Engineering Commons^™

Evorgcn: Harnessing Esm-2 Evolutionary Embeddings With Relational Gcns For High-Fidelity Protein-Protein Interaction Prediction, Mohit Kunder

Master's Projects

Accurately predicting protein-protein interactions (PPIs) is essential for understanding cellular function and advancing biomedical discovery. We model PPIs as graphs, where nodes represent proteins and edges denote interactions. Using interaction data from the STRING database, we use two samples of it, namely the benchmark datasets—SH27K and SH148K—filtered by confidence score and annotated by interaction mode (multiple relations). In this project, we present EvoRGCN, a graph-based machine learning framework for PPI prediction that integrates both sequence-level (ESM-2 embeddings) and network-level information. We incorporate various Graph Neural Network architectures, including Graph Convolutional Networks, Graph Attention Networks, and Relational Graph Convolutional Networks. Our …

Synthetic Malware Generation Using Generative Ai, Phanidhar Sai Sravan Chandana

Master's Projects

Malware grows in numbers and complexity, evading conventional signature-and anomaly-based defenses and worsening extreme data sparsity and class imbalance problems for machine learning based detection. Generative models, specifically GANs conditioned on contextual embeddings like BERT have proved effective augmenting training corpora to improve classifier accuracy, but these approaches have largely produced family-specific samples In this paper, we propose a generalized augmentation scheme for generating robust malware embeddings for various families. We begin by extracting opcode sequences from 13 malware families and encoding them into three embedding methods: CountVectorizer, TF-IDF, and BERT’s ‘[CLS]‘ vectors. We therefore train standard GANs and Wasserstein …

Comparative Analysis Of Embedding Techniques With Clustering Algorithms For Malware Opcodes, Ayush Koul

Master's Projects

Malware detection and classification remain critical challenges in cybersecurity, especially as malicious software becomes increasingly sophisticated and prevalent. While much of the work involving embeddings has traditionally relied on supervised learning approaches, there is significant potential in leveraging unsupervised learning techniques to discern hidden structures in malware data. By employing embedding techniques to convert malware samples into high-dimensional vector representations, we can capture the subtle and complex patterns inherent in malicious code without relying on pre-labeled data. This unsupervised approach helps categorize malware into predefined malware families, greatly aiding in developing cybersecurity solutions. In contrast to traditional supervised models that …

Gen Ai For Malicious Network Data, Aneesh Maturu

Master's Projects

Though botnet attacks are on the rise, they also have become sophisticated and difficult to detect. Such a rising threat demands more and more sophisticated cybersecurity that leverages machine learning technology. Nevertheless, one of the biggest bottlenecks remains the unavailability of large and well-balanced datasets, particularly for malicious traffic, which hampers the efficacy of detection models. In an attempt to address this issue, our research utilizes Generative Adversarial Networks (GANs) to produce synthetic samples of botnet traffic from the CTU-13 dataset. While the majority of generative models have been targeting image data, we use GANs for a new application: generating …

Contextual Augmentation In Artificial Intelligence, Emmanuel Joshua Balogun

College of Graduate Studies: Theses & Dissertations

Contextual understanding is a significant challenge of Large Language Models (LLMs), which are typically trained on general-purpose datasets. Due to this, LLMs fail to capture nuanced or domain-specific information and may struggle to interpret user queries accurately. Consequently, prompt engineering can become complex in automating, and LLMs are prone to “hallucinating”—generating random or irrelevant texts—when they lack sufficient context. This undermines their ability to provide focused, accurate responses. Accordingly, this thesis seeks to enhance the contextual understanding capabilities of Artificial Intelligence systems to facilitate more precise and relevant answer generation. Study A looks into a new approach to combating misinformation …

Ecu-Pmu-Fdi/Tsa, Taylah Griffiths, Mohiuddin Ahmed, Chadni Islam

Research Datasets

Cyberattacks are now targeting the electrical grid due to its inclusion of smart devices, e.g., smart meters, phasor measurement units. The need to understand and review the impacts of attacks is vital. ECU-PMU-FDI/TSA encompasses communications between a phasor measurement unit and a phasor data concentrator, using the IEEE C37.118 protocol. Benign traffic was captured as control, and for attacks false data injection and time synchronization attack traffic were captured.

