Digital Commons Network^™

Hidden Layer Reshaping On Convolutional Neural Network, Alan Delgado

Open Access Theses & Dissertations

Artificial Intelligence (AI) technologies have become really popular in recent years. From ChatGPT to Tesla cars, many applications can benefit from these type of technologies. Automotive, healthcare, biomedical, cybersecurity, finances, and retail are some of the fields that take advantage of it. It has been seen that AI can solve complex problems, but there is still work to be done to optimize it. A deep learning neural network (DLNN) tries to simulate how a human brain operates. These DLNNs are made up of artificial neurons which are connected by weight that are modified when the network is trained. These networks …

Machine Learning And Time Series Forecasting For Hydropower Predictions, Jose Reynaldo Vega

Open Access Theses & Dissertations

Recent advancements in machine learning have led to the design of many neural network architectures aimed at solving real-world problems. Each network works to make predictions by finding patterns in the provided data. One common application is time series forecasting, where a model predicts future events based on historical time series data. Time series forecasting is used in a variety of fields, one example being in predicting water releases of Hybrid Floating Photovoltaic-Hydropower (HFPVH) systems. As global population growth drives an increase in energy demand, the need for resilient and sustainable energy generation has become urgent. HFPVH systems have emerged …

Achieving Flexible Fairness And Privacy In Federated Learning, Alycia N. Carey

Graduate Theses and Dissertations

Having access to large, high-quality datasets is crucial for training machine learning models that achieve satisfactory performance. Unfortunately, it is common that a single entity (e.g., mobile device or organization) does not have access to such datasets due to monetary or resource constraints. Traditional machine learning requires that all training data reside in a centralized location during the entire duration of model training, however, in many circumstances it is difficult or even impossible (e.g., due to governmental regulations) for multiple parties to combine their data to meet this constraint. Federated learning is a machine learning paradigm that facilitates the joint …

Automation Of Vulnerability And Patch Management: Information Extraction, Association, And Optimization, Kylie Mcclanahan

Graduate Theses and Dissertations

Vulnerability and patch management is an integral part of a robust cybersecurity program, yet it grows increasingly complex due to the sheer amount of data that must be analyzed. Particularly in Operational Technology (OT) environments, analysis must be done manually because of the lack of automated solutions. Additionally, there are many steps in this process, from the initial discovery of the vulnerability to the implementation of its remediation, and each step in the process requires different data in order to be performed effectively. In this work, we provide approaches and strategies to assist operators in industrial or OT environments throughout …

Exploring The Pedagogical Impact Of Software Development Live Streams: Informal Learning Opportunities For Software And Game Developers, Ella Kokinda

All Dissertations

Live streaming is an increasingly popular medium for throwing back the curtain on software development where streamers and viewers share their knowledge and experiences. Popular platforms like Twitch and YouTube enable developers to stream live coding sessions where people around the world can engage in real-time collaboration, feedback, knowledge sharing, and skill development. This work investigates the pedagogical implications and learning opportunities present in software and game development live streaming while focusing on the role of streaming as a learning environment and collaborative community. We begin by exploring summer camps as an informal learning opportunity for STEM education, highlighting the …

Deepfakes On Trial: Developing A High-Accuracy, Court-Admissible Ai Pipeline For Deepfake Detection In Corporate Fraud Litigation, Aiden J. Green

Honors College Theses

As deepfake technology advances, cybercriminals are increasingly using AI-generated videos and audios to impersonate executives and carry out sophisticated CEO fraud schemes. These synthetic forgeries target human trust and corporate communication systems, creating an urgent need for forensic tools capable of authenticating digital evidence with legal accuracy. This thesis presents a forensic-grade AI deepfake detection pipeline designed for this purpose, emphasizing courtroom admissibility, reproducibility, and evidentiary integrity. Built entirely with free, opensource tools, the framework combines metadata analysis, AI-powered spectrogram analysis, neural artifact detection, and facial manipulation recognition into a transparent workflow that accurately identifies synthetic media. It was trained …

Privacy-Aware Ai-Based Agricultural Monitoring Using Internet Of Drones, Md Benozir Hossain

