Engineering Commons^™

Generative Ai-Based Optimized Recommender System For Debt Collection Using Large Language Models, Keerthana S

Theses and Dissertations

Reducing the percentage of defaulters who often skip payments throughout the debt collection process might help minimize losses in the banking industry. The debt collection process should be optimized to reduce the rate of defaulters and improve collection rates. Traditional Machine Learning algorithms focused on credit risk analysis, defaulter prediction, and forecasting the recovery rate of debt collection. Researchers are not currently prioritizing the analysis of debt collectors’ performance. The debt collector’s primary responsibility is to retrieve outstanding debts from consumers on behalf of the debt collection firm.

Examining debt collectors’ performance is essential to enhance collection efficiency in the …

Heat Transfer In Tightly Packed Cylinder Arrays, Martin Kovachev

Doctoral Dissertations and Master's Theses

Cylindrical arrays with a cross flow are commonly used for heat transfer augmentation within an internal channel. In most applications, the cylinders have a spacing of over 2 diameters (2D) between their center points in both the lateral and downstream directions. One option for battery thermal management in hybrid/electric aviation is to use cylindrical batteries packed in arrays with an applied cross flow. In the context of aviation, it is important to maximize space and weight savings. Tightly packing these cylinder arrays with a spacing of under 2D in both directions would save on both of these yet have not …

A Low-Complexity Algorithm For Trajectory Generation In The Three-Body Problem, Brian P. Baker-Mcevilly

Doctoral Dissertations and Master's Theses

The Cislunar realm holds intrinsic value for scientific, commercial, and military applications as numerous entities have begun to invest resources into the expansion and utilization of the region. As the Cislunar region continues to grow, there is an escalating need for efficient methods of trajectory generation in this multi-body dynamical system for computationally limited systems. Thus, a low-complexity classical algorithm is proposed to achieve accurate orbital trajectories in the three-body problem. The proposed algorithm solves a polynomial interpolation problem, formulated using state measurements, through the unique decomposition of a dense system into sparse matrices. Several relevant Cislunar trajectories are simulated …

Nasa Microgreen Cultivation In Space Utilizing Pegda Hydrogels, Thomas Alarcon Ali, Zohaib Gabriel Khan, Ariel Marroquin, Samuel Martinez, Fabiha Samiha, Emily Yong

Publications and Research

During long-term space expeditions, it is crucial that astronauts receive the nutrients they need to maintain their overall health. While the current space diet of palatable foods is commendable and constantly evolving, nutritional content and food quality degrades over long durations. Microgreens are excellent candidates for space cultivation because they are nutrient-dense, young plants that are are densely grown and harvested when leaves are just emerging. However, antigravity, microgreen fragility, degradation speed, contamination, and limited water resources are substantial barriers to doing so. This study aims to address these challenges by cultivating microgreens inside a hydrogel, a soilless medium, to …

Complex Precipitation Behavior In A Co-Free High Entropy Alloy During Aging, Matthew Luebbe, Fan Zhang, Jonathan D. Poplawsky, Jiaqi Duan, Haiming Wen

Materials Science and Engineering Faculty Research & Creative Works

High entropy alloys (HEAs) demonstrate high strength, thermal stability, and irradiation resistance, making them desirable for applications in nuclear reactors and other harsh environments. Many existing HEAs contain cobalt (Co), which makes them unsuitable for nuclear applications due to the long-term activation of Co. A previously studied Co-free alloy, (Fe_0.3Ni_0.3Mn_0.3Cr_0.1)₈₈Ti₄Al₈, exhibits high strength but compromised ductility due to its network of brittle precipitates upon aging. This work investigates the formation mechanism and evolution of the precipitates, including L1₂ (Ni₃Ti type, ordered face-centered cubic …

Sustainability Assessment Of Photovoltaic Cells In Cross-Functional Applications, Achyuth Ravilla

Dissertations and Theses

Achieving the G7 countries' net-zero emissions target by 2050 requires integrating photovoltaic (PV) systems into diverse cross-functional applications that support sustainable energy transitions across multiple sectors. This dissertation explores the economic and environmental sustainability of three such applications: agrivoltaics, lower-dimensional materials in perovskite solar cells, and PV-electrochemical water-splitting technologies for hydrogen production. Employing life cycle assessment (LCA) and techno-economic analysis (TEA), we address the knowledge gap in comprehensive evaluations of PV-integrated solutions.

