Computer Engineering Commons^™

Real-Time Fraud Detection, Haidi Aly Fahmy, Abdelhadi Nait-Zerrad, Shiva Krishana Reddy Ravuula, Sangwhan Cha

Harrisburg University Other Works

Financial fraud detection is a high-volume, high-velocity analytics problem. Traditional rule-based systems are often easy to deploy, but they are limited by static thresholds, delayed response, high false-positive rates, and weak explainability. This report presents a formalized end-to-end Big Data architecture for real-time fraud and anomaly detection in financial transaction streams.

The proposed architecture ingests transaction events through AWS Kinesis, enriches them through an Apache Flink stream-processing layer, scores them with an XGBoost classifier, explains model outputs using SHAP, and converts structured evidence into human-readable summaries through a controlled GPT explanation layer. Results are persisted through a hybrid storage strategy …

Power Consumption Prediction And Energy Forecasting Using Machine Learning Models, Sheik Mohideen Shah S Mr

Theses and Dissertations

Power consumption trends are essential to be identified in the energy grid areas to analyze the utilization, deficiency, and the measures to be taken for an effective and comfortable usage of energy. There are two scenarios in which the power consumption can be analyzed, namely identification and prediction. Identification deals with the post-utilization analysis of energy trends, whereas prediction deals with prior analysis of various factors of energy utilization, including the cost, supply details, shortages, and the need for new energy resources. In the existing models, the power consumption-related data are collected through smart meters, and the energy forecasting methods …

Predictive Natural Language Metrics Of Alzheimer's Disease And Cognitive Decline Trend Analysis, Zerui Ma

Computer Science and Engineering Theses and Dissertations

Inspired by Dr. David Snowden's Nun Study, which linked early-life Propositional Idea Density (PID) to later-life Alzheimer's disease, this thesis investigates two questions: whether fine-tuned Transformer-based large language models (LLM) can detect cognitive decline from patient speech transcripts with meaningful feature attribution, and whether longitudinal PID trends are observable across large-scale internet and academic text corpora. We evaluate dementia prediction on the DementiaBank Pitt Corpus and conduct an exploratory longitudinal PID analysis across seven diverse datasets spanning up to 29 years and over 12.6 million documents. This work suggests that linguistic ability metrics, traditional PID metrics and novel LLM-based analysis, …

Machine Learning And Formal Methods In Quantum Chemistry: Theory And Application, Ishna Satyarth

Computer Science and Engineering Theses and Dissertations

In recent years, the progress in inter-disciplinary application of machine learning and artificial intelligence (ML/AI) have truly transformed various fields, from weather forecasting and drug development to medical diagnostics, energy, and sustainability. Computational chemistry uses computational tools to model, predict, analyze, and explain chemical phenomena, while the Quantum chemistry specifically uses techniques based on quantum mechanics (as opposed to classical mechanics or empirical models). Quantum chemistry or Computational chemistry has also observed a momentum in application of ML techniques over the past decade significantly accelerating results and providing valuable insights into vast datasets, often surpassing traditional methods.

This dissertation explores …

Native Wayland Compositing On Apple Ecosystems: Assessing The Feasibility Of “Wawona” Compositor, Alex Spaulding

2026 Symposium

The Wayland display protocol is the modern standard for Linux window management, emphasizing security, performance, and simplicity. Expanding this ecosystem to macOS, iOS, and Android introduces technical hurdles due to proprietary windowing systems and divergent hardware APIs. This research evaluates the feasibility of developing a native Wayland Compositor for Apple and Android, given the closed nature of these ecosystems.

“Wawona” bridges this gap by architecting a native Wayland Compositor capable of executing unmodified Linux applications. The methodology involves implementing the Wayland protocol stack into native abstractions leveraging Metal, Android’s graphics pipeline, and CoreAnimation.

