Computer Engineering Commons^™

Optimizing Few-Shot Learning In Pruned Large Language Models With Task-Specific Prompts, Danyal Aftab

Dissertations

Few-shot learning enables large language models to efficiently perform tasks given only a limited number of labeled examples. However, training these models entirely from scratch requires substantial computational resources, making it challenging for many organizations to fully leverage their potential. This thesis explores how structured pruning, task-specific prompting, and parameter-efficient fine-tuning can be combined to preserve few-shot learning capabilities in compressed LLMs, while also extending their utility to real-world recommendation systems.

In this research, we propose the Tailored LLM framework, which first reduces model size through structured pruning and then enhances few-shot learning performance using carefully designed prompts. We experiment …

Monitoring And Short-Term Forecasting Of Atmospheric Air Pollutants Using Deep Neural Networks, Prasanjit Dey

Dissertations

Accurate forecasting of near-surface atmospheric air pollutants such as PM2.5, NO2, SO2, CO, and O3 remains a critical scientific and societal challenge. This difficulty arises from several factors, including nonlinear pollutant dynamics, sparse ground monitoring net works, heterogeneous satellite observations, and strong cross-pollutant interdependencies. Substantial advances have been achieved in temporal deep learning, probabilistic modeling, satellite-based estimation, physics-informed methods, and foundation models. However, these paradigms have largely evolved in isolation. As a result, existing systems are often station-dependent or pollutant-specific and optimized for a single forecasting task. This limits their robustness and generalizability across regions and heterogeneous data regimes.

This …

Enabling Ml/Ai In 6g And Future Wireless Communication With Privacy Preservation, Mec Offloading And Quantum Computing, Changshi Zhou

Dissertations

The forthcoming sixth-generation (6G) and future wireless networks are envisioned to support an unprecedented range of services, delivering ultra-low latency, massive connectivity, and intelligent real-time responsiveness. These capabilities will enable emerging applications such as extended reality (XR), autonomous vehicles (AVs), industrial robotics, and the Internet of Things (IoT) to reach their full potential. Achieving this vision requires the integration of enabling technologies such as artificial intelligence and machine learning (AI/ML) and quantum computing, which are poised to play central roles in shaping the landscape of wireless communication systems.

In AI-native, data-driven, and computing-centric 6G networks, ML models will be deeply …

Holistic Dram Enhancements: From Intrinsic In-Memory Operations To Robust Security Mechanisms, Ranyang Zhou

Dissertations

Dynamic Random-Access Memory (DRAM) is both the performance bottleneck and a critical security boundary of modern computing systems. Its physical properties make it an attractive substrate for near-data computation—yet those same properties expose it to disturbance-based hardware attacks. This dissertation argues that these two dimensions are not independent: the architectural choices that make DRAM efficient also reshape its threat landscape. Addressing both requires a unified approach to memory architecture and security co-design.

The first part of this dissertation attacks the memory wall through four processing-in-DRAM (PIM) frameworks. ReD-LUT and LT-PIM unify lookup-table arithmetic with charge-sharing logic, achieving up to 37.8x …

Active Listening And Reassurance In Text-Based Virtual Health Coaches, Ghulam Hussain

Dissertations

Conversational agents (CAs) have strong potential to support health and physical wellbeing through text-based coaching, but they remain limited in their ability to demonstrate supportive social behaviours that are important in human coaching interactions. In particular, relatively little is known about how Active Listening and Reassurance are perceived, modelled, and evaluated in text-based virtual healthcare coaching, or how such behaviours should be adapted to individual users.

