Engineering Commons^™

Artificial Intelligence Introduction Section, Seth Newell, Sally Brown

Artificial Intelligence Exhibit

The introduction gives an overview of the exhibition, along with an explanation of AI literacy, AI vs. Google, and a basic AI timeline.

Artificial Intelligence In Education, Sally Brown, Jill Woods, Mohamed Hefeida, Jennifer Sano-Franchini, Megan Vendemia, Erin Brock Carlson, Megan Leight, Gangqing Hu, Nicole Fuller

Artificial Intelligence Exhibit

This section explores the intersection of AI and education, including an overview of WVU's AI statement and submissions from WVU faculty, classes, students, and staff on AI related projects.

Advancing Circular Bioeconomy Through A Systems-Level Assessment Of Food Waste And Industrial Sludge Codigestion, Md Nizam Uddin, Cassidy Hartog, Emma Murray, Jacob Loveless, Luke Roberson, Asli Aslan, Francisco Cubas, Stetson Rowles

Civil Engineering & Construction: Faculty Publications

Disposal of food waste (FW) in landfills remains an unsustainable practice for organic waste management. Simultaneously, pulp and paper mills produce significant amounts of recalcitrant organic waste that is difficult to decompose due to its high lignocellulosic content. In this study, we developed an innovative approach to improve the digestion of pulp and paper mill sludge (PPMS) by amending FW to produce a low chemical oxygen demand (COD) sludge while recovering methane in the process. This codigestion process was evaluated through lab-scale biogas production experiments coupled with a comprehensive economic and environmental sustainability assessment. Biomethane production results revealed that the …

Teaching Learning Newsletter Vol 5 Issue 1, Sastra Deemed To Be University

TLC Newsletter

No abstract provided.

Elucidating The Impact Of Common Stormwater Pollutants On Antibiotic Resistance: The Role Of Heavy Metals, Nutrients, And Salts, Kassidy N. O'Malley, Patrick J. Mcnamara, Walter M. Mcdonald

Civil and Environmental Engineering Faculty Research and Publications

Antibiotic resistance poses a significant global health threat, and the urban water cycle presents an opportunity to augment or limit the spread of antibiotic resistance. In particular, stormwater runoff has recently been revealed as a key conduit for antibiotic-resistant bacteria (ARB). The specific role of stormwater pollutants, however, on antibiotic resistance has not been isolated. Understanding the impact of specific pollutants common to stormwater could help optimize design and operation of stormwater systems for management of antibiotic resistance. The objective of this research was to establish the potential contributions of common stormwater pollutants to antibiotic resistance proliferation. Lab-scale stormwater microcosms …

Response Of Soybean To Variable Irrigation Levels In Eastern Nebraska Using The Aquacrop Model, Anmol Singh

Department of Agricultural and Biological Systems Engineering: Dissertations, Theses, and Student Research

AquaCrop was calibrated and validated for soybean [Glycine max (L.) Merr.] using 19 irrigation treatments from five years using data from field experiments. The model accurately simulated canopy cover (CC), soil water content (SWC), and grain yield, with overall validation nRMSE values of 12%, 7%, and 7%, respectively. The overall validation nRMSE for SWC in individual 30-cm soil layers was comparatively higher, at 19%. The model was subsequently applied for long-term simulations (2010–2024) to estimate soybean yield and water requirements for two dominant soil types, Yutan silty clay loam and Tomek silt loam under three irrigation levels - rainfed, …

Optimization Of Thermoelectric Energy Harvester To Power Wireless Onboard Bearing Health Sensors During Rail Service, Danna Cecilia Capitanachi Avila

Theses and Dissertations

This work presents the optimization of a thermoelectric energy harvester designed to supply power to a wireless onboard bearing health monitoring device for critical freight rail components. The study demonstrates an enhancement in the circuitry through the integration of an energy management subsystem (E-Peas AEM20940), which features a boost converter with lower self-start voltage. The harvesting system was tested on dynamic bearing test rigs to closely replicate field service conditions. Test plans were conducted using common freight speeds and loads to simulate a representative urban route. The thermoelectric energy harvester was able to operate at temperature differentials as low as …

