Engineering Commons^™

A Maintenance-Aware Machine Learning Framework For Network-Level Highway Pavement Condition Prediction, Jin Hwan Kim, Guk Gon Song, Youngguk Seo

Faculty Articles

This study develops and validates maintenance-aware machine learning models for predicting the Highway Pavement Condition Index (HPCI) on the Korean expressway network. Multiple regression and tree-based models were trained and tested using the pavement condition surveys archived in the Highway Pavement Management System (HPMS). A stacking regressor that integrates random forest, gradient boosting, and extreme gradient boosting as base learners exhibited the most robust predictions. Performance metrics indicated that the stacking ensemble achieved a mean absolute error of 0.21, a root mean square error of 0.31, and a coefficient of determination exceeding 0.73 on the testing dataset. Also, the residuals …

Analysis Of Potential Alkali Reactivity Of Aggregates In Arkansas, Brigita Dowling

Civil Engineering Undergraduate Honors Theses

Alkali Silica Reaction (ASR) is a deleterious chemical reaction in concrete that leads to the deterioration of concrete structures. This reaction occurs between minerals present in aggregates and alkalis in the cement, and produces a gel-like substance called alkali silicate gel. Gradually, these gels absorb water from the environment and expand, leading to internal stresses in the concrete. This damage results in expansion, cracking, and deformation, reducing the strength and durability of the concrete significantly. While this damage appears minor initially, eventually they can lead to the need for costly repairs or replacement of the concrete. ASR has been observed …

Chloronitramide Anion Yields During Monochloramine Formation: Impact Of Reagent Addition Order, Ph, And Mixing, Barrett E. Johnson, Julian L. Fairey, Jason A. Thornhill

Civil Engineering Undergraduate Honors Theses

Chloronitramide anion was recently identified as a decomposition product of inorganic chloramines. Tap‑water concentrations > 300 μg/L reported in a recent study prompted this investigation of chloronitramide anion during monochloramine formation under conditions relevant to drinking water treatment plants. As monochloramine is formed by mixing free chlorine with free ammonia, the impacts of pH, reagent mixing intensity, and reagent addition order were assessed on monochloramine and chloronitramide anion yields. Jar tests were conducted in distilled deionized water at target pH levels of 7 and 9 under rapid, slow, and no‑mixing conditions, with alternating reagent order addition and a target monochloramine dose …

Uav Blast Load Characterization For Structural Design, Jalee Grace Spain

Civil Engineering Undergraduate Honors Theses

As the use of drones, or UAVs, increases, so does the risk of collision with infrastructure. When drones collide with a building, an impact or blast load is applied. Using current literature and structural analysis, a load case can be defined for a blast load induced by a drone.

The Expectation Of Pain: Effects On Threshold, Tolerance, And Perception, Emma Paulus

Mechanical Engineering Undergraduate Honors Theses

Brain activity in pain-related regions of the cortex is thought to be influenced by interactions between expectations and incoming sensory information. However, the subjective experience of pain based on expectation has not been thoroughly explored. By changing visual and auditory cues to set expectation levels, a relationship between unconscious expectation of pain and actual sensory pain experienced was characterized. With IRB approval, volunteers were randomly and blindly grouped into low and high pain expectancy groups. Each group completed a survey about initial pain expectations before the muscle stimulation tolerance test, followed by a survey about actual pain perception after the …

A Forecasting Framework For Distribution Center Capacity Utilization: An Applied Industry Study, Jordan J. Shortt

Data Science Undergraduate Honors Theses

This project develops and evaluates a predictive modeling framework for forecasting distribution center capacity utilization at Company Y, with monthly forecast horizons up to one year. Motivated by the operational challenges of seasonal demand volatility, promotional cycles, and the absence of a formally defined capacity metric, the study first constructs a historical capacity utilization measure from raw warehouse management system data — reconciling item volumes, location dimensions, and utilization factors across all DCs — which serves as the target variable for all modeling work. Four models are developed and evaluated against a naïve seasonal baseline: SARIMA, LightGBM, LSTM, and a …

Small-Scale Analog Spiking Neural Network: Design And Simulation Of An Analog Deep Neural Network, Lucas Hogue