Honors Theses

Artificial Intelligence (AI) has become a vital tool for agricultural farming. AI-based image processing models utilizing different machine learning (ML) algorithms and deep learning (DL) offer advanced functionalities in disease detection, yield estimation, land use, etc. This thesis examines AI-driven techniques utilizing Convolutional Neural Networks (CNN) with the addition of Federated Learning (FL) to analyze satellite and drone images for agricultural insights, especially in detecting Cotton diseases. The AI models improve agricultural farming in many ways, such as using data to make critical decisions, reducing labor costs, pest infestations, etc. Moreover, these models allow farmers to minimize yield losses by …

Towards Explainable And Robust Nlp: Neutrosophic Probability Augmentation In Text Classification, Nabil M. Abdel-Aziz, Mahmoud Ibrahim, Khalid A. Eldrandaly

Neutrosophic Systems with Applications

The rapid growth of textual data necessitates advanced text classification models. However, traditional methods struggle with ambiguity and uncertainty in natural language, reducing classification reliability. To address this, we integrate neutrosophic logic, which explicitly models truth, indeterminacy, and falsity, into a DistilBERT-based text classification framework. Additionally, we employ data augmentation using synonym replacement to enhance generalization. Our approach is evaluated on the AG News dataset, classifying articles into four categories: World, Sports, Business, and Science/Technology. By incorporating neutrosophic attributes, the proposed framework assesses text quality, mitigates uncertainty, and improves robustness against ambiguous inputs. Experimental results demonstrate an accuracy of 94.10%, …

Tailoring Transformer-Based Deep Learning For Code Generation And Translation, Imam Nur Bani Yusuf

Dissertations and Theses Collection (Open Access)

Software is increasingly pervasive in modern society, making the effective translation of human intent into code essential. Novice programmers often struggle with domain-specific code due to limited background knowledge, while experienced developers face challenges in maintaining evolving largescale codebases. Traditional pattern-based approaches address these issues, but such approaches are task-specific and require significant adaptation for different tasks. Transformer-based models offer a more flexible alternative, as the same architecture can be tailored for diverse programming tasks.

This dissertation investigates how Transformer-based models can be customized for various code generation and translation tasks. First, it introduces Transformer-based approaches that assist end-users with …

Evaluation Of Pre-Trained Vision Language Models In Challenging Contexts, Kankan Zhou

Dissertations and Theses Collection (Open Access)

The rapid advancement and proliferation of pre-trained vision-language models (VLMs) have heralded a new era in the realm of artificial intelligence (AI), opening up unprecedented opportunities and challenges alike. This dissertation sets forth on an ambitious and comprehensive journey to critically evaluate the performance and limitations of pre-trained VLMs, particularly in complex and challenging contexts that test the bounds of their capabilities. Our focus is twofold: to rigorously assess the extent of bias embedded in these models, and to meticulously scrutinize their reasoning abilities, highlighting parallels and disparities between machine and human cognition.

We initiate our exploration with a targeted …

Using Natural Language Processing And Machine Learning To Detect Online Radicalisation In The Maldivian Language, Dhivehi, Hussain Ibrahim, Ahmed Ibrahim, Michael N. Johnstone

Research outputs 2022 to 2026

Early detection of online radical content is important for intelligence services to combat radicalisation and terrorism. The motivation for this research was the lack of language tools in the detection of radicalisation in the Maldivian language, Dhivehi. This research applied Machine Learning and Natural Language Processing (NLP) to detect online radicalisation content in Dhivehi, with the incorporation of domain-specific knowledge. The research used Machine Learning to evaluate the most effective technique for detection of radicalisation text in Dhivehi and used interviews with Subject Matter Experts and self-deradicalised individuals to validate the results, add contextual information and improve recognition accuracy. The …

Empirically Exploring The Physical Realizability Of Adversarial Examples, Ruoyao Wen

McKelvey School of Engineering Graduate Student Theses & Dissertations

The development of autonomous vehicles (AVs) has been accelerated by advancements in deep neural networks (DNNs), which power the complex perception systems necessary for safe and efficient real-world navigation. However, as AVs increasingly integrate into public transportation networks, the robustness of their perception systems against potential vulnerabilities is critical. Among these threats, adversarial attacks—particularly through the use of adversarial patches—pose significant risks. These patches are carefully crafted perturbations designed to mislead DNNs, potentially compromising AV safety by causing incorrect object recognition or misclassification.