Evaluating Team Formation Strategies With Algorithms, Ethan E. Lopez, Andy Vo

Student Scholar Symposium Abstracts and Posters

Effective teamwork is essential for collaborative learning, yet forming compatible student groups remains a persistent challenge. This study explores how algorithmic team-building methods influence students’ social and academic compatibility overtime. To support this investigation, we designed a visual survey system called “The Disco Ball." Evaluating work ethics, lifestyles, behaviors, and communication styles, students were initially assigned to project teams using one of three conditions: (1) random assignment (control), (2) a “most matches” condition maximizing similarity between students, and (3) a “diverse communication styles” condition designed to balance differing interaction preferences. After an initial collaboration period, students were given the opportunity …

Culturally Inclusive Usability Engineering (Ciue): A Framework For Evaluating Cultural Inclusion In Study Abroad Platforms, Louis Muhammad

Master's Theses

Study abroad programs provide students with opportunities to develop global com- petence and intercultural understanding. However, the digital platforms that support these programs often fail to communicate information that reflects the cultural and faith-based needs of diverse student populations. While prior research in Human-Computer Interac- tion (HCI) and usability engineering has explored cross-cultural and accessible design, cultural and religious considerations are rarely integrated into usability engineering pro- cesses. This thesis introduces the Culturally Inclusive Usability Engineering (CIUE) frame- work, which extends traditional usability engineering by integrating culturally informed con- siderations into the system development lifecycle. CIUE begins by identifying the …

A Machine Learning-Based Apogee Prediction Methodology For Experimental Student Rockets, Price Hamilton Drawdy

Senior Honors Theses

The ability to predict the maximum altitude of a rocket (apogee) in real-time is incredibly useful for collegiate-level competition rockets. This project creates a machine learning-based real-time apogee prediction methodology. Three model types were tested: linear regression, random forest, and a 3-layer multi-layer perceptron (MLP) neural network. These models were trained on a large dataset of simulated flights. All models performed well on simulated test flights, with the linear regression model showing most promise for use on edge compute. More development and real-world testing are necessary to determine how applicable this method is for real-time operation. Nevertheless, this methodology provides …

Parallelism In Java, Matt Vierow

Departmental Honors & Graduate Capstone Projects

Parallelism and multithreading have become an important facet of programming in recent years. Much work has been done in programming languages such as C and C++ with libraries such as OpenMP. However, less effort has been made to create parallelism tools in higher level languages such as Java. This is important because most programmers learn the basics in languages such as Python and Java that lack parallel tools like OpenMP. This means they must directly manage threads which requires knowledge of object-oriented programming and design.

This project sought to incorporate some elements of OpenMP into Java to allow newer programmers …

Effectiveness Of Quiz-Based Interventions In Virtual Reality Lectures On Learning, Mason T. Prather

Master's Theses

This thesis examined whether quiz-based interventions affect learning during an immersive virtual reality (VR) lecture and whether quiz timing strategy matters when prompts are delivered on a fixed timer or through gaze/Region of Interest (ROI)-based attention timing. The study used an eye-tracking virtual reality headset and a game engine-based classroom application. The final completed cohort included 29 participants assigned to three between-subjects conditions: No Intervention (n = 10), Timer-Based Intervention (n = 9), and Attention-Based Intervention (n = 10). All participants viewed the same virtual reality lecture and completed the same 15-item post-lecture assessment. Mean learning scores were 44.00% for …

Generative Ai Of Breast Cancer Progression In Gene Expression Space, Xusheng Ai

All Dissertations

Breast cancer is one of the most common and deadly cancers in the world. Although doctors can use gene activity data to better understand different types of breast cancer, it is still difficult to identify the most important genes and to track how the disease changes over time. This is partly because gene data are very large and complex.

This dissertation develops a computer-based framework to study breast cancer using gene expression data. The work focuses on three goals: creating realistic synthetic gene data, identifying important genes linked to cancer, and modeling how breast cancer changes from normal tissue to …

Robust Hardware Trojan Detection Leveraging Dual‑Domain Features And Stacked Ensemble Learning, Sefatun-Noor Puspa

All Theses

In Cyber-physical systems rely on sensors, communication, and computing, all powered by integrated circuits (ICs). These ICs are vulnerable to malicious hardware attacks, with hardware Trojans being one of the stealthiest threats. Trojans are malicious implants in the circuitry, which are often inserted during design or fabrication stages. This stealthy addition remains dormant until triggered and might cause functional disruptions or sensitive information leakage once triggered. Traditional IC validation methods, such as functional testing and logic analysis, usually fail to capture these subtle anomalies because hardware Trojans are intentionally designed to mimic normal circuit behavior. They often remain dormant under …