Electrical Engineering and Computer Science Undergraduate Honors Theses

A small-scale analog schematic of a spiking neural network (SNN) is designed and demonstrated through the analog design environment (ADE) within Cadence Virtuoso. An SNN is a type of neuromorphic system that utilizes components mimicking the function of the neurons and synapses found in biological neural networks. The SNN designed in this project is composed of four layers: one input layer, two hidden layers, and one output layer. The inclusion of more than one hidden layer classifies the network as “deep” and increases the network’s efficiency at handling data with increased complexity. The SNN categorizes inputs by producing a set …

​Autonomous Agentic Orchestration For Physics-Aware Scientific Discovery: An Integrative Multimodal Framework For 2d Material Characterization​, Sankalp Pandey

Electrical Engineering and Computer Science Undergraduate Honors Theses

The advancement of next-generation semiconductor and quantum technologies relies on the scalability of the fabrication of two-dimensional (2D) van der Waals heterostructures. However, this process is severely bottlenecked by characterization workflows. Optical microscopy provides high-throughput imaging of 2D material flakes, but lacks the explicit physical priors required for the discernment of sub-nanometer thickness variations, such as distinguishing monolayers from bilayers. The use of computer vision models to automate the localization and characterization process of the flakes was proposed. As a part of this effort, we develop QuantumFlake, an open-source framework to streamline the integration and deployment of computer vision models …

Turning Down The Heat: Fine-Tuning Tempo-Modified Nanocellulose And Emim-Ac Ionic Liquid Membranes For Kidney Dialysis, Olivia Reid

Chemical Engineering Undergraduate Honors Theses

TEMPO modified nanocellulose membranes are utilized across various laboratory and industrial applications from protein purification to advancements in kidney dialysis. This study investigates the effect of varying coagulation temperatures on the morphology and transport properties of these membranes to enhance their performance for targeted filtration. It was hypothesized that higher temperatures would accelerate the solvent-nonsolvent exchange during phase inversion, resulting in larger pore structures. Conversely, lower temperatures were expected to slow solvent diffusion, yielding smaller, more uniform pores. The membranes[JH1]  were synthesized using 2,2,6,6-tetramethylpiperidinyl-1-oxyl (TEMPO) to improve selectivity and antifouling characteristics. Scanning electron microscopy (SEM) served as the primary …

Strengthening Kidney Dialysis One Membrane At A Time: Enhancing Tempo-Oxidized Nanocellulose And Ionic Liquid Membrane Strength Through The Variation Of Cosolvents, Bailey M. Butler

Chemical Engineering Undergraduate Honors Theses

Chronic kidney disease occurs when the kidneys lose the ability to effectively filter the blood, which causes waste build up. End-stage kidney disease (ESKD) is the most severe case of kidney disease and requires either dialysis or a kidney transplant. Hemodialysis, the most common form of dialysis, is an extremely time-intensive and physically burdensome process that is currently limited by membrane performance. The polysulfone (PSf) membranes that are widely used for dialysis today have many limitations, including fouling, toxin rejection, and essential protein loss. Recently, new membranes made from TEMPO-Oxidized nanocellulose dissolved in 1-ethyl-3-methylimidazolium acetate (EMIM-Ac) have shown promising characteristics, …

Shooting For The Stars: Stem Outreach Strategies Between 2nd And 7th Grade, Paige Miller

Chemical Engineering Undergraduate Honors Theses

Engineering and planetary science outreach programs are increasingly important as industries and research organizations face growing demand for STEM professionals. Despite the importance of these fields, many students receive little exposure to engineering careers during their early educational experiences. This honors thesis examines the effectiveness of interactive STEM outreach presentations designed for elementary and middle school students. Specifically, this study evaluates outreach activities centered on chemical engineering applications and the NASA M2M CO₂ regeneration project for Martian environments.