This dissertation investigates how supportive interaction behaviours can enhance text based virtual health coaching, with an initial focus on Active Listening and Reassurance and a later theoretical emphasis on Active Listening. Across five unique …

Feedback In Digital Game-Based Learning: A Taxonomy And The Design And Empirical Evaluation Of A Feedback System In A Mathematics Serious Game, André Almo

Dissertations

Digital Game-Based Learning (DGBL) is an active, student-centred pedagogical approach in which feedback plays a central role by informing learners’ actions, guiding decision-making and shaping motivation and engagement. Despite its importance, feedback in serious games is often described inconsistently and insufficiently in research, limiting comparability across studies and the accumulation of design knowledge, particularly for children. This thesis addresses these gaps through two complementary contributions: the development of a taxonomy for feedback design in digital serious games and the empirical evaluation of a taxonomy-informed feedback system in a mathematics game for primary school students. First, this work introduces the Taxonomy …

A Capability Maturity Model For Artificial Intelligence Integration In Supply Chain Management, Lordt Becklines

Dissertations

Artificial Intelligence (AI) is transforming Supply Chain Management (SCM), yet many organizations struggle to assess their readiness for AI adoption and to understand how AI capabilities develop across maturity stages. This dissertation addresses this gap by developing a Capability Maturity Model (CMM) for AI integration in SCM, grounded in Organizational Information Processing Theory (OIPT), the Resource-Based View, and related capability frameworks. The model provides a structured approach for evaluating an organization's information-processing requirements, resource configurations, and alignment needed for effective AI-enabled supply chain operations.

Using a design science research approach, the AI-SCM CMM and its associated assessment instrument were derived …

Sharing Patient-Generated Health Data With Electronic Health Record: A Standardised Provenance And Context-Rich Information Model And Clinician Evaluation, Abdullahi Abubakar Kawu

Dissertations

With the advent of Patient-Generated Health Data (PGHD) through wearable, mobile, and home monitoring systems, there is immense potential for ongoing monitoring and patient engagement. But integrating PGHD with Electronic Health Record (EHR) is challenged by sub-optimal support for contextual metadata and its relevant elements, lack of semantic interoperability among disparate systems, poor knowledge regarding the factors that impact clinician acceptance, and absence of globally agreed standards for data exchange. This thesis explores how contextually relevant patient-generated health data can be shared with EHRs through a FAIR standardized information model that ensures semantic and syntactic interoperability.

The study addresses six …

Privacy Preserving-Based Artificial Intelligence For Precision Agriculture, Partha P. Sengupta

Dissertations

The research work finds a solution to precision agriculture of cotton cultivation using artificial intelligence (AI) models. Two sets of model performance based on the application are selected namely a low resource and a high resource setting. This is because using drone surveys to capture images identifying the classes of stressed and unstressed cotton plantation requires limited model architecture and CPU based computation. Thus, traditional AI models were selected for low resource settings. Again, for high computation intensive models like transfer learning-convolution neural network (CNN) based architectures were grouped into high resource settings. There was another issue of class imbalance …

Optimizing Hip And Knee Assistance For Walking And Sit-To-Stand Transitions: An Intrinsic Muscle Mechanics Based Predictive Approach, Neethan Ratnakumar

Dissertations

As the global population ages, the demand for wearable assistive technologies continues to rise, driven by their potential to enhance mobility and independence in older adults. Effectively designed controllers for lower-limb exoskeletons to assist sit-to-stand (STS) and walking are crucial for delivering efficient, safe, and comfortable assistance during daily activities. Traditionally, controller optimization involves biomechanical modeling and user-specific customization. Musculoskeletal simulations play a central role in this process by providing insights into human-exoskeleton interaction dynamics, thereby informing and refining control strategies.

This work presents a simulation-driven approach for developing exoskeleton controllers for walking and STS using two distinct methods: optimal …

Reinforcement Learning And Virtual Human Animation: A Novel Approach To Data-Driven Animation, Portraying Dynamic, Flexible Human-Like Behaviours, Vihanga Gamage

Dissertations

Virtual characters require animation capable of portraying dynamic, context-sensitive human-like behaviours. Several approaches to generating such animation have been developed, but each carries limitations. Motion capture can produce high-fidelity animation but is expensive and ill-suited to systems that must respond in real time. Physics-based reinforcement learning (RL) enables flexible, dynamic behaviour portrayal, yet relies on simulation feedback signals that are unavailable for social gestures. Supervised approaches can learn social behaviours from motion capture data but yield agents with limited flexibility and generalisation.

