Engineering Commons^™

Line Outage Impact Factors: A New Approach To Line Outage Detection With Machine Learning, Daniel Flores

Open Access Theses & Dissertations

Electric power systems have become one of our most critical infrastructures as we've grown dependent on electricity for everyday tasks. Ensuring power systems provide reliable service is a priority that can be affected by disturbance events. A common event is transmission line outages, where a line in the system becomes disconnected due to varying forms of physical damage. If an outage isn't detected in time, other lines in the system may overload, causing cascading failures that leave many customers without power. Therefore, having a power system that can automatically detect outages is crucial for reliability, as it promotes real-time response …

A Digital Engineering Framework For Ai-Driven Trade-Off Evaluation And Predictive Component Classification, Alejandro Silva Au

Open Access Theses & Dissertations

This thesis introduces a digital engineering tool designed to help engineers make smarter decisions when choosing actuators. At its core, the system brings together machine learning (specifically XGBoost) and a decision-making method called Multi-Utility Attribute Theory (MUAT). The goal is to support engineers in picking components based on what really matters for their designs, whether that's speed, cost, durability, or any other performance factor. What makes this tool stand out is its user-friendly interface that lets people interact with the system directly. It takes a set of actuator performance data, classifies each one into a relevant use category, and then …

Human Activity Recognition And Identification Driven Automated Deep Learning For Time-Series Classification, Justin Alan Gamble

Engineering Management & Systems Engineering Theses & Dissertations

The growing emphasis on Digital Engineering (DE) within the U.S. Department of Defense (DoD) demands advanced methods for leveraging vast time-series data generated by sensor-rich environments. Deep learning models offer promising solutions for complex timeseries classification tasks, however their design and optimization remain highly resource intensive, requiring specialized expertise. This dissertation addresses this challenge by developing and evaluating an Automated Machine Learning (AutoML) framework specifically tailored for the time-series classification task of Human Activity Recognition and Identification (HARI).

A systematic investigation was conducted using the Design Science Research Methodology (DSRM) comparing traditional search strategies of grid search and random search …

Shape Memory Behavior In Medium To High Entropy Shape Memory Alloys: Design, Prediction, And Experimental Analysis, Hatim Raji

Theses and Dissertations

This dissertation provides a data-driven system integrating synthetic data generation and machine learning (ML) techniques to create multicomponent SMA compositions with specific transformation temperatures (TTs). Models were trained to represent the nonlinear dependencies influencing martensitic transformation behavior by using elemental, thermodynamic, and process-related aspects. The capacity of the ML models on medium entropy NiTiHfPd and high entropy NiTiHfZrCu systems accuracy was confirmed by experimental validation showing TTs closely matched with model outputs.

Decision Field Theory For Human-Multi-Robot Collaboration: Human-Centric Decision-Making For Multi-Robot Systems, Ryan Mbagna Nanko

All Theses

At first glance, choosing between an apple and an orange appears to be a straightforward matter of personal taste; however, this seemingly simple preference opens a window into the multifaceted world of decision-making, revealing the complex interplay of cognitive processes, psychological, and behavioral-economic principles that guide our choices \cite{bandyopadhyayRoleAffectDecision2013}. By unpacking these nuanced perspectives, we uncover insights that can drive more effective human-robot interaction and collaboration.

Modeling human cognition requires understanding the evolution of choice utility and the influence of emotions. Decision Field Theory (DFT) stands out by capturing the fluctuating nature in human preferences over time, explaining why choices …

Effects Of Lossy Compression Data On Machine Learning Models, Max H. Faykus Iii

All Dissertations

Machine learning is a fundamental tool that is incorporated in every field across academia and other industries. Due to the large amount of data needed for training machine learning models, lossy compression plays a crucial role in storing data. Machine learning involves the use of algorithms and models to learn patterns in data. This allows the AI to make decisions without specific programming. On the other hand, compression utilizes encoding and decoding techniques to reduce the size of files. Compression is either lossy or lossless, lossy causes a loss of data while lossless preserves the data. This dissertation will explore …

Simulation- And Machine Learning-Based Methods For Inland Waterway Operation And Maintenance Decision-Making, Maryam Aghamohammadghasem