While extensive research has demonstrated high attack success rates for adversarial patches in controlled digital environments, their …

On Learning Informative Trajectory Embeddings For Imitation, Classification And Regression, Zichang Ge, Changyu Chen, Arunesh Sinha, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

In real-world sequential decision making tasks like autonomousdriving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification,and clustering. For example, self-driving cars must replicate humandriving behaviors, while robots and healthcare systems benefitfrom modeling decision sequences, whether or not they come fromexpert data. Existing trajectory encoding methods often focus onspecific tasks or rely on reward signals, limiting their ability togeneralize across domains and tasks.Inspired by the success of embedding models like CLIP andBERT in static domains, we propose a novel method for embeddingstate-action trajectories into a latent space that captures the skillsand competencies in the …

Animal Burrow Detection In Levee Systems Using Res-Net 34, Christopher D. Moore

LSU New Orleans Theses and Dissertations

Animal burrow detection is a time-consuming and costly task for levee inspectors. Annual budgets run up to approximately $16 million per state. The inspectors typically will have to travel to the inspection sites using government-assigned transportation. Depending on the distance to the site, it may take minutes or hours to arrive before any productive inspections occur. Once at the site, the inspectors were subject to human error, overgrown foliage, severe weather, or prohibitive landscaping that would make any human inspection impossible. Also, animal burrows could be small enough or overgrown, so the human inspector misses the problem areas. We aimed …

Divergence-Free Smoothed Particle Hydrodynamics In A Stream Digital Twin, Austin Hartley

All Theses

Digital Twins (DT) are being explored by the South Carolina (SC) water community to simulate how SC streams will flow at various water levels. Currently, a DT called Gilligan simulates these streams utilizing weakly-incompressible Smoothed Particle Hydrodynamics (SPH). This method does not strictly enforce incompressibility, which leads to unrealistic water flows and unwanted visual artifacts that require post-processing effects to hide. To address these problems and simulate more realistic water flows, the Gilligan stream logic is updated and a state-of-the-art SPH method that enforces incompressibility—Divergence-Free SPH (DFSPH)—is implemented within the Gilligan framework. DFSPH is able to make use of two …

Global Sporadic-E Prediction And Climatology Using Deep Learning, J. A. Ellis, Daniel J. Emmons, M. B. Cohen

Faculty Publications

Sporadic-E (E_s) is an ionospheric phenomenon defined by strong layers of plasma which may interfere with radio wave propagation. In this work, we develop deep learning models to improve the understanding of E_s, including the presence, intensity and height of the layers. We developed three separate models. The first, building off earlier work in (J. A. Ellis et al., 2024, link in AFIT Scholar, 10.1029/2023sw003669), includes only the main features from radio occultation (RO) measurements. The second adds to that time, date, location, geomagnetic and solar indices, solar winds, x-ray flux, weather and lightning. A …

Improving Home Security Through User Centered Device Positioning, Lalith Nadipalli

Theses and Dissertations

In today’s world, where technology is advancing rapidly and security threats are becoming more complex, the need for effective home safety measures is more critical than ever. Homeowners are increasingly turning to a variety of smart devices, such as smoke detectors, carbon monoxide detectors, and security cameras, to protect their living spaces against potential dangers like burglary, fire, and environmental hazards. These devices offer essential protection, acting as both early warning systems and visual surveillance tools. However, their effectiveness largely hinges on how well they are placed within the home. Proper placement of these safety devices ensures that they provide …

Towards Visual Inertial Navigation With Fixed Tetrahedral Targets, Joao Leonardo Silva Cotta

Theses and Dissertations

This dissertation presents a robust method for 6DoF position estimation under impaired visual conditions utilizing a minimum 4-point Perspective-n-Point (P4P) solver designed for tetrahedral targets. Using SO(3) × R 3 instead of SE(3), the method uses a Lie group-based formulation to discriminate between rotation and translation, thereby enabling computationally efficient, resource-conscious op- optimization while preserving correct geometric behavior. Designed using the contemporary C++17 library ShomerTarget, the solver is analytically formulated and assessed under pragmatic robotic conditions. Particularly in low-light and high-dynamic environments, experiments on embedded systems, UAVs, and NASA’s Astrobee show that the proposed solver attains enhanced accuracy compared to …

Cross-Dataset Fairness Evaluation Of Transformer-Based Sentiment Models, Sara Zuiran