Investigation Of The Effect Of Material Density And Particle Size On Mixed Powder Spreading Behavior In Powder Bed Fusion Process, Alfred Kofi Apianing Achenie

Theses and Dissertations

Powder spreading marks a crucial step in the Laser powder bed fusion process, directly impacting the powder bed uniformity and paving the way for subsequent stages in the process. The laser powder bed fusion process depends heavily on the composition of the metallic powder feedstock. While most existing studies focus on pre-alloyed powders, limited work has explored the use of elemental powder blends as feedstock as used in in-situ alloying. Pre-alloyed powders are often costly, exhibit irregular morphologies and offer limited flexibility in material selection. This study uses Discrete Element Method (DEM) simulations to investigate how variations in material density …

Secure Query On Encrypted Data By Using Fully Homomorphic Encryption, Mrinmoy Bera

Master’s Dissertations

Cloud service providers typically store user data in an encrypted form (data at rest). However, when a user performs a query, the server first decrypts the data, processes the query on plaintext, and then sends the result back to the user (data in transit). This process exposes a critical vulnerability—if the cloud server is ever compromised, the decrypted data becomes accessible to the attacker. To address this security gap, we design a secure query protocol that eliminates the need to decrypt data on the server side. Fully Homomorphic Encryption (FHE) offers a groundbreaking solution by enabling arbitrary computations directly on …

Federated Learning Using Fully Homomorphic Encryption, Sk Golam Kuddus

Master’s Dissertations

Traditional machine learning approaches require centralizing data for training, which raises significant privacy concerns when dealing with sensitive information. Federated learning (FL) addresses this by keeping data local and enabling multiple users to collaboratively train a shared machine learning model. In spite of this, FL remains vulnerable to inference attacks, as sensitive information can still be extracted from the model’s learned parameters. While traditional privacy-enhancing techniques such as di!erential privacy introduce noise to model updates to obscure individual data points, they often present a fundamental trade-o! between privacy and utility. Furthermore, these approaches still carry risks of data leakage if …

Integrating Ensemble Hydrologic Forecasts With Policy Optimization Models For Forecast-Informed Reservoir Operations (Firo), Alessandra Estefania Perez Salas

Theses and Dissertations

Effective reservoir management in hydrologically variable regions such as California’s Central Valley faces increasing pressure to balance flood control, water supply reliability, hydropower generation, and ecosystem health. Traditional rule-based operations, while operationally simple, often lack the adaptability required to respond to real-time hydrologic conditions and forecast uncertainty. This study presents an integration of a policy tree optimization model with ensemble streamflow forecasts to enhance Forecast-Informed Reservoir Operations (FIRO) at Folsom Reservoir. Building on historical data for inflow, storage, and release, an interpretable, threshold-based decision framework was developed and coupled with 14-day ensemble inflow forecasts from the California-Nevada River Forecast Center’s …

Microstructure And Defects Of Aa6061 In The Laser Powder Bed Fusion Additive Manufacturing, Sivaji Karna

Theses and Dissertations

AA6061 is a widely used aluminum alloy known for its excellent thermal conductivity, strength, and corrosion resistance. However, its application in Laser Powder Bed Fusion (LPBF) additive manufacturing is restricted by solidification cracking and porosity. This study examines defect formation, microstructural evolution, and precipitate behavior in AA6061 processed under various LPBF conditions, including room temperature and heated substrates (500°C), as well as pulsed wave laser configurations. Microstructural characterization was conducted using optical microscopy, scanning electron microscopy (SEM) with energy dispersive X-ray spectroscopy (EDS) and electron backscatter diffraction (EBSD), and transmission electron microscopy (TEM).