Graduate Theses and Dissertations

The U.S. inland waterway transportation system (IWTS) is an essential part of the country's multimodal freight transportation network. In addition to seasonal droughts and floods, the operations of the IWTS may be disrupted by random malfunctions and scheduled maintenance of its critical components. Among these critical components, locks play a key role in the operation of navigable inland waterways, and lock-induced disruptions to the supply chains of related industries, such as agriculture and manufacturing, often result in significant economic losses. To assess the performance of the U.S. IWTS, we develop a PyNetLogo simulation tool to capture the movements and delays …

Exploring Methods For Quantifying Uncertainty In Neural Network-Based Turbulence Closures, Cody Grogan

All Graduate Theses and Dissertations, Fall 2023 to Present

Machine Learning (ML) is a very promising field for data-driven modeling of different phenomena. In the field of Computational Fluid Dynamics (CFD), ML is an enticing alternative to traditional methods to improve the accuracy and computational efficiency of simulations. However, many ML models, like Neural Networks, don’t quantify their uncertainty or indicate their confidence in a prediction to those who wish to use them. This is especially important because the use of inaccurate ML predictions in a CFD simulation can greatly impact the validity of a simulation. However, with uncertainty quantification, an ML model can indicate to a modeler the …

Optimal Distributed Energy Resource Control And Scheduling In A Microgrid Framework, Timothy M. Dodge

All Graduate Theses and Dissertations, Fall 2023 to Present

As we use more renewable energy, such as solar power, and add new devices, such as electric vehicle chargers and battery storage, to our buildings, the management of electricity becomes more complex. These local energy sources and devices can form small "microgrids" that need careful coordination to work efficiently with the main power grid. The system figures out the best times to use, store or charge different devices (such as batteries and EVs) to avoid costly, high electricity demand spikes and help stabilize the main power grid, especially when asked by the utility company. A major part of this work …

Discovering And Designing Novel Perovskite Photovoltaic Materials Via Machine Learning, Junyeong Ahn

Discovery Undergraduate Interdisciplinary Research Internship

Perovskite semiconductors are promising materials for high-efficiency photovoltaics due to their outstanding optoelectronic properties, emerging as a sustainable energy source through solar cell applications. Perovskites with the ABX₃ composition (A, B = metal or organic cations with varying oxidation states; X = chalcogen or halogen anions) have gained interest for their excellent phase stability and compositional tunability. However, combinatorial possibilities arising from the many choices of A, B, and X site species, and their respective mixing fractions, a large number of possible ABX₃ perovskites remain undiscovered. In this work, we used machine learning (ML) methods to design new stable and …

Optimization And Acceleration Of Puf Design Through Reduced Order Standard Cell Modeling, Ian Z. Wilcox

Electrical and Computer Engineering ETDs

Application Specific Integrated Circuit (ASIC) designs continue to scale with ever increasing complexity and device counts in the billions. Demand for scalable high-fidelity simulations of these systems drives the need for the development of novel modeling capabilities. This research formulates a non-intrusive model order reduc-tion (MOR) framework, called PUF-ROMS, to accelerate and optimize the design and analysis of physical unclonable functions (PUFs) on ASICs. The primary goals of PUF-ROMS are to estimate entropy and temperature-voltage noise (TV-noise) of circuit structures used in the design in an accelerated evaluation environment to enable designers to explore architecture options with the goal of …

Design For Additive Manufacturing: Simultaneous Optimization Of Structural Integrity And Minimal Support Structures, Naresh Ahuja

Doctoral Dissertations and Master's Theses

This dissertation addresses two core challenges limiting the widespread application of Topology Optimization (TO): the difficulty in fabricating its complex designs, especially for Additive Manufacturing (AM), and its significant computational costs. It develops a unified design framework that directly embeds AM constraints such as overhang angles and build direction into robust TO formulations. To enhance manufacturability, two distinct methodologies are proposed. Firstly, a Solid Isotropic Material with Penalization (SIMP) framework introduces a three-stage robust optimization algorithm. Secondly, the Geometric Projection Topology Optimization (GPTO) method inherently integrates overhang constraints by controlling individual geometric components and their inclined angles relative to a …

Energy Equity In The Built Environment: Analyzing Building Energy Consumption For American Low-Income Households, Sorena Vosoughkhosravi

