placing operators under conditions where reliable performance is most difficult to achieve. Predicting how operators respond under such conditions is central to risk management, yet current Human Reliability Assessment (HRA) methods depend on expert judgement that is rarely tested against operational evidence, assume independence among factors known to interact, and do not explicitly represent the cognitive processes through which performance emerges. In Resilience Engineering terms, these methods encode Work-as-Imagined with limited means to assess how far expectations hold when work is …

Edge Co-Occurrence Regularization For Node Classification, Kadir Altunel

Theses

We propose a simple yet effective regularization technique for node classification on graphs that leverages edge-based label co-occurrence patterns. We first train an MLP on node features to produce class probability distributions, then compute a fixed penalty matrix from edge-based co-occurrence statistics of these predictions. This penalty matrix, which captures unlikely class combinations on connected nodes, is then used to regularize GNN training without further updates. We evaluate this approach across multiple homophilic datasets (Cora, CiteSeer, PubMed, ogbn-arxiv) and heterophilic benchmarks (Chameleon, Squirrel, Actor, Roman-Empire) using three GNN architectures: GCN, GraphSAGE, and H2GCN. Results show consistent improvements on homophilic graphs, …

Sound Detection Of Memory Leaks In Llvm Ir Programs Using Accumulation Analysis, Robert Blacha

Theses

Resource leaks occur when a limited resource such as memory is allocated by a program and needlessly held past the point of use. Leaks can lead to a degradation of services which can be specifically triggered with malicious behavior, for example abusing a memory leak in a program to cause a server to slow down and crash for a denial-of-service attack.

Prior work has demonstrated that accumulation analysis provides a sound detection of resource leaks with a working implementation for programs written in Java. While useful, current implementations are limited to programs written in Java, which has a garbage collector, …

Adaptive Multimodal Smart Home Control On A Raspberry Pi 5 Using Hand Gestures, Voice Cues, And User Feedback, Vaibhav Bora

Theses

A real time multimodal smart home control system deployed on a Raspberry Pi 5 is presented. The system combines hand gestures, short voice cues, and proximity aware interaction to execute household commands such as light brightness control, fan speed adjustment, and stop or kill switch actions. Lightweight gesture and keyword spotting voice classifiers were trained offline and exported to TensorFlow Lite for efficient on device inference. For more natural spoken phrases, the system additionally integrates a locally deployed pretrained offline ASR component rather than a speech recognizer trained from scratch. Using a USB camera and microphone, the system operates fully …

Pypitfall: Dependency Chaos And Supply Chain Vulnerabilities In Python, Jacob Mahon

Theses

Python software development heavily relies on third-party packages. Direct and transitive dependencies create a labyrinth of software supply chains. While it is convenient to reuse code, vulnerabilities within these dependency chains can propagate through dependencies, potentially affecting downstream packages and applications. PyPI, the official Python package repository, hosts many packages and lacks a comprehensive analysis of the prevalence of vulnerable dependencies. PyPitfall, a quantitative analysis of vulnerable dependencies across the PyPI ecosystem, is introduced. The dependency metadata of 378,573 PyPI packages is analyzed. 4,655 packages that explicitly require a known vulnerable package version and 141,044 packages that permit a vulnerable …

Robustness Of Ai-Driven Histopathology Under Real-World Adversarial Examples, Ruchik N. Yajnik

Theses

This robustness of histopathology classification models under adversarial and real-world perturbations resembling clinical artifacts is being investigated.