This thesis presents RLAnimate, a model-based, data-driven RL framework for character animation that enables a single agent to …

Enhancing Credit Path Planning With Llm-Based Multi-Agent Systems, Sahar Yarmohammadtoosky

Dissertations

This work explores applying Multi-Agent (MA) Large Language Models (LLMs) to enhance credit card management, an underexplored area for their multi-step reasoning capabilities. Focusing on Equifax’s Optimal Path™ model [1]—a personalized solution for credit score optimization—the study addresses two key challenges: first, designing a natural language interface for financial credit models to improve accessibility and aid customer decision-making, and second, enhancing the reliability and real-world applicability of complex financial models prone to generating invalid or unfeasible recommendations caused by a lack of practical interpretability and susceptibility to edge cases. To tackle these, we propose and evaluate various MA designs, including …

Adversarial Robustness In Advanced Machine Learning Models Integrating Graph Neural Networks And Large Language Models, Mahmoud Nazzal

Dissertations

Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle these structures; Graph Neural Networks (GNNs) for relational mining and Large Language Models (LLMs) for sequential understanding. Despite their success, these models face challenges in security, robustness, and interpretability. GNNs excel in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and …

Balancergnn: Balancer Graph Neural Network For Imbalanced Datasets, Mallika Boyapati

Dissertations

Addressing imbalanced datasets is challenging due to machine learning models' inclination to learn the majority class. Graph construction plays a major role in determining how Graph Neural Networks (GNNs) perform on imbalanced datasets. In this research, we introduce the BalancerGNN framework to tackle highly imbalanced datasets, demonstrating its effectiveness in fraud detection as one of the case studies. This framework is designed to work for any binary node classification dataset with significant class imbalances. This research addresses the following questions: i) How effective are feature engineering techniques in the case of imbalanced datasets? ii) How do graph representation learning and …

Navigating Big Data In Cyber Archaeology: An Updated Four-Field Approach Applied To San Miceli, Jared Wilson

Dissertations

Problem

This dissertation examines the evolving role of digital technologies in archaeological research, focusing on the management and interpretation of extensive digital datasets generated by modern excavations. Drawing on six years of comprehensive fieldwork at San Miceli, Sicily, this study critically evaluates and updates the established four-field methodology proposed by Levy et al. (2012), encompassing acquisition, analysis, dissemination, and curation. While traditional archaeological documentation methods rely heavily on analog techniques, these approaches increasingly fall short due to the rapid expansion and complexity of digital data.

Method

To address this gap, the dissertation refines and expands the current methodological framework by …

Federated Learning Systems For Mobile Sensing Data, Xiaopeng Jiang

Dissertations

Federated Learning (FL) has emerged as a new distributed Deep Learning (DL) paradigm that enables privacy-aware training and inference on mobile devices with help from the cloud. This dissertation presents a comprehensive exploration of FL with mobile sensing data, covering systems, applications, and optimizations.

First, a mobile-cloud FL system, FLSys, is designed to balance model performance with resource consumption, tolerate communication failures, and achieve scalability. In FLSys, different DL models with different FL aggregation methods can be trained and accessed concurrently by different apps. In addition, FLSys provides advanced privacy-preserving mechanisms and a common API for third-party app developers to …

Network Slicing And Noma Enabled Mobile Edge Computing For Next-Generation Networks, Mohammad Arif Hossain

Dissertations

The advent of next-generation wireless networks ushers in a new era of potential, harnessing cutting-edge technologies like mobile edge computing (MEC), non-orthogonal multiple access (NOMA), and network slicing as pivotal drivers of transformation. Within this landscape, an innovative approach is proposed by introducing a NOMA-enabled network slicing technique within MEC networks. This approach aims to achieve multiple objectives: meeting stringent quality of service requirements, minimizing service latency, and enhancing spectral efficiency. By seamlessly integrating NOMA with network slicing in edge computing environments, significant reductions in overall latency are achieved, alongside ensuring optimal resource allocation for NOMA users. To address these …