Solar Energy Prediction Using Advanced Hybrid Machine Learning Models, Jelawi A. Alqhtani

UNF Graduate Theses and Dissertations

Accurate short-term forecasting of solar power generation is critical for the reliable and cost-effective operation of renewable-based microgrids, where sudden weather-induced variability can compromise grid stability, battery scheduling, and energy trading decisions. Traditional physical and statistical models struggle to capture the complex non-linear relationships and localized weather effects, while individual deep learning architectures often exhibit systematic biases such as chronic under-prediction of peak generation. This thesis proposes a novel Cross-Feedback Ensemble framework that combines the complementary strengths of Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and one-dimensional Convolutional Neural Network (1D-CNN) models through an iterative cross-feedback mechanism and a …

Quantum-Resilient Architectures For Enterprise And Cloud Information Systems, Implications Of Quantum Computing For Enterprise Cybersecurity And Data Integrity, Manikantha Varaprasad Inakollu

Computer Science and Engineering Faculty Publications

The emergence of quantum computing presents unprecedented challenges to contemporary enterprise cybersecurity frameworks. Current cryptographic systems that protect sensitive data and secure communications will become vulnerable to quantum attacks within the next decade. This research examines the implications of quantum computing advancement for enterprise and cloud information systems, proposing quantum-resilient architectural frameworks that can withstand both classical and quantum threats. We analyze the timeline of quantum computing development, assess vulnerabilities in existing enterprise security infrastructures, and evaluate post-quantum cryptographic approaches suitable for organizational implementation. Through comparative analysis of quantum-resistant algorithms and architectural patterns, this study demonstrates that enterprises must begin …

Blockchain-Enabled Trust Frameworks For Enterprise Information Systems, Establishing Verifiable Trust In Distributed Organizational Environments, Manikantha Varaprasad Inakollu

Computer Science and Engineering Faculty Publications

Enterprise information systems increasingly operate in distributed environments where traditional trust mechanisms based on centralized authority prove insufficient. This research develops a comprehensive blockchain-enabled trust framework that establishes verifiable, decentralized trust mechanisms for enterprise systems operating across organizational boundaries. The study addresses critical gaps in current enterprise architectures where trust depends on centralized intermediaries, creating single points of failure and limiting inter-organizational collaboration. Through examination of existing trust models and blockchain capabilities, we propose an integrated framework that combines cryptographic verification, distributed consensus, and smart contract automation to establish trust without centralized control. Our framework enables organizations to verify data …

Landslide Prediction Using Time-Series Decomposition, Reinforcement Learning-Based Feature Selection And Ml Models, Mohith Sai Venkat Ankem

Master's Projects

Landslides pose significant risks to human life, the community, and the environment, yet their prediction remains a complex and unexplored challenge. Existing prediction models often rely on surface measurements and satellite images, neglecting the critical role, in providing deeper insights into landslide analysis. The literature review highlights a lack of research in time series decomposition techniques, despite their potential to improve prediction accuracy. Similarly, feature selection methods that enhance model robustness and precision have not been adequately addressed. This study presents a novel approach to predicting landslide displacement by combining feature selection through reinforcement learning techniques with advanced time-series machine …

Movie Genre Classification Using Script Texts, Michael Roman Cuomo

Electronic Theses and Dissertations

Genres are used to classify movies so that they can be grouped with others that have similar themes and structures. These classifications are categories created by humans. In the process of creating a movie, a script is often the first creation to write and share ideas about a topic. The script contains large amounts of text that is used to describe the dialog, setting and direction of the film. Although the script contains important information for the film, the amount of text can present a challenge for machine learning algorithms. Often in studies on film classification, if text is used, …

Précis Of The Edge Of Sentience: Risk And Precaution In Humans, Other Animals, And Ai, Jonathan Birch

Animal Sentience

We often face grave practical decisions that seem to hinge on whether a system is sentient. This family of cases includes invertebrate animals, people who are unresponsive after brain injury, fetuses, neural organoids, and now AI technologies. We must decide what to do despite ongoing disagreement about the nature of sentience. In our state of uncertainty, we should pragmatically transform the question from “Is it sentient?” to “Is it a sentience candidate, an investigation priority, or neither?”. When a system is a sentience candidate, it is negligent to fail to consider precautions. We should instead evaluate precautions for their proportionality …

Scalable Mental Health Analysis Using Big Data: A Demographic And Geographic Study Of Depressive Symptoms, Saikrishna Katamneni, Anitha Bommana, Naman Pandya, Gokul Kareti, Sangwhan Cha