Using whole-slide images from the CAMELYON17 cohort, four representative architectures—ResNet-18, ResNet-50, HIPT-2MLP, and ViT-B/16 —are benchmarked across controlled pixel-level distortions and artifact-like transformations. Adversarial methods include iterative Fast Gradient Sign, Projected Gradient Descent, Salt-and-Pepper noise, and the Adversarial Watermark—Stain Shift (AWSS). Three defense strategies—Randomized Smoothing, Adversarial Training, and an Artifact Detector—are evaluated for their ability to preserve diagnostic accuracy and model reliability. Structured perturbations consistently degrade performance, with transformer-based models showing the greatest sensitivity. The benchmark developed here offers a reproducible framework for …

A Comparative Study On Performance Of Iot-Driven Ml-Enabled Forecasting Models For Efficient Air Quality Monitoring, Bara Ksiksi

Theses

Air pollution is one of the most critical environmental challenges affecting public health globally, responsible for approximately 4.2 million premature deaths annually according to the World Health Organisation. This thesis presents a comparative study of IoT-driven machine learning forecasting models for air quality monitoring in Abu Dhabi, UAE, introducing a zonal approach combined with satellite-based spatial validation. The primary objective is to evaluate forecasting performance across three distinct activity zones using ground station data from the Environment Agency Abu Dhabi (EAD), and to incorporate a spatial validation component using satellite imagery to assess the consistency of ground-based predictions at a …

Llm-Driven Mission Control And Autonomous Planning For Search-And-Rescue Uavs: A Simulation-Based Evaluation, Naser Bader Alsaedi

Theses

Unmanned aerial vehicles (UAVs) are increasingly used in search‑and‑rescue (SAR) missions, yet many systems still rely on fragmented software where mission design, perception, and flight control are configured separately. This thesis examines whether a unified AI‑driven framework can reduce configuration effort and operator workload in UAV‑based SAR operations. The proposed system integrates natural‑language mission specification using a large language model (LLM) (LLaMA 3.1), autonomous coverage planning, YOLOv8‑based victim detection, and PX4/MAVSDK control within a single architecture. Operators describe missions through free‑form text or a graphical interface; the model converts these descriptions into structured mission parameters that are automatically planned and …

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Hindi

Theses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). The thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows.

The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Enhancing The Acceptability Of Decision-Making System Using Xai Case: Crime Profiling System, Mohamed Saeed Al Shamsi

Theses

In the current world, we need to place more emphasis on how easily interpretable, accurate, and acceptable data analysis results are, given that essential operations in law enforcement, among other sectors, are backed up by the use of complex computing systems. Crime profiling systems that use crime data for profiling encounter major problems because they depend on algorithm-based methods. These methods can be ambiguous and inaccurate, leading to low public acceptability. The study investigates major problems with Complex Crime profiling systems (CPS) because their unexplained algorithms result in system performance issues and public scepticism. XAI provides a solution to handle …

Enhanced Privacy Preserving Healthcare Data Management With Federated Learning Using Homomorphic Encryption, Omar Abdulla Ali

Theses

Federated Learning (FL) is a decentralized approach of machine learning on multiple clients jointly training models without sharing their raw data, which drastically improves privacy and enhance protection against security breach. This is particularly critical in the healthcare sector, where hospitals and medical institutions are often unable to exchange patient records due to strict privacy regulations and data-management policies. However, there is still a risk of privacy breach when clients send their model updates to the central server, because if a model update is intercepted or analyzed by a malicious entity, it could be used to recover sensitive data using …

Detecting Data Poisoning Attacks In Medical Imaging: A Study On Chest X-Ray Classification Tasks, Akhila Abdulla Asgar

Theses

This thesis examines the vulnerability of AI medical imaging models to adversarial threats, with a specific focus on data poisoning attacks in chest X-ray classification. The study begins with a Systematic Literature Review (SLR) to assess the existing adversarial attacks and defenses in medical imaging, revealing a significant research gap in studies exploring data poisoning attacks in the medical domain. Based on our literature search, an efficient and lightweight defense, namely friendly noise defense, against data poisoning has not been investigated in medical imaging classification tasks. Hence, in this work, we investigated its effectiveness on the chest X-ray dataset, and …

Startup Success Forecasting Through Machine Learning: A Comprehensive Analysis Of It Startups, Khaled Abdulla Alhassani

Theses

Lately, startups attracted significant attention from investors throughout the previous years. This raised several questions concerning startups and what they possibly define as them. It could refer to collective individuals who focus on innovative ideas with a reproducible and scalable business model; others refer to it as a newly established business. Nevertheless, all these definitions lead to a predictive question. Will these startups face success?