LSU Doctoral Dissertations

The built environment consumes a significant amount of energy in the United States, with outdated and inefficient affordable housing increasing financial pressure on low-income households (LIHs) who face high energy burdens. This research aims to assess the energy performance of American households, focusing on LIHs, to promote energy justice by providing data-driven insights and models for energy efficiency improvements. More specifically, this research aims to (1) create a large-scale national residential building energy dataset by integrating the American Housing Survey and the Residential Energy Consumption Survey using machine learning techniques; (2) analyze and model American household occupancy profiles by leveraging …

Seconds From Impact: Anticipatory Vehicular Crash Prediction Using Video Vision Transormers, Ryan P. Geisen

Master's Theses

Vehicular collisions represent a significant public health concern, necessitating re search into advanced emergency notification systems. While deep learning has shown promise in accident detection, a research gap persists in applying state-of-the-art transformer architectures to the task of anticipatory, real-time crash prediction from video. This thesis addresses this gap by developing and evaluating a Video Vision Transformer (ViViT) for the binary classification of imminent vehicular collisions. Utilizing a curated dataset of 1,493 unique collision sequences, this study systemati cally investigates the impact of temporal context by comparing the ViViT against a single-frame Vision Transformer (ViT) baseline and conducting comprehensive exper …

Towards Efficient Privacy-Preserving Deep Learning: He-Friendly Structures, Flexible Pruning, He-Efficient Architectures, And Secure Transformer Token Drop, Yifei Cai

Electrical & Computer Engineering Theses & Dissertations

Deep learning (DL) has become a powerful tool for solving complex problems, but developing DL models typically requires vast datasets, high computational resources, and expert knowledge—barriers that limit accessibility. Machine Learning as a Service (MLaaS) addresses this challenge by allowing resource-rich providers to deliver pre-trained DL models as services. However, privacy concerns arise: clients hesitate to share sensitive data, while providers protect their proprietary models. To address this, privacy-preserving MLaaS integrates cryptographic techniques into DL computations, as seen in frameworks like Cryptonets, SecureML, GAZELLE, CrypTFlow2, Cheetah, and BOLT. Among them, Homomorphic Encryption (HE) enables computation on encrypted data but remains …

Advancements In Human Action Recognition In Manual Material Handling Using Machine Learning, Jesus Jimenez, Joni Mccawley, Francis A. Mendez Mediavilla, Abhimanyu Sharotry

International Material Handling Research Colloquium

No abstract provided.

Ai-Driven Emi Mitigation For Smart Healthcare: Generative Adversarial Networks And Edge Computing For Reliable Medical Systems, Mona Esmaeili

Electrical and Computer Engineering ETDs

Electromagnetic interference (EMI) from radio frequency (RF) sources poses a major challenge to digital systems, especially in high-electromagnetic environments. Tradi- tional electromagnetic compatibility (EMC) analysis often focuses on continuous wave (CW) interference and overlooks the effects of waveform modulation on EMI coupling. This thesis explores how modulated waveforms influence EMI coupling and introduces a Generative Adversarial Network (GAN)-based classification framework to distinguish between harmful and non-harmful EMI signals. The study extends conventional EMC analysis using machine learning (ML), showing that modulated EMI waveforms can in- crease coupling by up to 27% compared to CW signals. This highlights the need for …

Hierarchical Reinforcement Learning (Hrl) In Multi-Goal Spatial Navigation With Autonomous Mobile Robots, Brendon Johnson

USF Tampa Graduate Theses and Dissertations

Hierarchical reinforcement learning (HRL) is hypothesized to be able to take advantage of the inherent hierarchy in robot learning tasks with sparse reward schemes, in contrast to more traditional reinforcement learning algorithms. In this research, hierarchical reinforcement learning is evaluated and contrasted with standard reinforcement learning in complex navigation tasks. We evaluate unique characteristics of HRL, including their ability to create sub-goals and the termination function. We constructed experiments to test the differences between PPO and HRL, different ways of creating sub-goals, manual vs automatic sub-goal creation, and the effects of the frequency of termination on performance. These experiments highlight …

Embedding-Based Deep Learning Frameworks For Multimodal Oncology Data Integration, Aakash Gireesh Tripathi