Theses and Dissertations

With the growing exploration of Natural Language Processing (NLP) systems in decision-making environments, it is essential to evaluate technical and ethical aspects of the dataset and the NLP model to improve fairness. To assess fairness, the thesis examines demographic imbalances in sentiment classification models by evaluating transformer-based models fine-tuned on the Stanford Sentiment Treebank version 2 dataset (SST-2) against the demographically annotated Comprehensive Assessment of Language Model dataset (CALM). This work identifies performance disparities in sentiment prediction across demographic groups by examining sensitive attributes such as gender and race. The study evaluates both the RoBERTa and MentalBERT transformer models using …

Effects Of Reflective Journaling And Nudges On Academic Motivation And Engagement, Lakshmi Satya Sai Veda Mahita Uppuluri

Theses and Dissertations

This study investigates the effects of reflective journaling and motivational nudges on academic motivation and engagement among college students. Grounded in Self- Determination Theory (SDT), the research examines how different interventions influence intrinsic motivation, and academic behaviors such as class attendance, participation, and preparation. The study employed a between-group experimental design with three conditions: a control group, a journaling group, and a journaling group that also received daily motivational nudges. Results showed that students in the journaling groups—particularly those who received nudges—experienced a significant increase in academic motivation. While changes in academic engagement were not significant, the effect size suggested …

An Analysis Of Face Morphing Presentation Attacks Against Facial Recognition Systems, Joshua Breininger

Theses and Dissertations

Security has been a problem for human society for as long as history has been recorded. The identification of people is an ongoing, ancient battle, with a variety of methods that only become more complex with time. The Romans performed censuses, ciphers have been used for thousands of years in the pursuit of security, and in modern day we own identifications and governments keep track of who lives in their country with citizenship and licenses. The question of ”Who are you?” is vital for society to function, which opens up a massive field of potential for how to ask that …

Personality Trait Recognition Through Deep Neural Temporal Modeling Of Non-Verbal Behavior, Kushal Vangara

Theses and Dissertations

Personality research seeks to explain the wide range of human behaviors through stable, measurable traits. Human interactions are inherently rich and multidimensional, and analyzing behavioral data offers a promising path to uncover personality insights. The increasing convergence of psychology, computer science, and machine learning has fueled interest in computational approaches to personality assessment. Advances in sensing technologies have made it possible to capture fine-grained information about individuals’ behaviors and interactions in naturalistic and controlled environments. Automated audio-visual analysis techniques extract relevant behavioral cues, which machine learning models then interpret to infer underlying personality traits. This work provides a comprehensive overview …

Towards Advancing Streamflow And Peak Flow Prediction With Machine Learning: Identifying Infrastructure At Risk, Sudan Pokharel

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Due to climate change and its impact, the need for adaptive strategies for natural disaster mitigation and resource management has never been more urgent. Central to this is water resource management, which is essential for sustainable human activities, ecological balance, and the mitigation of natural hazards like floods. Streamflow is a crucial element of water resource management and plays a vital role in planning and building water infrastructure, implementing emergency response plans, supporting flood mitigation initiatives, and regulating agricultural and industrial use. However, accurate prediction of streamflow still remains a challenge due to the complex non-linear and non-stationary interaction between …

Robot-Integrated 4d Building Information Modeling (4d Bim): Framework For Planning Safe Autonomous Construction Operations In Dynamic Environments, Hafiz Oyedimeji Oyediran

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

In the construction industry, the use of autonomous robots is considered a solution to overcome the heavy reliance on human workers to perform repetitive, strenuous, and hazardous tasks. While these robots offer the advantage of autonomous operation, ensuring their safe and efficient integration within construction sites requires precise planning. Such planning must account for the varying project complexities such as scope, site layout, tasks, timelines, existence of human workers, and other spatiotemporal conditions of the construction site. Currently, there are no methods to safely plan autonomous robot operations considering these factors within the overarching construction planning process. Thus, autonomous robots …

Physics Embedded Neural Network: A Novel Data-Free Numerical Method For Solving Computational Physics Problems, Pawan Gaire