The first chapter assesses agrivoltaic systems (AVS), which combine PV systems with agriculture to mitigate land-use conflicts while enhancing food and energy production. Findings indicate that AVS designs, …

Holomind: Engineering Mindfulness Through Holographic Display, Hannah Bauer, Jaime Song

Student Scholar Symposium Abstracts and Posters

Our research project, HoloMind, explores the potential of developing interactive experiences using a holographic display to engage the audience in relevant education, and wellness outcomes. To accomplish this aim we are using the Dreamoc HD3.2 by Realfiction, which provides a passive playback of preloaded 3D visuals. The first step in our methodology is to get familiar with the Dreamoc HD3.2 hologram, create 3D visuals, and uncover design guidelines and best practices for creating 3D visualizations. To create 3D visualizations, we are using Adobe Substance 3D Stager. Then, we adapt Realfiction’s template in Adobe After Effects to precisely fit the specific …

Valve Train Design And Material Testing, Luis Luna

Publications and Research

In automotive engineering, CAD software like SolidWorks enables engineers to design and simulate mechanical components efficiently, reducing the need for extensive prototyping. This project examines the rocker arm's performance and durability within a valve train system. Components like pushrods, camshafts, and rocker arms control air intake and exhaust timing. Due to its high-impact motion and exposure to elevated temperatures, the rocker arm endures considerable wear. This study uses SolidWorks and Finite Element Analysis (FEA) to analyze the rocker arm's stress, deformation, and wear potential during camshaft movement. Material testing and motion analysis results provide insights into improving the durability of …

Empathy And Academic Achievement Among Black/African American College Students In An Hbcu, Hyung Nam Kim

Journal of Educational Research and Practice

Empathy is the ability to understand the thoughts, behaviors, and feelings of others. In addition to fostering strong relationships and overall personal growth, empathy plays a crucial role in college students achieving positive academic outcomes. However, a knowledge gap exists concerning the role and impact of empathy among college students, particularly Black/African American students at historically Black colleges and universities (HBCUs). This research aims to address this gap by examining those students’ empathy levels and their association with academic achievement. The study found relatively low levels of empathy and a negative association between empathy and academic performance. Further research is …

Deciphering Mechanochemical Influences Of Emergent Actomyosin Crosstalk Using Qcm‑D, Emily M. Kerivan, Victoria N. Amari, William B. Weeks, Leigh H. Hardin, Lyle Tobin, Omayma Y. Al Azzam, Dana N. Reinemann

Faculty and Student Publications

Purpose: Cytoskeletal protein ensembles exhibit emergent mechanics where behavior in teams is not necessarily the sum of the components’ single molecule properties. In addition, filaments may act as force sensors that distribute feedback and influence motor protein behavior. To understand the design principles of such emergent mechanics, we developed an approach utilizing QCM-D to measure how actomyosin bundles respond mechanically to environmental variables that alter constituent myosin II motor behavior.

Methods: QCM-D is used for the first time to probe alterations in actin-myosin bundle viscoelasticity due to changes in skeletal myosin II concentration and motor nucleotide state. Actomyosin bundles were …

Substantial Gas Enrichment In Shales Influenced By Volcanism During The Ordovician–Silurian Transition, Yujie Yuan, Songtao Wu, Emad A. Al-Khdheeawi, Jingqiang Tan, Zhuo Feng, Zhenjiang You, Reza Rezaee, Han Jiang, Jun Wang, Stefan Iglauer

Research outputs 2022 to 2026

The substantial gas enrichment in shales of the Ordovician–Silurian transition is associated with the development of the organic matter (OM)-rich source rock. While organic matter enrichment has been linked to intensive volcanism, it remains a challenge to precisely evaluate the impact of the volcanism on substantial gas enrichment containing the largest gas storage capacity. This study focused on consecutive borehole shale samples from the Wufeng–Longmaxi formations during the Ordovician–Silurian transition in southern China. We conducted a comprehensive analysis, integrating the major geological volcanism with high-resolution analysis, including QEMSCAN, argon-ion SEM, thin-section examination, XRD mineralogy, TOC, Hg concentration, petrophysical properties and …

Carbon Nanotube-Enhanced Nanolubricants: Stability And Performance Improvements For Automotive Use, Sherif Elsoudy

Mechanical Engineering

Nanotechnology has been a promising technology over the years. Carbon nanotubes (CNTs) are one of the principal technologies that are developed in the nanotechnology sector. This study investigated the implementation of CNTs as additives in automotive lubricants, focusing on their impact on performance metrics. The dispersion of CNTs in lubricants is influenced by several factors, the most critical of which is the dispersion stability. Key findings include improved dispersion stability of CNTs in lubricants through adding surfactants like oleic acid, which effectively managed the aggregation issues. The CNT-enhanced lubricants exhibited superior tribological, thermophysical and rheological properties compared to the bare …