Hdra-Fusion: Hybrid Detection With Routed Architecture For Manipulation-Aware Ai Face Forgery Detection, Omar Ebeid

Theses and Dissertations

With the rapid advancements in artificial intelligence-based image generation and manipulation tools, it is extremely difficult to detect if an image is genuine or artificially crafted. Despite extensive research in this area, existing image detection systems suffer from three major problems: suboptimal cross-dataset generalization due to shortcut learning of dataset-specific patterns, unreliable probability estimates due to domain shift, particularly in cross-manipulation evaluation settings, and an inability to detect images manipulated by multiple types of manipulations within a single detection framework. To address these limitations, we propose HDRA-Fusion (Hybrid Detection with Routed Architecture), a framework built on the conclusion that different …

Using Ali-4 Z-Implication In Controller Design, Shamil Azer Ahmadov

Chemical Technology, Control and Management

One of the widely used theories in the information processing is Professor Zadeh's fuzzy logic theory. Fuzzy implications form the basis of this theory. When processing information using fuzzy implication, the chosen judgment method and the type of implication affect the result. Referring to the review of the relevant literature on fuzzy implications, it can be noted that there are still unresolved problems and issues. For example, fuzzy implications cannot be used in processing imperfect information or information based on probabilistic and fuzzy uncertainty. Existing fuzzy implications face limitations in practical applications. Fuzzy implications only take into account inaccuracy, but …

Conceptual Model For Protecting Personal Data By Depersonalization In Information Systems: Principles, Components, And Life Cycle, Zarina Ildarovna Azizova

Chemical Technology, Control and Management

This article presents a systematic approach to personal data protection through depersonalization in the context of regulatory pressure and growing cyber threats. It proposes a comprehensive conceptual model that formalizes the de-identification process as a manageable sequence of steps, from attribute classification and method selection to mandatory verification of the result. The article also provides a comparative analysis of existing depersonalization methods in terms of their applicability within the proposed model. The model serves as a basis for the development of specific algorithms, as demonstrated by the example of a data shuffling approach.

Developing Text-To-Video Ai Workflows Through Creative Practice, Nathan S. Jensen

Staff Scholarship - Australia & Dubai

This creative practice project investigates the extent to which Gen-AI text-to-video tools can maintain coherence across a short multi-shot sequence rather than a single generated clip. This includes continuity in recurring characters, visual style, and simple narrative flow. Using a Creative Practice Scholarship framework and practice-based methodology, I developed Bush Friends, a proof-of-concept children’s television intro, as the artefact of experimentation. This  project combined concept development, storyboard planning, iterative prompting, AI video generation, and editorial assembly using ChatGPT (OpenAI, n.d.) for ideation and prompt development, Kling 3.0 Omni (KlingAI, n.d.) for video generation, and DaVinci Resolve 20 (Blackmagic Design, n.d.) …

Deep Spiking Neural Network Autoencoders For Efficient Temporal Data Compression, Shruti Bhandari

ATU Scholars Symposium

High dimensional temporal data processing, such as that required for neuroprosthetics and remote physiological monitoring presents significant challenges for real time deployment because transmitting and storing raw signals is computationally demanding and energy intensive. Effective data compression is essential to act as a "biological zip file," reducing transmission bandwidth while preserving the critical temporal features required for accurate signal reconstruction and analysis. This study proposes a deep Spiking Neural Network (SNN) Autoencoder designed for high-fidelity data compression by utilizing the event-driven firing behavior of Leaky Integrate-and-Fire (LIF) neurons, which ensures extreme computational efficiency compared to traditional models. The model is …

Generalized Planning Using Language Models And Its Applications, Vishal Pallagani

Theses and Dissertations

Planning is a fundamental capability for intelligent systems, yet classical planners remain difcult to scale and generalize across domains due to their reliance on hand- engineered models, brittle search procedures, and limited adaptability. These limita- tions constrain real-world applications that require fexible reasoning, robust decision- making, and the ability to operate across diverse environments.