Two student age groups participated in this study: 2nd grade students at Butterfield Elementary School and 7th grade students at Woodland Junior …

Optimizing College Food Pantry Locker Systems Through Simulation Techniques, Jacob W. Holmes

Industrial Engineering Undergraduate Honors Theses

Food insecurity affects 10.5% of households in the United States. Among those affected, college students are a group with increasing food insecurity. Through novel food pantry order methods, such as locker order systems, some effects of college food insecurity can be alleviated. The Jane B. Gearhart Full Circle Food Pantry (FCFP) at the University of Arkansas implemented a locker system, beginning in the Fall of 2020. There is a lack of investigation into locker management policies for pantries, such as how much time clients should be allowed to pick up orders after they are placed in lockers, how many lockers …

Domain-Specific Design On Fpga And Npu For Scientific Computing And On-Device Llm Inference, Miaoxiang Yu

All Dissertations

High-performance computing (HPC) is changing rapidly as scientific simulations and large language model (LLM) workloads push the need for higher performance under tight power and memory constraints. Conventional platforms such as CPUs and GPUs accelerate computation through instruction-driven parallelism, relying on multithreading, SIMD, and SIMT execution, but increasingly encounter scalability limits imposed by the power and memory walls. In contrast, Field-Programmable Gate Arrays (FPGAs) and Neural Processing Units (NPUs) offer a high-efficiency alternative through dataflow-oriented architectures that exploit deep pipelining and customized memory hierarchies to reduce data movement. However, the performance potential of these spatial accelerators remains largely unrealized when …

Physical And Optical Properties Of The Germanium-Arsenic-Selenium Glass Forming Region For Precision Glass Molding And Infrared Optics, Peter F. Wachtel Ii

All Dissertations

The growth and advancement of infrared optical systems for thermal imaging, multi-band imaging, hyperspectral imaging, medical diagnostics, and chemical sensing are pushing the material science community to better understand existing materials while also developing new materials. Additionally, the thermal imaging market continues to grow, and system designers are continually being asked to reduce size, weight, and power while reducing costs (SWaP-c). Market growth has shifted optics manufacturing towards higher volume processes such as precision glass molding, but this does require most materials to be recharacterized due to property changes resulting from the process. Affecting the SWaP-c requirements, manufacturing tolerances are …

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 …

Experimental Data-Driven System Identification Of Scale-Model Airboat Dynamics For Control And Autonomy Applications, Miguel A. Trejos

LSU New Orleans Theses and Dissertations

To achieve autonomous control of a surface watercraft requires an accurate model describing the dynamics of the system. To this end, the modeling of dynamics of an airboat with a combustion engine-based propulsion system is investigated. Specifically, a black-box data-based approach using neural networks. To facilitate this, a custom data collection system was developed to record linear and rotational motion during field tests. Due to the airboats unique ability to traverse different terrains, not just water, the modeling of dynamics on different terrains was investigated.

A Comparative Analysis Of Macro-Scale And Micro-Scale Pcswmm Models For Urban Flood Simulation In The Ormond Drainage System, Binit Gautam

LSU New Orleans Theses and Dissertations

This research utilized an existing SWMM modeling framework of the Ormond area within St. Charles Parish, Louisiana. A micro scale PCSWMM model was updated using GIS Derived values for CN, percent imperviousness, and subcatchment slope and compared to an macro-scale model. Models were compared under several storm events, which included the recent May 14, 2020 storm as well as 2-, 10-, and 100-year design storms. Peak flow, total inflow volume, and hydrograph characteristics were analyzed to assess response of each model.

The results show that the macro-scale model generally produces higher peak flows and total volumes, while the micro-scale model …

Optimization-Based Power Management For Hybrid Towing Vessels: A Comparative Framework Toward Mission-Aware Control, Rachel K. Burchill

LSU New Orleans Theses and Dissertations

This thesis presents an optimization-based framework for power management in hybrid towing vessels operating under dynamic mission conditions. A physically consistent modeling approach is developed, incorporating battery state-of-charge dynamics (SOC), unified power flow, and operational constraints. The framework evaluates rule-based control using fixed heuristic thresholds, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and multi-objective Non-Dominated Sorting Genetic Algorithm II (NSGA-II) under a representative harbor-assist mission profile. Results show that optimization-based methods significantly outperform rule-based control. PSO achieves the lowest fuel consumption and near-perfect tracking with minimal battery use, while GA provides balanced performance with moderate battery utilization. NSGA-II reveals a …