Developing A Nearly Automated Open-Source Pipeline For Conducting Computational Fluid Dynamics Simulations In Anterior Brain Vasculature: A Feasibility Study, Mostafa Rezaeitaleshmahalleh, Nan Mu, Zonghan Lyu, Joseph Gemmete, Aditya Pandey, Jingfeng Jiang

Michigan Tech Publications

Intracranial aneurysms (IA) pose significant health risks and are often challenging to manage. Computational fluid dynamics (CFD) simulation has emerged as a powerful tool for understanding lesion-specific hemodynamics in and around IAs, aiding in the clinical management of patients with an IA. However, the current workflow of CFD simulations is time-consuming, complex, and labor-intensive and, thus, does not fit the clinical environment. To address these challenges, we have developed a semi-automated pipeline integrating multiple open-source software packages to streamline the CFD simulation process. Specifically, the study utilized medical angiography data from 18 patients. An in-house open-source DL image segmentation model …

Propagation Modeling Of Terahertz Reflections And Reflector Design For Mimo Channel, Thanh Ngoc Dan Le

Dissertations and Theses

Wireless communication has transformed connectivity, enabling seamless access across devices without physical constraints. Terahertz (THz) frequencies, ranging from 100 GHz to 10 THz, promise high-bandwidth channels crucial for applications like IoT and virtual reality. However, deploying THz communication faces challenges due to significant propagation limitations such as high attenuation and environmental absorption. The motivation behind this research is to develop a comprehensive understanding of THz propagation dynamics and utilize reflective surfaces to create multipath environments for an improvement in the capacity performance of MIMO channels.

This research investigates the potential of Multi-Input Multi-Output (MIMO) channels at THz frequencies to overcome …

Applying Positive Unlabeled Learning Techniques And Using The Kullback-Leibler Divergence To Improve Geothermal Surveying Assessments, Martín Thomas Rodriguez

Dissertations and Theses

As we face the current climate crisis, the discovery of geothermal energy resources has the potential to greatly reduce our dependence on fossil fuels worldwide. However, the development of any new energy infrastructure is expensive and depends on the willingness of energy agencies and developers to make initial investments based on calculated risk measures. One such measure, called geothermal favorability, is the likelihood that a site has conditions favorable for geothermal systems containing recoverable energy potential. Its prediction from existing geophysical datasets proves to be a nontrivial task. The prediction of geothermal favorability can be framed as a binary classification …

Breaking The Yoke: A Systematic Unmasking Of Challenges To Sustainable Rural Development In South Sudan, Gai Chol Paul

Journal of Sustainable Social Impact

South Sudan, a young nation grappling with the legacy of protracted conflict, faces significant challenges in fostering sustainable rural development. While the immense potential of its vast agricultural lands remains largely untapped, the persistent triple threat of insecurity, deficient infrastructure, and the absence of robust government policy actively hinders progress. The ongoing armed conflict, characterized by inter-communal violence and sporadic attacks, casts a long shadow over rural areas in South Sudan. Thus, I developed this mixed-method multiple-case study, grounded in the sustainable livelihoods framework, to explore challenges that hinder sustainable rural development in South Sudan. I collected data through document …

Understanding The Role Of The Heat Transfer Coefficient Between Tool/Workpiece Interface During Friction Stir Welding, Matthew Goodson

Theses and Dissertations

The heat transfer coefficient is a key parameter in modeling friction stir welding and has yet to be measured experimentally. The importance of this parameter was shown through validating friction stir models on both sides of the tool/workpiece interface. Both a transient plunge and a steady state model were validated by matching experimental temperatures. The steady state tool temperatures were matched (with in 2.5%), but the steady state workpiece temperatures were off by around 20%. The transient model of the FSW plunge showed the effect of varying the ℎ𝑊/𝑇 on workpiece temperatures and tool temperatures. Two methods were looked at …

Aerodynamic Noise Reduction Of Wind Turbine Blades, Steven Davenport

Honors Theses

This project is presented to meet Western Michigan University’s College of Engineering and Applied Sciences Senior Design requirements. With wind turbines becoming increasingly popular as a form of energy generation, the need to reduce the aerodynamic noise is needed. Most commercial wind farms use turbines with a NACA 0012 airfoil. Thus, that is the only profile shape considered in this research. Seven modifications were made to a NACA 0012 airfoil to reduce aerodynamic noise. The airfoils were designed in SolidWorks and 3D printed at the WMU College of Aviation. The airfoils were simulated in Ansys Fluent and experimentally tested in …