Large language models have emerged as powerful learners supported by their ar- chitectures and large-scale training data, demonstrating strong capabilities in tasks such as question answering, code generation, summarization, and reasoning. Moti- vated by their broad generalization abilities, I investigate whether language models can be systematically …

Reconstruction Of Information System Acceptance Model In The Era Of Integrated Artificial Intelligence: A Systematic Literature Review, Ilham, Merlin Apriliyanti

Library Philosophy and Practice (e-journal)

This study aims to explain the rapid development of Artificial Intelligence (AI) which has driven significant transformations in the development and use of information systems. However, most classical information system acceptance models, such as the Technology Acceptance Model (TAM) and  (UTAUT), have not been able to fully explain the unique characteristics of AI-based systems that are autonomous, adaptive, and complex. This study aims to reconstruct the information system acceptance model in the era of integrated AI through a Systematic Literature Review (SLR) approach. This study was conducted using the PRISMA protocol on 130 leading scientific articles indexed by Scopus and …

Learning To Refine Gesture-Derived Voxel-To-Loop For Generative 3d Modeling In Vr, Kallen Lonbom, Trudi Di Qi

Engineering Faculty Articles and Research

We present a generative modeling pipeline for refining and denoising coarse 3D shapes created through freehand interaction in virtual reality (VR). While recent loop-based generative models focus on shape synthesis from clean inputs, our work addresses the challenge of reconstructing coherent geometry from noisy, coarse volumetric data. To this end, we introduce a hybrid voxel-to-loop representation that captures the topology of rough voxel shapes and converts them into sequential cross-sectional loops for generative refinement. We develop two transformer architectures and evaluate their efficacy primarily on synthetically perturbed datasets with additional examples from VR. Our results demonstrate that this representation is …

Influence Of Gender-Specific Data Imbalance On Scgpt Fine-Tuning For Single-Cell Genomics, Mohammad Aman Ullah Al Amin, Daniil Filienko, Hong Qin

The Knowledge and Creativity Expo

The transformer-based foundation model scGPT has demonstrated strong capabilities in analyzing high-dimensional single-cell RNA sequencing data. However, the impact of demographic factors, particularly gender, on model performance remains insufficiently understood. Gender is known to influence cell-type compositions in the immune system. Here, using the gender-sensitive cell-type composition in immune system, we comprehensively evaluated how the gender-sensitive imbalance of training data influences the performance of scGPT in cell-type predictions. We fine-tuned scGPT on male-only, female-only, and mixed-gender subsets from two large-scale datasets containing immune cells. We used a logit difference to measure the confidence gap between the true label and the …

The Writing On The Wall: The Rise Of Applied Ai And The Life-Or-Death Choice Every Ceo Must Make Now, Gary Sheng, Ron Roberts

Digital Laboratory: Publisher of Internet Journal

Applied AI is putting AI to its highest and best use: running your organization as autonomously as possible so you can deliver value for humanity while maximizing the scale of the value. The economy is splitting. Organizations that adopt applied AI are expanding their capacity, accelerating their impact, and pulling ahead. Those that don't are quietly becoming irrelevant, not because they're doing bad work, but because the gap between what they can do and what the moment requires is widening every day. This is not a technology question. It is a leadership question. This paper is written for organizational leaders, …

Time-Robust Evaluation For Multi-Dataset Intrusion Detection Reveals Temporal Shortcuts And Strong Baselines, Kyle A. Mccleary

LSU Master's Theses

Pooled multi-dataset benchmarks are an attractive way to evaluate intrusion detection systems (IDS) across heterogeneous public corpora, but they can quietly reward shortcut features tied to capture schedules and dataset identity. This work introduces TRACER, an auditable benchmark specification that standardizes seven public IDS corpora into a shared transaction-window prediction unit and a shared label ontology, enabling controlled comparisons between compact sequence backbones and strong tabular baselines under matched splits, training budgets, and scoring rules.

Under this protocol, absolute clock time is a strong shortcut under pooled random splits. Enforcing time-robust controls (timestamp rebasing, circular shifts, and schedule-token masking) reduces …

Development Of Hypergraph Based Deep Neural Framework For Precise Cancer Subtyping And Meta Visualization, Pooja G Ms

Theses and Dissertations

Accurate Cancer Subtyping is a cornerstone of modern oncology essential for effective diagnosis and guiding personalized treatment. Histopathological Images (HIs) which capture the microscopic structure of tissues are widely used for cancer detection and subtyping. Even though deep learning has made significant advances, existing HI based subtyping methods often focus on specific cancer types, lacking a generic framework.