This study explores startup success prediction methods, focusing on forecasting information technology startup (SIT) insights using Machine Learning (ML) models such as Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbor (k-NN), …

Enhancing It Security Management With An Advanced Intrusion Detection System Based On Machine Learning And Explainable Ai, Hanan Aslam Al Zubaidi

Theses

The fast changing landscape of cyber threats continues to challenge the development of strong and reliable security frameworks for IT management systems. Traditional defense tools, such as Intrusion Detection Systems (IDS), often struggle to keep up with today's advanced and constantly evolving attack methods. This thesis explores these ongoing challenges and looks into how machine learning (ML) and explainable artificial intelligence (XAI) can be used to boost IDS performance.

The research outlines a smart, adaptive system that combines supervised learning for real-time threat detection, unsupervised models for anomaly analysis, and proactive defense strategies. The goal is to improve detection accuracy, …

Advancing Security Safeguards In Large Language Models Through Multi-Agent Systems, Mohammed Rashed Alnuaimi

Theses

This thesis focused on enhancing the safe use of Large Language Model (LLM) through the innovative use of a Multi-Agent System (MAS). As LLMs like ChatGPT became essential to our everyday interactions, the need to maintain the safe use of these systems increased. This research thoroughly assessed the current security measures in place for LLM, pointed out their limitations and developed new and more effective security strategies. The core of the proposed solution was a MAS designed to ensure that all data processed by LLM met guidelines including Privacy, Confidentiality, and Ethical standards before reaching the user. The system involved …

Evaluating Large Language Models For Automated Cv Ranking: A Hybrid Embedding Approach For Enhanced Recruitment, Sarah Mohamed Alhindaassi

Theses

Increasing numbers of applications have revealed limitations in legacy keyword-filtering-based Applicant Tracking Systems (ATS), which commonly overlook candidate potential and ignore contextual or transferable skills. Advances in Natural Language Processing (NLP) and Large Language Models (LLMs) offer an exhilarating alternative, supporting context-sensitive and human-crafted reasoning in candidate evaluation. This thesis systematically evaluates four classes of approaches, lexical models, embedding-based methods, Large Language Models (LLMs), and hybrid ensembles, for automation of Curriculum Vitae (CV) to Job Description (JD) matching without exploiting prior annotations or annotations at match time. Using a combination of publicly available datasets and real-world sample data covering three …

Adaptive Security Metric For Optimizing Post-Quantum Cryptography In Constrained Iot Devices, Aisha Nasser Ahmed

Theses

Quantum Computing poses real threat to Classical Public-Key Cryptography requiring the use of Post-Quantum Cryptography for all Internet of Things Devices. However, there are greater computational, memory and communication overheads in PQC algorithms that create additional burdens on resource constrained IoT devices. At this time, there are no standard measures for systems developers to determine optimal PQC settings for the various IoT Device Classes. This Thesis develops a new framework of metrics for determining the most suitable PQC settings based on Security Strength, Performance Indicators (Latency, Memory, Energy), Communication Overhead and Reliability for each IoT device class. The Research introduces …

Enhancing Llm Code Generation: A Systematic Evaluation Of Multi-Agent Collaboration And Runtime Debugging For Improving Accuracy, Reliability, And Latency, Nazmus Ashrafi

Theses

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has opened up new possibilities for automating intricate programming tasks with greater accuracy. Although contemporary foundational models demonstrate promising results, researchers continue to explore optimal post-training strategies to enhance code quality. These include supervised fine-tuning, retrieval-augmented generation (RAG), debugging, and many others. In this thesis, I combine two such widely used post training approaches—namely (1) multi agent collaboration and (2) runtime execution of information-based …

A Web Application For Generating Argument Maps For Essays Using Llms, Alexis R. Chalmers

Theses

Argumentative writing is a critical skill that strengthens students’ reasoning, communication, and analytical abilities. However, maintaining a clear and organized argument structure while writing can be challenging. Argument maps — visual diagrams which explicitly show an argument’s structure — have been shown to improve students’ writing, but are rarely used outside of the planning stage of an essay due to the time and effort required to create them. Automatically generating argument maps from student essays helps students to evaluate the structure of their argument as they write and makes identifying unsupported claims visible. To evaluate whether large language models (LLMs) …