Graph Neural Networks Powered Scientific Paper Recommendation, Junhao Shen

Computer Science and Engineering Theses and Dissertations

Scientific paper recommendation systems aim to help researchers discover relevant papers amidst the vast and ever-growing body of literature. With the exponential yearly increase in scientific publications, the demand for effective paper recommendation solutions has become both critical and increasingly challenging. In recent years, deep learning techniques have revolutionized recommender systems, and scientific paper recommendations have naturally integrated these advancements. In this dissertation, we address these challenges through three progressive contributions.

First, we enhance traditional content-based methods using Graph Neural Networks (GNNs) by introducing a Graph Convolutional Network-strengthened Topic Modeling (GCN-TM) approach. This method improves upon conventional topic modeling techniques …

Deployable Assembly Structure And Harnessing For A Langmuir Probe (Dash-Lp), Sean Cowell

Honors Theses

The nanosatellite being designed by the Western Aerospace Launch Initiative (WALI) will demonstrate the technology of single-polarity electrospray thrusters. Essential to the mission is the collection of information from the ionospheric plasma surrounding the CubeSat in Low Earth Orbit (LEO). Due to the plasma sheath generated by the spacecraft, a 1.75 m boom is required to extend the Langmuir probe (LP) outside of the region of disturbed plasma. This project, Deployable Assembly Structure and Harnessing for a Langmuir Probe (DASH-LP), developed components that accompany the boom deployment system. In particular, a cable stowage system to store the RG403 shielded triaxial …

Machine Visual Perception From Sim-To-Real Transfer Learning For Autonomous Docking Maneuvers, Derek Worth, Jeffrey Choate, Ryan M. Raettig, Scott L. Nykl, Clark N. Taylor

Faculty Publications

This paper presents a comprehensive approach to enhancing autonomous docking maneuvers through machine visual perception and sim-to-real transfer learning. By leveraging relative vectoring techniques, we aim to replicate the human ability to execute precise docking operations. Our study focuses on autonomous aerial refueling as a use case, demonstrating significant advancements in relative navigation and object detection. We introduce a novel method for aligning digital twins using fiducial targets and motion capture data, which facilitates accurate pose estimation from real-world imagery. Additionally, we develop cost-efficient annotation automation techniques for generating high-quality You Only Look Once training data. Experimental results indicate that …

Solar Module Material And Support Testing, Darbi Dorr

Honors Theses

Sunseeker Solar Car Project manufactures and uses solar modules with a specific material composition to power their car. The current composition consists of many expired materials that are also too expensive to repurchase. In order to find new materials, they need to meet the material requirements while also being affordable for the team. A material analysis was done, and new materials were chosen based on specific properties like transmissibility, UV wavelength range, volume resistivity, adhesion strength, and the thickness. Power losses were then measured using an IV tracer at a set irradiance. This was done before and after encapsulating solar …

Energy Optimization In Wireless Sensor Networks: A Review, Zahraa Hammodi, Ahmed Al Hilli, Mohanad Al-Ibadi

Iraqi Journal for Computer Science and Mathematics

The use of wireless sensor networks (WSNs) has become an inevitably necessary for a smart world, such as smart cities and environmental fields. WSN consists of hundreds or even thousands of sensor nodes that have the ability to sense physical conditions from the target field, and also consists of a device that acts as a link between the sensor nodes and the base station (BS) called cluster head (CH). In the recent years, researchers have become interested in optimizing the energy efficiency of the WSNs due to the limited and non-replenish energy sources of their sensor nodes. In this paper, …

Processing Cost Analysis For Great South Metals, Evan Briggs, Madisen Laskos, Jared Perrin

Senior Design Project For Engineers

Great south Metals (GSM), a steel processing company based in Acworth, GA, has partnered with the Kennesaw State University (KSU) Industrial and System Engineering (ISYE) department to optimize its costing model. Currently, GSM uses a flat pricing structure for GSM-owned materials and estimates costs for toll processing. However, this approach has led to inaccuracies in pricing and challenges in tracking profitability. GSM seeks to transition to a more systematic and data-driven costing model that will improve both internal and external quoting while ensuring competitiveness in the market.