Harrisburg University Other Works

This project explores the application of Big Data technologies for large-scale mental health analysis, focusing on the prevalence of depressive disorder symptoms across diverse demographic and geographic subgroups. Utilizing Apache Spark on Google Cloud Dataproc, the system efficiently processed millions of survey records stored in Hadoop Distributed File System (HDFS). Through comprehensive data preprocessing, aggregation, and visualization, the analysis revealed critical trends and disparities in mental health outcomes related to age, race, education level, gender, and state. Seasonal variations and subgroup-specific confidence intervals were also examined to identify high-risk populations and areas of measurement uncertainty. The results offer actionable insights …

Implication And Applications Of Machine Learning On Biomedical Images, Jason Hagerty

Doctoral Dissertations

Medical imaging ranges in modality including computer tomography imaging, x-ray imaging, digital microscopy, and macro-focus dermoscopy images. The latter two modalities are the focus of the presented work.

To perform a diagnostic evaluation on the captured dermoscopy image, it begins with what is usually a labor-intensive operation that requires an expert to perform the initial segmentation for localizing a region of interest (ROI). Once that ROI is obtained, a physician with years of training and experience will observe biological markers that can be used to visually differentiate whether a lesion is benign or malignant. A similar process is used for …

Safe Data-Enabled Control Of Human-In-The-Loop Robotic Manipulator Systems, Ritirupa Dey, Avimanyu Sahoo, Vignesh Narayanan

Publications

Safe control of human-in-the-loop (HIL) robotic manipulators is critical for applications such as assistive robotics, teleoperation in hazardous environments, and collaborative manufacturing. However, this remains challenging due to the lack of a unified framework that simultaneously addresses safety constraints, external disturbances, unmodeled dynamics, and dynamic role switching in the HIL setting. In this paper, we propose a novel NN-driven HIL control framework in which human–robot dyadic interaction occurs through the haptic channel. Using Lyapunov stability analysis, we theoretically show that the proposed NN-based controller ensures accurate joint trajectory tracking, compensates for system uncertainties, and adapts to human inputs modeled as …

An Iterative Shifting Disaggregation Algorithm For Multi-Source, Irregularly Sampled, And Overlapped Time Series, Colin O. Quinn, Ronald H. Brown, George F. Corliss, Richard J. Povinelli

Electrical and Computer Engineering Faculty Research and Publications

Accurate time series forecasting often requires higher temporal resolution than that provided by available data, such as when daily forecasts are needed from monthly data. Existing temporal disaggregation techniques, which typically handle only single, uniformly sampled time series, have limited applicability in real-world, multi-source scenarios. This paper introduces the Iterative Shifting Disaggregation (ISD) algorithm, designed to process and disaggregate time series derived from sensor-sourced low-frequency measurements, transforming multiple, nonuniformly sampled sensor data streams into a single, coherent high-frequency signal. ISD operates in an iterative, two-phase process: a prediction phase that uses multiple linear regression to generate high-frequency series from low-frequency …

Computer Vision-Based Framework For Data Extraction From Heterogeneous Financial Tables: A Comprehensive Approach To Unlocking Financial Insights, Iftakhar Ali Khandokar, Priya Deshpande

Electrical and Computer Engineering Faculty Research and Publications

Information extraction from financial document images is crucial in computer vision and NLP, as financial data often exists in image or PDF format, enabling organizations to analyze and make informed business decisions using OCR advancements. The table contents of financial document images are one of the prominent structures to confine important portions of data of the document and many Deep learning-based methods have been proposed to detect Table regions inside document images. The shortcomings of the current approach are that it is bounded within the detection of the table region and struggles in cases such as handling different layouts and …

Power Utilization In Open Ran: Key Findings From A Usa Testbed, Saish Urumkar, Byrav Ramamurthy, Seshu Tirupathi, Sachin Sharma

Articles

Open Radio Access Networks (Open RAN) provide flexible, scalable, and interoperable solutions to address the growing demands of mobile traffic while also aiming to reduce energy consumption. Most prior research on energy-efficient Open RAN has focused on switching techniques such as dynamic cell on/off strategies and adaptive resource allocation, primarily through simulations. This letter investigates Central Processing Unit (CPU) power utilization at the NodeB (base station) level, focusing on User Equipment (UE) connection states by making use of a USA testbed (i.e., POWDER testbed). Two scenarios are considered for the experimental setup: (1) a simulated virtual environment with a single …

An Optimized Generalized Multi-Color Point Implicit Solver For Intel Gpus Using Oneapi Esimd, Joseph Wassell, Mohammad Zubair, Aaron Walden, Gabriel Nastac, Eric Nielsen, Timothée Ewart