Limitations Of Using Large Language Models For Automated Essay Scoring, Thomas A. Fink

Theses

Background: Automated essay scoring (AES) is a challenging deep learning problem. The two most widely used methods for predicting essay quality scores, supervised learning-based and LLM-based, have their own limitations. Although supervised learning-based methods are more accurate, they only predict a score and do not offer descriptive feedback to students. On the other hand, LLM-based methods can offer rubric-guided feedback but are known to be less accurate.

Methods: This work focuses on improving the accuracy of state-of-the-art LLM-based AES methods. We began by thoroughly investigating why these methods were performing poorly for certain datasets and certain examples. This led us …

Bridging Classical Rhetoric And Ai: A Systematic Framework For Developing Authorial Voice Through Large Language Models, Daniel Plate

Theses

This project addresses critical gaps in AI-assisted writing by developing the first systematic framework that integrates classical rhetorical principles with modern large language model capabilities for authorial voice development. The primary focus is on creating reliable methods for stylistic control through strategic AI collaboration rather than ad hoc prompting approaches. The project develops a comprehensive coding system for analyzing prose style, creates ten distinct authorial personas, and establishes a dual curation methodology that structures both stylistic analysis and content preparation. Implementation through the AI Writing Guide website provides practical tools including prompt templates, annotated examples, and instructional materials that demonstrate …

Customizing Ai Strategies Across Multiple Generations, Matthew Harrer

Theses

This project investigates how artificial intelligence can help brands and marketers connect more effectively with Generation X, Millennials, and Generation Z. The literature review lays the groundwork that focuses on consumer behaviors and the integration of AI into digital marketing practices for each generation. The second part of the project involves a secondary data analysis of 21 recent marketing surveys and reports that explores topics related to trust, personalization, and social media. By integrating the findings into an insightful guidebook, marketers will be able to maximize these insights into clear actionable strategies.

Advancing Academic Advising With Knowledge Graphs: Integrating Machine Learning And Llms For Personalized Course Planning, Sara Alshamsi

Theses

Academic advising plays a critical role in helping students make informed decisions, improve academic performance, and successfully navigate their university journey. However, with increasing university enrollment, traditional advising methods often struggle to scale, leading to student frustration and overburdened advisors. Additionally, designing course offerings that match student demand is a complex and error-prone process involving multiple stakeholders. To address these challenges, this thesis proposes an automated, data-driven system for generating personalized academic plans for students. The primary aim of this thesis is to develop a system that reduces students’ dependency on advisors while simultaneously providing accurate estimates of course demand …

Gamified Gait Rehabilitation Via Real-Time Biofeedback And Adaptive Hip-Exoskeleton Control, Mariya Huzaifa Tohfafarosh

Theses

Gait impairments arise from systemic diseases, age-related degeneration, musculoskeletal dysfunctions, or neurological conditions. While traditional rehabilitation can be effective, they often face challenges such as high costs, inaccessibility, and low patient engagement. To address these challenges, my work introduces a virtual reality-based rehabilitation (VRBR) system, integrating real-time motion and electromyographic (EMG) muscle activation feedback with a gamified virtual environment for enhanced adaptability and engagement. The system includes a custom-designed hip-exoskeleton that provides adaptive spring-like assistance or resistance, supporting both mobility-impaired users and strength training. Assistance levels can be tuned to match the user's progress. Additionally, a custom pressure insole was …

From The Bleachers To The Browser: Redefining Fan Experience With Ar And Ai In Smaller Teams, Jennifer Lee Wunder