A maximum relative density of 99.17% was …

Hydrogen Permeation And Mechanical Behavior Of Hydrogen-Charged Cr-Coated And Oxidized Zr-Alloy Fuel Cladding, Daniel Cole Viands

Theses and Dissertations

Following the Fukushima nuclear accident in 2011, accident tolerant fuel (ATF) became a major research interest to enhance the safety of light water reactors. Because the current fleet of light water reactors and their associated fuel cycle infrastructure are well-established, developing ATF that does not significantly alter the current fuel form or change its supporting infrastructure is ideal. Cr-coated Zircaloy fuel cladding is therefore an excellent short-term solution to enhance accident tolerance. Thin layers of Cr-coating offer notable resistance to corrosion, high-temperature oxidation, physical wear, and hydrogen permeation. Cold spray (CS) and physical vapor deposition (PVD) are two well-established Cr-coating …

Legacy Nutrient Transport By Overland Sheet Flow, John E. Gilley, Ryan P. Mcgehee, Kenneth M. Wacha

Department of Agricultural and Biological Systems Engineering: Faculty Publications

The transport of phosphorus (P) and nitrogen (N) from sites containing varying quantities of legacy nutrients was evaluated in this investigation. The data that were examined were collected during four previously reported field hydrologic studies performed in eastern Nebraska. Additional flow was introduced to the top of the rainfall simulation plots to replicate runoff conditions occurring along a hillslope. It was observed that both P and N delivery were influenced by runoff rate on sites where beef cattle manure or inorganic fertilizer had been applied. Legacy nutrient delivery appeared to have been influenced by the quantity of nutrients released at …

Modeling Multiple Tasks In Recommendation Systems, Dinh Hieu Do

Dissertations and Theses Collection (Open Access)

Traditional research in recommendation systems has largely centered on the static offline supervised learning setting. In this paradigm, all available user-item interaction data is collected and partitioned into fixed training, validation, and test sets. Models are developed and evaluated in this controlled environment, where the underlying data distribution is assumed to remain unchanged. This approach offers clear advantages: it simplifies experimentation, enables reproducible benchmarking, and allows for straightforward comparisons between algorithms.

However, this static offline setting does not reflect the realities faced by modern recommendation systems. In real-world applications, data is dynamic and ever-evolving, where new users and items are …

From Sparse Feedback To Sequential Decision-Making: Learning Safety Constraints With Weak Supervision, Siow Meng Low

Dissertations and Theses Collection (Open Access)

Real-world decision-making often involves safety constraints that are implicit, non-Markovian, or difficult to specify directly. Standard reinforcement learning (RL) approaches typically assume access to fully specified cost functions and constraint budgets—assumptions that limit their applicability in domains where such structure must instead be inferred from data. This dissertation develops a sequence of methods for learning safety-relevant structure from weak supervision, such as sparse binary feedback on trajectory segments, and using these signals to guide planning and policy optimization.

The first part of the dissertation introduces a sample-efficient method for planning in continuous Markov Decision Processes (MDPs) using deep reactive policies. …

Numerical Simulation For The Design Of Induction Heating Based Radio Frequency Reactor For Ethylene Production, Hunter Teel, Matthew Craps, Hector-Colon Mercado, Perter Ciesielski, Sirivatch Shimpalee

Faculty Publications

Ethylene is a vital petrochemical compound produced in vast amounts yearly by manufacturers that have enough scale to overcome the inherent thermodynamic inefficiencies of the process. In order to address the inefficiencies that prevent smaller scale or intermittent production ethylene, investigation of new production methods are required. In this work, we investigate the use of a radio frequency (RF) based reactor system that generates heat internally as opposed to applying heat externally via steam or direct combustion of fossil fuels. In order to guide the design of an electromagnetic based reactor system, we have created a macroscale model capable of …

A Comparative Techno-Economic Analysis Of Aqueous And Anhydrous Hcl Electrolysis Processes, O. Felix, K. Likit-Anurak, K. Ngamsanroaj, Sirivatch Shimpalee, Ben Meekins