Integrating Laser Charging And Drones For Secure Edge Computing, Weiqi Liu

Dissertations

Drone-mounted base stations (DBSs) have emerged as a promising solution to enhance the flexibility and coverage of wireless networks, potentially revolutionizing communication systems. This dissertation explores the integration of DBSs into 5G and beyond networks, focusing on methodologies to optimize their deployment and performance. A laser charging-enabled DBS framework is proposed to extend flight time and enhance network coverage. By leveraging laser charging technology, the DBS can receive continuous energy transmission from a ground-based charging station while providing communication services to users. The framework is formulated as an optimization problem to jointly maximize flight time and communication data rate, while …

Enhancing Cybersecurity In Wireless Sensor Networks: Machine Learning, Blockchain And Future Perspectives, Ilemona Solomon Atawodi

Dissertations

Security in the Industrial Internet of Things encounters various security issues but the main issues can be broken down into three core issues: Availability, Integrity, and Confidentiality. Security challenges generally tend to be caused by a failure of the system in one of these areas or cause a failure in one of these areas. Therefore researching scalable solutions to these security issues is prudent to explore methods that could be applied to large-scale industrial IIoT with tens to hundreds of devices as well as small-scale systems on a tiny factory floor comprising of just a few devices. In our research, …

A Novel Data Fusion Fr Amework To Enhance Contextual Awareness Of The Autonomous Vehicles For Accurate Decision Making, Henry Alexander Ignatious

Dissertations

Autonomous driving has the potential to bring significant changes and benefits to various aspects of transportation. Autonomous vehicles (AVs) use a combination of advanced sensors, cameras, radar, lidar, GPS, maps, and AI algorithms to perceive their environment, make decisions, and control their movements. Though there is a significant increase in the AVs utility, there are several challenges associated with the AVs among which ensuring safety and security for a reliable drive is still an existing challenge. The majority of accidents involving the AVs result from faulty decision-making resulting in fatal incidents. Multiple elements contribute to the flawed decision-making in autonomous …

Steminism: Analyzing Factors That Improve Retention Of Women In Stem, Kira Carter, Jane Kelley, Jason Vasser-Elong, Rc Patterson

Dissertations

Our co-authored research ‘Steminism: Analyzing Factors That Improve Retention for Women as STEM Majors’ analyzed factors that contributed to the retention of women in science, technology, engineering, and mathematics (STEM) programs at Missouri University of Science & Technology (Missouri S&T). Women make up half of the US population, and while careers in (STEM) are an integral part of the US economy, women are underrepresented in these career fields. The purpose of our dissertation is to address the underrepresentation of women in STEM majors. Our methodology included homogeneous sampling to collect qualitative data. More specifically, we consulted with academic advisors and …

Adaptive Inter-Vehicular Collaboration For Level 5 Autonomous Driving, Sumbal Malik

Dissertations

The evolution of sensor technologies, mobile networks, and artificial intelligence has significantly expanded the horizons of various sectors, notably in autonomous driving. According to the World Health Organization, over 1.3 million people succumb to traffic accidents annually, predominantly due to human negligence. Complex urban environments, characterized by mixed traffic flow involving Human Driven Vehicles and Connected and Autonomous Vehicles, intricate traffic patterns, frequent lane changes, and slow speeds, face escalating challenges related to traffic accidents and congestion. These challenges lead to wasted time, increased fuel consumption, and heightened pollution emission levels. Hence, the development of a safe and robust version …

How Can A Cloud Computing It Framework Be Created And Applied Effectively In The Online Printing Industry?, Stefan Meissner

Dissertations

This research aims to design a cloud computing IT framework for the online printing industry based on a detailed literature review, the development of proof of concepts (PoC), and the conduction of a focus group. The framework can be adopted by the online printing industry or by vendors of print-specific applications to optimize their products for the online printing industry. The author has been working in the online printing process optimization and automation since 2007. During this time, he got deep insight into many industry-specific applications, their architectural design, and their challenges being used in the context of online printing. …

A Fully Automated Global Post-Hoc Method Based On Abstract Argumentation For Explainable Artificial Intelligence And Its Application On Fully Connected Dense Deep Neural Networks, Giulia Vilone