An Alternative To Armageddon: O.P. Weyland And The Development Of Tactical Air Power, Paul Wells

LSU New Orleans Theses and Dissertations

Theorists and advocates of air power argued that aircraft, not ground forces, would become the dominant platform for victory in war. They promoted the concept of strategic bombing, using aircraft to bypass ground forces and directly attack a nation's industrial capacity to wage war, hoping to ensure quick victory and avoid a repeat of the prolonged slaughter in the trenches of WWI. In 1947, led by advocates of strategic bombing, the United States Air Force (USAF) became an independent and equal branch of the U.S. military. The USAF developed the Strategic Air Command (SAC) to meet the requirements of the …

Power System Small-Signal Stability Migration And Metric Trends In A Test System With Increasing Ibr Penetration, Brandon Marshall

LSU New Orleans Theses and Dissertations

With the increasing demand of cleaner energy, inverter-based resources (IBRs) provide a greener alternative to traditional generation methods. IBRs fundamentally work different from traditional generators, though, and power system stability will change as IBRs are integrated into the system. The limitations of IBRs include providing less reactive power support to the system and lacking a spinning rotor for inertia to dampen disturbances. This study examines how small-signal stability is impacted when increasing IBR penetration on a test system. Stability impacts are realized by the migration of eigenvalues and relationships between power system metrics and small-signal stability metrics.

Database State Reconstruction And Audit Log Reconciliation For Data Systems Security, Mahfuzul I. Nissan

LSU New Orleans Theses and Dissertations

Modern organizations rely on diverse database management systems to store critical data across heterogeneous storage architectures. These platforms complicate forensic investigations because database engines vary profoundly in their layouts, encodings, and update policies. Malicious insiders can exploit this architectural opacity to alter data and disable audit logging undetected, leaving investigators with an untrusted view of database activity. Furthermore, building custom forensic solutions for every database version is fundamentally unscalable.

This dissertation advances data-system security through a tamper-aware, cross-layer framework that reconstructs database states and detects unauthorized operations even when audit logs are manipulated. By unifying the analysis of physical storage …

Utility-Scale Battery Energy Storage Systems - Field Pilot Unit Experience, Analysis, And Review Of Technological Advancements, Kwabena A. Kyeremeh, Shaun E. Lavin, Grant M. Fischer, Dan M. Ionel, Aron Patrick

Electrical and Computer Engineering Graduate Research

Utility-scale Battery Energy Storage Systems (BESS) are becoming increasingly important in modern power systems, providing services ranging from backup support to load balancing and peak shaving. The long-term operational performance and reliability of these systems with expanding deployment remain insufficiently documented. This paper provides an operational assessment of a 1MW/2MWh utility-scale BESS alongside a systematic review of technology developments across major subsystems. Operational metrics including round-trip efficiency (RTE), outage characteristics, and degradation patterns are examined to identify performance trends and the underlying causes of outages. In addition, testing and operational principles aligned with utility practice and standards are presented to …

Fatigue And Cyclic Loading In Aircraft Engine Turbomachinery, Sarah Hilliard

Senior Honors Theses

The fatigue and cyclic loading of aircraft engine turbomachinery was explored in order to better understand and predict its failure. This exploration included a review of central topics such as aircraft engine components, fatigue, and the microstructural nature of metal. Also, the ANSYS Mechanical microstructural crystal plasticity tool was evaluated for its utility in fatigue prediction studies. No validation of the tool in question was possible within the scope of this thesis. Numerical fatigue life prediction methods were discussed, and current advancements in metal coatings and surface treatments for prolonging the life of certain superalloys were investigated. Further work in …

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 …

Analyzing The Writing Style Of Generative Ai When Prompted With Writing Samples, Samuel Mcdowell

Senior Honors Theses

Authorship attribution is an important topic in today’s world of Large Language Models (LLMs). It is the technology that helps to verify the author of a written work. This study explores whether LLMs can successfully mimic an individual’s writing style if they are given a text sample. A dataset of human-written texts was collected and used to prompt several LLMs to generate new texts that attempt to replicate the original author’s stylistic characteristics. The generated texts were then tested with modern authorship attribution models to determine whether they would be identified as being written by the original author. The results …