Faculty Publications

The state-of-the-art aqueous HCl electrolysis process is a well-established process for chlorine production but faces challenges such as limited conversion efficiencies, corrosion, and additional pre- and post-electrolyzer processing steps that add to its cost. This study evaluates whether a recently demonstrated anhydrous HCl electrolysis process is more economically viable than the state-of-the-art aqueous process. A 1D electrolyzer model was developed using Aspen Custom Modeler® and integrated into Aspen Plus® for process modeling. Multiple conversion efficiencies (30.5 %, 50 %, 80 %, and 93.4 %) were analyzed for the anhydrous process, with various heat recovery and heat exchanger configurations assessed using …

Navigating Perceptions: How Organizational Type And Message Source Affect Willingness To Fly In Automated Air Taxis, Cody James Sweatt

Doctoral Dissertations and Master's Theses

A new era of transportation and business is beginning to emerge. Advanced air mobility (AAM), which uses highly automated aircraft that transport passengers and cargo in the underutilized, low-altitude airspace above and around urban areas, is rapidly becoming a reality (FAA, 2023). These new companies will utilize air taxis, which are automated, electric, vertical takeoff and landing (eVTOL) aircraft and will potentially foster a revolutionary new commerce infrastructure. Unfortunately, it is not currently understood how the credibility of a message source or specific type of organization that owns and operates an automated air taxi company influences a customer’s willingness to …

Advancing Food Nutrition Estimation Via Visual-Ingredient Feature Fusion, Huiyan Qi, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Nutrition estimation is an important component of promoting healthy eating and mitigating diet-related health risks. Despite advances in tasks such as food classification and ingredient recognition, progress in nutrition estimation is limited due to the lack of datasets with nutritional annotations. To address this issue, we introduce FastFood, a dataset with 84,446 images across 908 fast food categories, featuring ingredient and nutritional annotations. In addition, we propose a new model-agnostic Visual-Ingredient Feature Fusion (VIF2 ) method to enhance nutrition estimation by integrating visual and ingredient features. Ingredient robustness is improved through synonym replacement and resampling strategies during training. The ingredient-aware …

A Wearable-Based Approach To Spinal Posture Tracking And Assessment, Sydney Marie Sherman, Noah Jeffery

Biomedical Engineering: Graduate Reports and Projects

This paper describes the design, manufacturing, and testing of a novel spinal posture tracking wearable device with embedded sensors. Currently on the market, most of the spinal posture tracking devices only focus on one segment of the spine and therefore do not track the entirety of human posture. The objective for this project was to create a wearable device in the form of a “smart shirt” that offers insights into posture trends throughout the day by tracking the entire spine. To begin the project, multiple designs were developed for the sensor array and wearable materials. These concepts were compared against …

Building A Long Text Privacy Policy Corpus With Multi-Class Labels, David Stein, Florencia Marotta-Wurgler

Vanderbilt Law School Faculty Publications

Legal text poses distinctive challenges for natural language processing. The legal import of a term may depend on omissions, cross-references, or silence, Further, legal text is often susceptible to multiple valid, conflicting interpretations; as the saying goes: a good lawyer’s answer to any question is “it depends.”This work introduces a new, hand-coded dataset for the interpretation of privacy policies. It includes privacy policies from 149 firms, including materials incorporated by reference. The policies are annotated across 64 dimension that reflect the applicable legal rules and contested terms from EU and US privacy regulation and litigation. Our annotation methodology is designed …

Data Annotations, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Pixel-wise object masks for each polarimetric scene in ASL file format for the Model Desert Terrain Monochromatic DoT data.

Distributed Monitoring Of Moving Thermal Targets Using Unmanned Aerial Vehicles And Gaussian Mixture Models, Gustavo Vejarano, Yuanji Huang, Pavithra Sripathanallur Murali

Electrical and Computer Engineering Faculty Works

This paper contributes a two-step approach to monitor clusters of thermal targets on the ground using unmanned aerial vehicles (UAVs) and Gaussian mixture models (GMMs) in a distributed manner. The approach is tailored to networks of UAVs that establish a flying ad hoc network (FANET) and operate without central command. The first step is a monitoring algorithm that determines if the GMM corresponds to the current spatial distribution of clusters of thermal targets on the ground. UAVs make this determination using local data and a sequence of data exchanges with UAVs that are one-hop neighbors in the FANET. The second …