Computer Science Faculty Publications

This paper presents an efficient implementation of a linear-solver kernel relevant to FUN3D, a suite of computational fluid dynamics software developed at NASA’s Langley Research Center. The linear solver is optimized for a range of block sizes commonly used in FUN3D. The implementation targets Aurora, the Argonne Leadership Computing Facility’s (ALCF) exascale machine featuring Intel Data Center Max 1550 GPUs. The linear solver’s performance is memory bandwidth-bound due to its low arithmetic intensity. The primary performance challenges stem from variable matrix row lengths and indirect memory access patterns inherent in unstructured-grid applications. Variable block sizes introduce additional complexity through differing …

Lara : A Light And Anti-Overfitting Retraining Approach For Unsupervised Time Series Anomaly Detection, Feiyi Chen, Zhen Qin, Mengchu Zhou, Yingying Zhang, Shuiguang Deng, Lunting Fan, Guansong Pang, Qingsong Wen

Research Collection School Of Computing and Information Systems

Most of current anomaly detection models assume that the normal pattern remains the same all the time. However, the normal patterns of web services can change dramatically and frequently over time. The model trained on old-distribution data becomes outdated and ineffective after such changes. Retraining the whole model whenever the pattern is changed is computationally expensive. Further, at the beginning of normal pattern changes, there is not enough observation data from the new distribution. Retraining a large neural network model with limited data is vulnerable to overfitting. Thus, we propose a Light Anti-overfitting Retraining Approach (LARA) based on deep variational …

Investigation Of A Busemann Intake At Negative Angle Of Attack, Mark E. Noftz, Andrew N. Bustard, Nicholas J. Bisek, Thomas J. Juliano, Joseph S. Jewell

Publications

A high-speed, shape-transitioned, inward-turning intake was tested in Purdue’s Boeing/AFOSR Mach 6 Quiet Tunnel. The inlet model, called the Indiana Inlet (INlet), had a total contraction ratio of 4.68:1 and a design point of Mach 6 at 0° angle of attack. The model was outfitted with a suite of high-frequency pressure transducers, and the external flowfield was imaged with high-speed schlieren photography. The INlet was tested under low freestream disturbance levels for a variety of freestream unit Reynolds numbers and at-4° angle of attack. An unsteady shockwave near the leading edge of the inlet forebody, indicative of boundary layer separation, …

Rodcast Interaction: A Novel Technique For Dense Virtual Reality Environments, Nevzat U. Demirseren

UNF Graduate Theses and Dissertations

Virtual Reality (VR) technologies continue to grow in popularity and application versatility, yet effective interaction within complex dense environments remains as a critical challenge. In particular, users with low level of VR experience often face decreased accuracy and dissatisfaction selecting occluded objects. A variety of interaction techniques to select and manipulate objects exist, but there is a research gap in understanding what kinds of techniques support users in dense environments. This study evaluates the user performance and preference in such environments. Three interaction techniques are examined in this study: Go-Go Hand, Flower Cone, and a proposed technique called RodCast Interaction. …

Computational Pangenomics And Machine Learning For Genotype-Phenotype Analysis, Tejaswi Vemuri

UNF Graduate Theses and Dissertations

Phenotypes are the observable characteristics of an individual organism. Predicting quantitative phenotypes from genomic variation remains challenging when causal signals span both local motifs and distal regulatory contexts. Building on Frequented Regions (FRs)—subsequences conserved across genomes and extracted from a pangenome graph generated from a large collection of closely related species—we compare several modeling strategies across 35 Saccharomyces cerevisiae growth phenotypes: Random Forest (RF) on FR counts (called RFCounts), RF on FR sequences, 1D convolutional neural networks (CNN) on FR sequences, Long Short-Term Memory (LSTM) networks on FR sequences, a Genomewide Association Study (GWAS) baseline, and a sequence-based transformer model, …

Fast-Sparse-Spanner: A Practical Algorithm For Constructing Low-Stretch Sparse Geometric Graphs, Fnu Shariful

UNF Graduate Theses and Dissertations

When constructing geometric graphs (vertices are points and edges are line segments connecting point pairs) on pointsets, stretch-factor (worst-case detour between any point pair) is often considered a quality metric. A low stretch-factor (a quantity that is usually > 1) guarantees short paths between all vertex pairs. A geometric graph having a stretch-factor of t is known as a t-spanner. Creating low stretch-factor geometric graphs for large pointsets with a low number of edges is an open problem in computational geometry.