USF Tampa Graduate Theses and Dissertations

This dissertation presents a cohesive set of novel frameworks developed to address critical challenges in oncology data integration, representation learning, and clinical information extraction. The work encompasses four interconnected projects: MINDS (Multimodal Integration of Oncology Data System), HoneyBee (Harmonized ONcologY Biomedical Embedding Encoder), LLM Extraction (Large Language Model-based Extraction from Pathology Reports), and EAGLE (Embedding Analysis for Generalized Learning in Oncology). Together, these systems enable the unification of diverse cancer data modalities—from genomics and clinical records to histopathology images and radiological scans—creating a robust foundation for advanced machine learning applications in precision oncology. By addressing key barriers in data accessibility, …

Data-Driven Machine Learning Applications For Predictive Modeling Of Petrochemical And Ecofrendly Systems, Noora Al Mansoori

Thesis/ Dissertation Defenses

Traditional experimental approaches in industrial processes, such as Fourier Transform Infrared Spectroscopy (FTIR) spectroscopy, thermogravimetric analysis (TGA), and well-drilling operations, are often constrained by time, cost, and operational limitations. This research explores the application of data-driven Machine Learning (ML)-based predictive modeling to improve efficiency and reduce dependency on resource-intensive experimentation. The study develops ML models for three distinct processes: FTIR intensity prediction of bitumen thermal cracking products, thermal degradation of Medium-Density Fibreboard (MDF) using TGA data, and Rate of Penetration (ROP) prediction in petrochemical industry. Six algorithms: Linear Regression (LinReg), Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Gradient …

Multi-Parameter Optimization Of Brine Desalination Using Machine Learning, Elaf Mman Seif

Theses and Dissertations

Air Gap Membrane Distillation (AGMD) is a promising desalination technology with significant potential for addressing global water scarcity. However, the interplay of operational parameters significantly impacts its performance, making optimization a challenging task. This research focuses on brine desalination as a means to mitigate the negative environmental impacts of brine disposal which will eventually help in provide a sustainable solution for handling brine while producing freshwater. The study seeks to develop a predictive model and optimize the AGMD process for efficient brine desalination. To achieve this, Response Surface Methodology (RSM) and Artificial Neural Networks (ANNs) were utilized to develop predictive …

Ergonomic Human Robot Handovers Using Surface Electromyography (Semg) Sensors, Maya Murphy, Michael Mishkanian

Electrical and Computer Engineering Senior Theses

For decades, robots have been kept in cages in industry. With the advances of collaborative robots and Artificial Intelligence (AI), there is a shift towards humans and robots working together. In this research, we propose an ergonomically friendly collaborative robotic cell that enables a human and a collaborative robot to work synergistically to assemble a mobile robot. The collaborative robot provides the parts while explaining the process through a computer, and the human co-worker follows the instructions to complete the assembly. The proposed collaborative robotic cell is evaluated in a user study to ensure that the handovers of the parts …

Exploring The Interplay Between Economic Growth And Sustainable Development: A Complex Systems Approach To Gsdp And Sdgs In Indian States, Rosewine Joy, Helen Josephine, Divya D, Midhun Raj

Northeast Journal of Complex Systems (NEJCS)

Pursuing Sustainable Development Goals (SDGs) necessitates aligning business and management practices on a global scale. This paper delves into the intricate dynamics between Gross State Domestic Product (GSDP) and SDGs across diverse states in India, offering nuanced insights to policymakers, businesses, and stakeholders. This paper explores the dynamic relationship between Gross State Domestic Product (GSDP) and the Sustainable Development Goals (SDGs) in the context of India's diverse states by applying modern machine learning techniques such as XG boost, Decision trees, and K mean clustering. The study delves into how economic growth influences the progress towards SDGs. The research integrates complex …

Investigation And Prediction Of Excessive Water Production In Bottom Water-Drive Naturally Fractured Reservoirs Using Machine And Deep Learning, Sami Abderraouf Belkhir

Theses

Naturally Fractured Reservoirs (NFRs) are characterized by dual-porosity and dual-permeability systems, posing significant challenges in managing water production due to highly conductive fracture networks that facilitate rapid water migration from bottom aquifers, often bypassing oil stored in the matrix, thus resulting in early water breakthrough and water channeling phenomena. The main objective of this thesis is to develop and validate deep learning and machine learning models to predict water production, water breakthrough time (tbt), and ultimate water cut (WCult) in NFRs, thereby enabling more effective reservoir management strategies. This work also aims to evaluate the sensitivity of water behavior to …