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 …

Hardware Accelerated Simulation Of Buck Converters Using Physics-Informed Neural Networks, James Clayton Crews

Theses and Dissertations

Physics-informed neural networks (PINNs) are an emerging machine learning method for learning the behavior of physical systems described by governing differential equations. Dc-dc power-electronic converters are used in a variety of industry applications such as motor drives or power supplies where real-time simulation is critical for control and safety. This thesis investigates physics-informed machine learning as an approach to develop a real-time digital twin for dc-dc power converters. Traditional numerical integration methods are used to approximate discretized behavior, and the results are compared with a trained PINN model. Modern ML frameworks (such as PyTorch and TensorFlow/Keras) are used to quickly …

Electrochemically Active Liquid Organic Hydrogen Carriers For Energy Generation And Storage, Jinyao Tang

Theses and Dissertations

The growing demand for sustainable energy has spurred interest in hydrogen as a clean energy carrier, yet its widespread adoption is limited by storage and transport challenges. Liquid organic hydrogen carriers (LOHCs) offer a promising solution by enabling reversible hydrogen storage through chemical redox reactions under ambient conditions. Compared to conventional thermal methods, LOHC electrochemistry provides improved energy efficiency, operational safety, and integration into electrochemical systems. However, key challenges remain, such as catalyst deactivation, limited redox reversibility, and low system-level performance that hinder broader application. Alcohols like isopropanol (IPA) and cyclohexanol (CHOL), and amines like ethylamine, have emerged as promising …

Saw Biosensor For The Detection Of Cyanobacteria And Cyanotoxin, Tally Bovender

Theses and Dissertations

The growing prevalence of cyanobacterial blooms and associated cyanotoxins, such as microcystin-LR (MC-LR), presents a significant threat to water quality and public health. Conventional detection methods, including ELISA and PCR, are often time-consuming, expensive, and require trained personnel, limiting their application in field settings. Hence, a miniaturized, quick testing sensor is proposed to circumvent the current sensing challenges for real time, in-situ diagnostics of MC-LR. The proposed high-frequency ultrasonic sensor employs surface acoustic waves (SAW). The sensor was designed using a multi-physics simulation tool to understand wave propagation in the piezoelectric substrate (lithium tantalate) and optimize the design of the …

Design Of Supercritical Reactors To Understand Supercritical Water Oxidation Process And Hydrothermal Flames, Victor Dubceac

Theses and Dissertations

Supercritical water oxidation (SCWO) has been a topic of immense interest as an effective technique/tool for hazardous aqueous waste disposal. SCWO can be achieved by introducing an oxidizer (e.g., H2O2), or a hydrothermal flame as an internal source of both heat and oxidizer species in an aqueous environment at conditions above the critical point of water (P > 218 atm and T > 647 K). SCWO poses important environmental advantages for the treatment of harmful organic materials contained in waste streams. An SCWO reactor has the potential to be compact in design and therefore can be an ideal alternative to existing technology …

Optical And Thermal Characterization Of Vertically Conducting Β-Ga₂O₃ Diodes Grown On 4h-Sic Substrates For Short-Wavelength (<254 Nm) Detection, Muhammad Hassan Tahir

Theses and Dissertations

The advancement of compact, thermally stable, and efficient devices for deepultraviolet (DUV) detection below 254 nm is critical for solar-blind sensing, radiation monitoring, and high-power electronics. This thesis presents the growth, fabrication, and detailed optical and thermal characterization of vertically conducting β-gallium oxide (βGa₂O₃) Schottky barrier diodes (SBDs) grown on n-type 4H-Silicon Carbide (4H-SiC) substrates using metal-organic chemical vapor deposition (MOCVD).

β-Ga₂O₃ is an ultra-wide bandgap (UWBG) semiconductor (~4.8 eV) with intrinsic DUV transparency and high breakdown electric field, making it an ideal candidate for short-wavelength photodetection. However, its low thermal conductivity limits its vertical device performance. To overcome this, …