Theses

This project documents the creation and deployment of HootyHoo, an interactive augmented reality (AR) mascot experience designed for the O’Fallon Hoots, a small-scale collegiate summer baseball team. Built using accessible, open-source tools such as WebXR, Mixamo, Meshy, Botpress, Claude and ChatGPT, this prototype merges AI-driven conversation with animated 3D avatar interaction—redefining how fans engage with sports organizations digitally. Unlike enterprise-level applications used by professional franchises, HootyHoo is entirely browser-based, eliminating the need for app downloads and ensuring maximum accessibility for families and new fans with smartphones. The experience centers on Hooty, the team mascot, who answers questions about baseball and …

A Data-Driven Recommendation System For Selecting The Appropriate Mode Of Learning And Instructional Tools Based On Course Characteristics, Ayisha Manzoor

Theses

The rapid transformation of educational delivery methods during the COVID-19 pandemic required institutions to transition between online, hybrid, and offline learning approaches, creating both challenges and opportunities for educators and students. While online and hybrid learning modes ensured continuity, their effectiveness across different course types remained uncertain. This thesis addresses this gap by developing a datadriven recommendation framework that predicts Course Learning Outcome (CLO) achievement scores using regression, and recommends the most appropriate learning mode (online, hybrid, or offline) along with instructional tools based on course characteristics. This study analyzed 100 undergraduate and postgraduate courses from the College of Information …

Collaborative Network Traffic Management Strategies Using Distributed Reinforcement Learning And Large Language Models, Saeed Rashed Alkuwaiti

Theses

The focus of this research is to explore collaborative network traffic management strategies using the Distributed Reinforcement Learning (DRL) and Large Language Models (LLMs) approaches. It emphasizes exploring a new tool for addressing network traffic by utilizing Distributed Reinforcement Learning (DRL) and Large Language Models (LLMs). This is achieved by utilizing self-organizing and self-directing techniques to optimize the network performance. Using the NF-TON-IOT dataset, various classifiers such as Random Forest, AdaBoost, C4. 5, Multi-Layer Perceptron (MLP), and SVM with an RBF kernel were tested for traffic classification and intrusion detection. Research recommends that DRL optimizes the complexity of the network …

Assessing Readiness For Transformation From Rulebased To Ai-Based Chatbot In Uae Healthcare: A Case Study Of A Rehabilitation Hospital In Abu Dhabi, Mubarak Alketbi

Theses

This study investigates the readiness for transforming rule-based chatbots to AI-based chatbots in UAE healthcare, examining a rehabilitation hospital in Abu Dhabi through quantitative research involving healthcare professionals (N=96) and technical analysis. Findings revealed positive perceptions of the current system alongside enhancement opportunities through AI capabilities, with perceived usefulness strongly correlating with behavioural intention, high service quality ratings for empathy and responsiveness, midcareer professionals demonstrating the highest AI acceptance levels, and system integration identified as the highest priority implementation area.

The research contributes to healthcare technology transformation knowledge in the UAE by providing a structured implementation framework addressing technical requirements, …

A Framework For Mixed Reality Within Healthcare Education, Benyamin Ebadinia

Theses

Understanding complex three-dimensional systems and spatial relationships is a recurring difficulty in healthcare education, where students are often expected to reason about internal structures and multi-system processes from 2D diagrams, textbook figures, and static mannequins. This thesis presents the design, implementation, and mixed-methods evaluation of Systems Simulation, a reusable mixed reality (MR) application intended to help undergraduate nursing students explore human anatomy and pathophysiology using immersive 3D visualization.

Built in C# with the StereoKit framework for Microsoft HoloLens 2, Systems Simulation organizes nine anatomical body systems within a shared application. Learners can select a system, anchor the model in their …

Surveying The Role Of Visual Analytics In Human-Machine Teaming, Naga Datha Saikiran Battula

Theses

Humans and machines both possess their unique capabilities and have their strengths and weaknesses, which can be complementary to one another and allow them to achieve a common goal. Teaming in the modern era involves text prompts, voice commands, gesture recognition, touch interfaces, and the latest visualization techniques that allow parties/agents to interact. Communication through visualization plays a vital role in allowing robust insights to be gained through a glance. Using visualization as a medium between humans and machines can increase the communication bandwidth. Human-machine teaming has witnessed much progress, with many theories and practical examples emerging. In the report, …