To address these challenges, the project focused on developing separate costing matrices for …

Inventory Tracking System, Anthony B., Ankita Hattangady

Senior Design Project For Engineers

The project will target the three big issues that the Kennesaw State University Textile Department is currently facing. The first is real-time tracking of inventory. We want to create a system that tracks how much inventory is always available to be used, and how much depletes each time a student/ faculty member uses a product. As restocking finished items is a long process, low stock alerts may help combat wait times. This system tracks when an item is running low and is able to send out low stock alerts in order to avoid shortages and make repurchases easier. The second …

The Impact Of Student Engagement Activities On Future Climate Change Adaptation: The Case Of Student Simulation Models, Bassel Mostafa Elkalaf

Future Journal of Social Science

This paper explores the critical role of student engagement in addressing the growing challenges of climate change, with a focus on the Model United Nations (MUN) as a case study. As climate-related security threats increase globally, educational platforms that prepare youth for effective leadership in climate politics are more essential than ever. MUN, a widely practiced student activity simulating global policy-making, provides a valuable opportunity for students to deepen their understanding of the interconnectedness between climate change, peace, and security. By participating in MUN simulations, students engage in debates, develop innovative solutions, and practice diplomatic skills, all while exploring the …

Increasing Drift Capacity Of Non-Ductile Concrete Shear Walls Through Confinement With Fiber-Reinforced Polymer Application, Andrew Duong, Sophia Maglabe, Sheyna Rongong

Architectural Engineering: Graduate Reports

The seismic response and laboratory testing of pre-1980s reinforced concrete (RC) shear walls commonly exhibit undesirable concrete crushing and rebar buckling in the wall end-zones leading to a flexural compressive failure. The lack of ductility of these walls is attributed to low reinforcement ratios and absence of special boundary elements (SBE) as required by modern design code. Thus, the authors are proposing a fiber reinforced polymer (FRP) retrofit method to provide confinement to the end-zones of pre-1980s walls equivalent to that of an SBE. Current industry applications of FRP have largely been for shear strengthening of RC beams, columns, and …

Universal Shape Replication Via Self-Assembly With Signal-Passing Tiles, Andrew Alseth, Daniel Hader, Matthew J. Patitz

Computer Science and Computer Engineering Faculty Publications and Presentations

In this paper, we investigate shape-assembling power of a tile-based model of self-assembly called the Signal-Passing Tile Assembly Model (STAM). In this model, the glues that bind tiles together can be turned on and off by the binding actions of other glues via “signals”. Specifically, the problem we investigate is “shape replication” wherein, given a set of input assemblies of arbitrary shape, a system must construct an arbitrary number of assemblies with the same shapes and, with the exception of size-bounded junk assemblies that result from the process, no others. We provide the first fully universal shape replication result, namely …

Measuring Gait Of Total Knee Arthroplasty Patients Pre-Op And Post-Op Using A Smartphone, Celeste A. Thai

Master's Theses

Motion capture technology is a tool often used in orthopedic applications, including measuring gait dysfunctions. However, gait analysis research focused on total knee arthroplasty (TKA) patients is limited, especially using motion capture systems. This may be due to a multitude of factors, such as inaccessibility to gait labs to the general public, difficulty of travel post-surgery, and overall costs of care and maintenance of motion lab equipment. New emerging novel methods use wearable devices such as smartphones and inertial measurement devices (IMUs) to perform gait assessment and are becoming favorable due to their increasingly ubiquitous nature. One such method using …

Medium-Entropy Engineering Of Magnetism In Layered Antiferromagnet CuXNi2(1-X)CrXP2S6, Dinesh Upreti, Rabindra Basnet, M. M. Sharma, Santosh Karki Chhetri, Gokul Acharya, Md Rafique Un Nabi, Joshua Sakon, Mourad Benamara, Mansour Mortazavi, Jin Hu

Physics Faculty Publications and Presentations

Antiferromagnetic van der Waals-type M₂P₂X₆ compounds provide a versatile material platform for studying 2D magnetism and relevant phenomena. Establishing ferromagnetism in 2D materials is technologically valuable. Though magnetism is generally tunable via a chemical way, it is challenging to induce ferromagnetism with isovalent chalcogen and bimetallic substitutions in M₂P₂X₆. Here, we report co-substitution of Cu¹⁺ and Cr³⁺ for Ni²⁺ in Ni₂P₂S₆, creating Cu_xNi_2(1-x)Cr_xP₂S₆ medium-entropy alloys spanning a full substitution range ( …