Dissertations

Explainable Artificial Intelligence (XAI) has rapidly grown in the past decade due to the prevalence of machine learning, especially deep learning, in fields like healthcare and finance. While these models excel in accuracy, their complexity hampers transparency and interpretability. Ensuring understandable explanations for AI predictions fosters trust, prevents errors, complies with regulations, and enhances model refinement. The research project outlined in this thesis unfolds in phases. It commences with a comprehensive review of existing XAI studies, contributing to the field’s knowledge by proposing a taxonomy that organises theories and notions related to explainability, the evaluation approaches for XAI methods, and …

Timeseries Forecasting Of U.S. Housing Price Index Using Machine Learning And Deep Learning Models, Krishna Chaitanya Nunna

Dissertations

Time series forecasting is a promising technique for various applications which predicts future values or patterns by taking historical data as base. Forecasting future trends is very beneficial for different industries to make valuable decisions and strategies. One such industry is housing market; it has biggest influence on U.S. economy. Housing price index (HPI) is a one of the crucial economic indices published by various government funded and private agency to benefit several industries and individuals for better analysis of future trends of housing market.

Several factors influence the HPI, economical, geographical, and demographic features. Development of traditional time series …

Advanced Traffic Video Analytics For Robust Traffic Accident Detection, Hadi Ghahremannezhad

Dissertations

Automatic traffic accident detection is an important task in traffic video analysis due to its key applications in developing intelligent transportation systems. Reducing the time delay between the occurrence of an accident and the dispatch of the first responders to the scene may help lower the mortality rate and save lives. Since 1980, many approaches have been presented for the automatic detection of incidents in traffic videos. In this dissertation, some challenging problems for accident detection in traffic videos are discussed and a new framework is presented in order to automatically detect single-vehicle and intersection traffic accidents in real-time.

First, …

Toward Smart And Efficient Scientific Data Management, Jinzhen Wang

Dissertations

Scientific research generates vast amounts of data, and the scale of data has significantly increased with advancements in scientific applications. To manage this data effectively, lossy data compression techniques are necessary to reduce storage and transmission costs. Nevertheless, the use of lossy compression introduces uncertainties related to its performance. This dissertation aims to answer key questions surrounding lossy data compression, such as how the performance changes, how much reduction can be achieved, and how to optimize these techniques for modern scientific data management workflows.

One of the major challenges in adopting lossy compression techniques is the trade-off between data accuracy …

Intelligent And Explainable Solution To Predict Infant Birthweight And Preterm Birth In The United Arab Emirates, Wasif Khan

Dissertations

Adverse pregnancy outcomes such as Low Birth Weight (LBW) and Preterm birth (PTB) are complex pregnancy challenges that can lead to high perinatal mortality and long-term morbidity for infants. Early prediction of such adverse outcomes can be useful for averting catastrophic outcomes for the mother and her baby. With advances in machine learning (ML)-based algorithms, several models have been proposed for both PTB and LBW predictions. However, the risk factors associated with these outcomes are still unknown, particularly in the United Arab Emirates (UAE). Furthermore, existing ML-based prediction models work in a black-box manner and lack proper interpretations for clinicians, …

The Effects Of Disinformation Upon National Attitudes Towards The Eu And Its Institutions, Alex Murphy

Dissertations

This work explores the effects of misinformation and disinformation upon national attitudes towards the EU. Several nations, in particular the Russian Federation, have been working for decades to spread narratives that debase the political processes of healthy democracies around the world. There is strong evidence to show that extensive efforts have been made to disrupt the inner workings and overall membership of the EU, to support disruptive policies in the United States such that political deadlock is maintained indefinitely. These efforts are largely based on the spreading of misinformation and disinformation across social networks that have done very little to …

Development Of A Hospital Discharge Planning System Augmented With A Neural Clinical Decision Support Engine, David Mulqueen

Dissertations

The process of discharging patients from a tertiary care hospital, is one of the key activities to ensure the efficient and effective operation of a hospital. However, the decision to discharge a patient from a hospital is complex, as it requires multiple interactions with nurses, family, consultants, health information records and doctors, which can be very time consuming and prone to error. This thesis descries how a neural network based Clinical Decision Support system can be developed, to help in the decision making process and dramatically reduce the time and effort in running the discharge process in a hospital. A …