Data-Driven Machine Learning Applications For Predictive Modeling Of Petrochemical And Ecofriendly Systems, Noora Saleh Al Mansoori

Theses

Traditional experimental approaches in industrial processes, such as Fourier Transform Infrared Spectroscopy (FTIR) spectroscopy, thermogravimetric analysis (TGA), and well-drilling operations, are often constrained by time, cost, and operational limitations. This research explores the application of data-driven Machine Learning (ML)-based predictive modeling to improve efficiency and reduce dependency on resource-intensive experimentation. The study develops ML models for three distinct processes: FTIR intensity prediction of bitumen thermal cracking products, thermal degradation of Medium-Density Fibreboard (MDF) using TGA data, and Rate of Penetration (ROP) prediction in petrochemical industry. Six algorithms: Linear Regression (LinReg), Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Gradient …

Leveraging Machine-Learning Algorithms In Two Car Crash Detection Systems On A Custom Dataset, Addison Jacob Sandvik

Master's Theses

Traffic accidents pose a significant threat to public safety, causing millions of deaths and injuries worldwide each year. While efforts to reduce accidents have seen limited progress in recent years, improving emergency response times through automated detection systems is a promising avenue for saving lives. This thesis describes the development of machine learning-based traffic accident detection systems, exploring both video classification and image detection models. The models are trained on a new dataset deemed the Cal Poly Traffic Accident Dataset, an extension of the existing Car Accident Detection and Prediction (CADP) dataset with a precise collision annotations. Two systems were …

Streamlined Intelligence: Resource-Efficient Machine Learning For 5g Nr V2v Channel Equalization, Jacqueline G. Radding

Master's Theses

As autonomous vehicles continue to evolve, reliable and efficient real-time communication between vehicles is essential for safety and performance. This thesis explores Streamlined Intelligence: Resource Efficient machine learning for 5G NR V2V Channel Equalization, focusing on lightweight random forest decision tree models to address the challenges of channel equalization in 5G New Radio (NR) vehicle to vehicle (V2V) systems. Using orthogonal frequency division multiplexing (OFDM) with QPSK modulation, the study simulates data transmission in nonlinear channels characterized by obstructions, Doppler shifts, and fading. Decision trees are proposed as a computationally efficient alternative to other machine learning methods while being compared …

Deeppanorf: Deep Prior For Neural 3d Reconstruction From Sparse Panoramas, Edward Du

Master's Theses

Advances in neural field representations have led to a significant improvement in view synthesis quality. However, many current novel view synthesis methods rely on a dense set of input views, which can be impractical and inefficient in real-world applications. We propose DeepPanoRF, a novel method for 360◦ scene reconstruction from a sparse set of input equirectangular panoramas. Built upon K-Planes, a radiance field representation that encodes explicit features on orthogonal feature planes, our method does not directly learn feature grids. Instead, we parameterize the feature grids to enable sparse view reconstruction without pretraining or additional regularization. We implement a custom …

An Analysis Of The Power Consumption Of Various Computer Vision Machine Learning Techniques On A Microcontroller Utilizing The Clusterduck Protocol, Kaveh Shafiei

Electrical Engineering

Constant data processing is essential for effective data collection, particularly in remote and hard-to-reach areas. The need for efficient, autonomous data acquisition and transmission is increasingly addressed by integrating machine learning within larger communication networks. This paper explores the application of machine learning techniques with Internet of Things (IoT) mesh networks. Utilizing the LoRa communication protocol, data is captured and analyzed on an edge device and transmitted to a larger communication network. The ClusterDuck Protocol (CDP), developed by OWL Integrations, serves as an IoT mesh network designed to allow for communication in areas lacking traditional static infrastructure such as WiFi …

Load Balancing In Mobile Networks Using Deep Reinforcement Learning And Traffic Prediction, Shorouk Raafat Mokhtar Abouamasha

Theses and Dissertations

Wireless communication networks are advancing at a rapid pace, driven by various challenges and ambitious goals. This rapid growth is driven by a range of applications, including technologies like the Internet of Things (IoT), as well as innovations in smart cities, autonomous vehicles, and more. Different applications demand specific performance criteria such as high data throughput, low latency, robust reliability, and efficient energy usage. In this thesis, we investigate two enhancements that can be adopted in wireless networks to tackle the challenges of resource optimization and network management. The motivation behind this is the fact that future networks will face …