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

A novel approach for solving partial differential equations (PDEs) using neural networks for scientific computing is introduced. The proposed approach, referred to as physics-embedded neural network (PENN), features a unique architecture that incorporates the PDE and boundary conditions information directly within the final fully-connected layer of the feed-forward neural network (NN). The key aspect of PENN is the parallel numerical embedding of a differential equation associated with physical problems within the activation function of the network’s final layer. This integration leads to a new class of computational solvers competitive with classical methods like the Finite Element Method (FEM) and capable …

A Machine Learning Framework For Packet Anomaly Detection In Smartgrid Substation Networks, Sowmya Bandari

School of Computing: Dissertations, Theses, and Student Research

The increasing reliance on Smart Grid Substation Networks for efficient electricity distribution has amplified cybersecurity vulnerabilities, particularly within Supervisory Control and Data Acquisition (SCADA) systems. The IEC 60870-5-104 (IEC-104) protocol, widely adopted for communication between Remote Terminal Units (RTUs) and Human-Machine Interfaces (HMIs), lacks inherent encryption and authentication mechanisms, rendering it susceptible to sophisticated cyberattacks. Threats such as False Data Injection Attacks (FDIAs), command injection, covert attacks and replay attacks pose significant risks by manipulating grid control signals, potentially leading to undetected operational disruptions, cascading failures, or system-wide instability. Conventional signature-based Intrusion Detection Systems (IDS) often fail to identify zero-day …

Using Machine Learning To Detect Vault (Anti-Forensic) Apps, Michael N. Johnstone, Wencheng Yang, Mohiuddin Ahmed

Research outputs 2022 to 2026

Content hiding, or vault applications (apps), are designed with a secondary, often concealed purpose, such as encrypting and storing files. While these apps may serve legitimate functions, they unequivocally present significant challenges for law enforcement. Conventional methods for tackling this issue, whether static or dynamic, prove inadequate when devices—typically smartphones—cannot be modified. Additionally, these methods frequently require prior knowledge of which apps are classified as vault apps. This research decisively demonstrates that a non-invasive method of app analysis, combined with machine learning, can effectively identify vault apps. Our findings reveal that it is entirely possible to detect an Android vault …

Gamba: Marry Gaussian Splatting With Mamba For Single-View 3d Reconstruction, Qiuhong Shen, Zike Wu, Xuanyu Yi, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang

Research Collection School Of Computing and Information Systems

We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. Existing methods for single-image 3D reconstruction are primarily based on Score Distillation Sampling (SDS) with Neural 3D representations. Despite promising results, these approaches encounter practical limitations due to lengthy optimizations and significant memory consumption. In this work, we introduce Gamba, an end-to-end 3D reconstruction model from a single-view image, emphasizing two main insights: (1) Efficient Backbone Design: introducing a Mamba-based GambaFormer network to model 3D Gaussian Splatting (3DGS) reconstruction as sequential prediction with linear scalability of token length, thereby accommodating a substantial number …

Towards Multimodal Scene Graph Generation Approaches To Video Understanding, Trong-Thuan Nguyen

Graduate Theses and Dissertations

This thesis advances video understanding by enhancing Video Scene Graph Generation (VidSGG) through improved temporal modeling, the integration of long-range temporal dependencies via continuous updates to interaction histories, and the utilization of Large Language Models (LLMs) for scene graph reasoning. To this end, three novel datasets and corresponding approaches are introduced. First, the ASPIRe dataset incorporates interactivity annotations and leverages the Hierarchical Interlacement Graph (HIG) for hierarchical temporal modeling, providing deep insights into scene changes and effectively capturing intricate interactions. Next, the AeroEye dataset, focusing on drone videos, is paired with the Cyclic Graph Transformer (CYCLO), which establishes circular connectivity …

Contrastive Learning Techniques For Fraud Detection, Vinay Madanbhavi Shashidhar

Graduate Theses and Dissertations

Detecting fraud in computing platforms involves identifying malicious user sessions, often using deep learning models, but several challenges hinder effective deployment. Attackers can craft diverse malicious sessions that closely resemble normal ones, complicating the learning of robust decision boundaries. While supervised contrastive learning offers a promising solution through class-specific clustering, its potential remains underexplored. Real-world datasets typically contain few labeled malicious sessions and many normal ones, creating an open-set anomaly detection challenge. Costly expert annotation further limits labeled data, especially for smaller organizations, leading to Positive Unlabeled (PU) learning and noisy label learning issues. Organizations are increasingly turning to LLMs …