Dor-E: Final Design Report, Arav Singh, August Hogen-Esch, Bruce Le, Patrick Mcgee, Spencer Major

Mechanical Engineering

I. PROBLEM STATEMENT

The Chumash Heritage National Marine Sanctuary contains a diverse array of benthic habitats that remain largely undocumented due to the financial and logistical barriers of deep-sea exploration. Traditional high-end autonomous underwater vehicles and remotely operated vehicles capable of reaching 1000-meter depths require significant surface support infrastructure and hundreds of thousands of dollars in funding. Furthermore, navigating protected ecological zones demands strict adherence to "Leave No Trace" principles. Conventional benthic landers and submersibles routinely leave metallic debris behind; many submersibles use galvanic timed releases that corrode in seawater over a set period of time or heat-activated bolts to …

Boron Nitride Nanotubes Assist The Self-Assembly Of Spherical Cholesteric Liquid Crystal Shells Of Cellulose Nanocrystals In Water, Tanner L. Larson, Brandon J. Heppe, Benjamin S. Flavel, Ralph Krupke, Geyou Ao

Chemical & Biomedical Engineering Faculty Publications

Spherical confinement of cholesteric liquid crystal (ChLC) droplets is emerging as an intriguing approach for achieving complex ordered structures for photonic applications and beyond. Previously, this has been achieved primarily through microfluidic assembly utilizing immiscible solvents or immiscible mesogen-solvent systems, such as oil-water or thermotropic liquid crystal-water systems, respectively. Here, we show the spontaneous assembly of spherical ChLC droplets with isotropic cores from lyotropic liquid crystals of mixed nanorods containing boron nitride nanotubes (BNNTs) and cellulose nanocrystals (CNCs) in all-aqueous environments. We show that the mixing of as low as 0.094 vol % of pectin-coated BNNTs with isotropic dispersions of …

Harness: Hybrid Architecture For Resilience In Networked Engineering System Simulations, Daniel Scott

Graduate Theses and Dissertations

This dissertation presents the development of HARNESS, a unified, domain-agnostic framework for the modeling, optimization, and evaluation of complex systems under conditions of degradation and uncertainty. The research addresses a persistent challenge in systems engineering: the lack of a generalizable, behaviorally grounded approach for quantifying resilience and robustness across diverse domains. HARNESS integrates graph-theoretic dependency modeling, GPU-accelerated evolutionary optimization, and agent-based simulation into a modular architecture that enables both system design and diagnostic analysis. The framework models system interdependencies through user-defined components, parameters, and constraints, allowing architectures to evolve dynamically while maintaining structural validity. A mutation-only genetic algorithm with a …

An Energy- And Area- Efficient Two-Stage Latch Comparator Using Common-Mode Reset, Larry Yu

Electrical Engineering Theses and Dissertations

This thesis presents an energy-and-area-efficient two-stage comparator implemented in TSMC 65 nm CMOS that incorporates a Floating Inverter Amplifier (FIA) followed by a latch using a common-mode reset scheme. The FIA improves input sensitivity and reduces kickback noise by isolating the input nodes from large latch voltage swings. The proposed latch resets its output nodes to a common-mode voltage rather than one of its supply rails, thereby reducing switching energy during the reset phase. The comparator can resolve differential input voltages as small as 2 mV with a clock period of 500 ps, achieving 74.33 μV input-referred noise while consuming …

Modeling Structural Support To Facilitate Novel Treatments Of Degenerative Disc Disease, Jose Luis Calderon

Poster Presentations

Over 600 million people worldwide suffered from low back pain in 2020, with projections for 2050 being over 800 million [1]. Annual costs associated with low back pain total over 450 billion dollars in the US alone [2]. This research serves as a proof-of-concept for the use of structural supports to facilitate intervertebral disc healing. This treatment would involve the implementation of these supports along with existing injection treatments to promote regeneration. In both models, along with the combined model, the ability for these supports to alleviate intervertebral disc height loss is shown. This indicates that these supports would serve …