A unified framework that can classify multiple cancers with high specificity is desperately needed. In response to these limitations, this thesis proposes a robust multi-cancer, multi-class subtyping framework called DSHGNet (Depthwise Separable Hypergraph Convolutional Neural Network) which integrates Depthwise Separable Convolutional Neural …

Move Fast And Don’T Break Things: Collaborative Privacy Governance In Higher Education, Tyler Schroder, Chad Fenner

Research & Publications

Student-developed applications increasingly replicate or replace official university platforms, often prioritizing speed over security and privacy. This “shadow IT” ecosystem emerges from gaps in institutional tools and is amplified by AI-assisted development, which can introduce insecure defaults. These informal systems risk exposing FERPA‑protected or sensitive institutional data, as seen in student‑built directory and club‑information apps that redistributed restricted information more permissively than intended. While most universities lack clear governance mechanisms for student developers, Yale’s structured, student‑specific data‑use policy offers a notable model. This paper examines these risks and proposes a collaborative, API‑first framework that supports innovation while enforcing privacy, security, …

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 …

Cognivault: Enabling Privacy-Aware Cognitive Distortion Detection In Intelligent Mental Health Applications, Mariam Dawoud

Theses and Dissertations

Mental health applications are increasingly leveraging intelligent systems to sup- port psychological well-being, yet preserving user privacy remains a major concern. This thesis presents CogniVault, a secure ecosystem for cognitive distortion data. The framework includes Cognify, a mobile journaling application that detects cog- nitive distortions in user-written journal entries using a locally deployed machine learning model. Cognitive distortions are maladaptive thought patterns such as catastrophizing or personalization, which the app identifies to provide therapeu- tic insights. To ensure privacy-preserving data analytics, CogniVault includes the design and implementation of a hybrid security architecture, PRISM-HDI, that combines Paillier Homomorphic Encryption (HE), Differential …

Securing U.S. Leadership In Agentic Ai Literacy And Adoption: U.S. Vs Chinese Government Policies And Initiatives, Satyadhar Joshi

Harrisburg University Other Works

This paper conducts a comparative analysis of U.S. and Chinese frameworks for AI literacy and adoption, with focus on agentic AI and Artificial General Intelligence (AGI) systems capable of autonomous reasoning and execution. We examine national policies, educational integration, governance structures, and technological roadmaps, employing both qualitative review and quantitative modeling. Mathematical formulations include multi-dimensional literacy scoring, Bass diffusion models for adoption dynamics, risk assessment functions, regulatory effectiveness indices, competitiveness metrics, and optimization frameworks for resource allocation. Our analysis reveals divergent paradigms: the U.S. Favors decentralized, innovation-driven approaches with emphasis on interoperability and public-private collaboration; while China pursues centralized, state-led …

Comparative Evaluation Of Deep Learning Models: Resnet18, Minivgg, And Yolov8 For Five-Class Blood Cell Classification, Keita Sakurai

Master's Theses or Doctor of Nursing Practice

Accurate classification of blood cell types is a critical task in automated hematological analysis. This study presents a comparative evaluation of three deep learning architectures, ResNet18, MiniVGG, and YOLOv8, for five-class blood cell image classification. To ensure a fair comparison, all models were trained under standardized conditions, including a consistent 90:10 training–validation split, controlled dataset size, and fixed training epochs. ResNet18 was trained to establish a baseline using residual learning. MiniVGG employed a compact VGG-inspired design with regularization to balance efficiency and accuracy, while YOLOv8 leveraged a lightweight, pretrained classification backbone with integrated data augmentation. Experimental results demonstrate a clear …

Data Augmentation And The Reliability Of Conformal Prediction For Uncertainty Quantification In Medical Imaging, Rizwan Ahamed

Graduate Theses, Dissertations, and Problem Reports (ETD)

The safe clinical deployment of deep learning models for high-stakes medical imaging tasks requires more than high average accuracy; it requires demonstrable, per-case reliability. Uncertainty quantification (UQ) provides the missing signal that tells a clinician when a model prediction can be trusted and when a case should be escalated for expert review. Among UQ approaches, conformal prediction (CP) is especially attractive because it produces prediction sets that are guaranteed, under the assumption of exchangeability, to contain the true label with a user chosen probability, and it does so without assumptions about the model or the data distribution. This report first …