In this work, we have designed and engineered a new simple and practical (fast and memory-efficient) algorithm named Fast-Sparse-Spanner algorithm …

Deep Target Recognition: Semi-Supervised Annotation, Sensor Fusion And Super-Resolution, Shoaib Meraj Sami

Graduate Theses, Dissertations, and Problem Reports (ETD)

Despite the recent expansion of machine learning algorithms to cover a wide range of disciplines, several areas of automatic target recognition (ATR) remain underexplored. This dissertation presents tools developed to improve performance in three significant aspects of ATR: semi-supervised annotation, sensor fusion, and image super-resolution. The aim of the semi-supervised methods is to automatically annotate targets in scenarios where labeled data are scarce in the target domain but available in the source domain. Secondly, to address the limitations of individual image sensors and enhance robustness under different environmental conditions and man-made constraints, a sensor fusion algorithm was developed to improve …

Imitation Learning In Robotic Manipulation Using Diffusion Models, Marlon Domingues De Oliveira

Graduate Theses, Dissertations, and Problem Reports (ETD)

This work deals with the problem of teaching robots by demonstration, also known by imitation learning. The main objective of this area of research is to enable the autonomous execution of complex robotic tasks using neural networks trained on expert-generated data, thus allowing the transfer of human knowledge to machines. To this end, this thesis describes an experimental setup especially designed for the study of imitation learning in robotic manipulation tasks and the adaptation and evaluation of a previously published technique to this setup. The experimental setup developed in this work is based on the Franka Emika Research 3 manipulator, …

The Digital Loophole: Evaluating The Effectiveness Of Child Age Verification Methods On Social Media, Fatmaelzahraa Eltaher Ph.D, Rahul Gajula, Luis Miralles-Pechuán, Christina Thorpe, Susan Mckeever

Conference papers

Social media platforms are an integral part of daily life for nearly five billion people worldwide. However, the growing presence of underage users on these platforms raises significant concerns regarding children's exposure to harmful content and its impact on their mental health. This paper examines the effectiveness of age verification measures implemented on leading platforms Facebook, YouTube, Instagram, TikTok, Snapchat, and X. We evaluate the age verification processes required for account creation by simulating the registration steps for minors on these platforms. We also compare these methods to best practices in online age assurance in finance, betting and public transportation …

Generalizing Medical Image Segmentation Task With Efficient Deep Learning Models, Abel A. Reyes-Angulo

Dissertations, Master's Theses and Master's Reports

Medical Image Segmentation is a critical task in the field of medical imaging, playing a crucial role in diagnostics, treatment planning, and disease monitoring. The emergence of Deep Learning (DL) has ushered in a new era in Artificial Intelligence (AI), propelling remarkable advancements in key domains like language translation, object recognition, and recommendation systems. This evolution has been accompanied by continuous enhancements in computational efficiency and improvements in predictive accuracy. The introduction of sophisticated algorithms, such as convolutional neural networks (CNNs) and transformers, exemplifies these advancements. DL algorithms have demonstrated exceptional efficacy in medical image segmentation tasks, showcasing the potential …

Deep Learning For Computer Vision Applications In Medical Diagnostics And Wildlife Monitoring, Mostapha Al Saidi

Electronic Theses and Dissertations

This dissertation explores innovative applications of deep learning and computer vision techniques across three distinct domains: medical imaging, dermatological diagnostics, and wildlife monitoring. The research addresses critical challenges in each field through the development and optimization of convolutional neural networks and other deep learning architectures.

The first study examines COVID-19 classification from X-ray images, comparing one-shot versus two-stage classification approaches using transfer learning with pre-trained models such as VGG16 and VGG19. The initial hypothesis was that breaking down the classification task into two optimized tasks would yield better results than one-shot classification. Results demonstrated that the single-stage approach achieved superior …

Customer Segmentation And Fuel Economy Prediction Using Telemetry Data From Heavy-Duty Trucks, Batishahe Selimi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Heavy-duty trucks constitute only a modest fraction of on-road vehicles, yet their intensive duty cycles and high fuel demands yield a disproportionately large share of transportation fuel use and greenhouse gas emissions. Addressing this imbalance requires data-driven tools that capture the realities of fleet operation and translate complex telemetry into actionable insight.

This dissertation introduces a unified machine-learning framework that operates exclusively on high resolution time-series data collected from fifty-nine diesel trucks deployed across Southern California. It begins by constructing a multi-modal feature space that blends statistical summaries of key engine signals, static vehicle descriptors, and Mel-Frequency Cepstral Coefficients, thereby …