Engineering Commons^™

Generalized Model To Enable Zero-Shot Imitation Learning For Versatile Robots, Yongshuai Wu

Master's Theses

The rapid advancement in Deep Learning (DL), especially in Reinforcement Learning (RL) and Imitation Learning (IL), has positioned it as a promising approach for a multitude of autonomous robotic systems. However, the current methodologies are predominantly constrained to singular setups, necessitating substantial data and extensive training periods. Moreover, these methods have exhibited suboptimal performance in tasks requiring long-horizontal maneuvers, such as Radio Frequency Identification (RFID) inventory, where a robot requires thousands of steps to complete.

In this thesis, we address the aforementioned challenges by presenting the Cross-modal Reasoning Model (CMRM), a novel zero-shot Imitation Learning policy, to tackle long-horizontal robotic …

The Design And Optimization Of An Ethylbenzene Production Process, Alexander Koons

Honors Theses

Ethylbenzene is a foundational organic compound used as a reactant in styrene production. The objective of this thesis is to present the optimization of the in-house production process of ethylbenzene, aiming to avoid external procurement for the downstream styrene manufacturing facility. The process underlines a strategic approach to enhance the yield and cost efficiency of the production of ethylbenzene. An economic analysis revealed a promising net present value of approximately $57.6 million. This thesis not only proposes a viable route for internal ethylbenzene generation but also discusses optimizing the chemical production processes for enhanced efficiency and sustainability.

Calcium Analysis Of Intercellular Communications Between Alpha Cells And Delta Cells Across The Pancreatic Islet, Shichao Gao

McKelvey School of Engineering Graduate Student Theses & Dissertations

The intricate communication between different cell types within pancreatic islets plays a crucial role in regulating glucose homeostasis. Among these cellular interactions, the interplay between α cells (responsible for glucagon secretion) and δ cells (secreting somatostatin) is particularly intriguing due to the inhibitory effects of somatostatin on glucagon release. Understanding the intercellular interactions between α and δ cells may provide insights into the mechanisms underlying the coordinated regulation of blood glucose levels. In this study, we employed a multi-modal approach combining confocal imaging, image analysis, and correlation network analysis to investigate the spatial relationships and potential functional connections between α …

Latent Auto-Recursive Composition Engine, Yenkai Huang

Dartmouth College Master’s Theses

This thesis investigates the shifting boundaries of art in the era of Generative AI, critically examining the essence of art and the legitimacy of AI-generated works. Despite significant advancements in the quality and accessibility of art through generative AI, such creations frequently encounter skepticism regarding their status as authentic art. To address this skepticism, the study explores the role of creative agency in various generative AI workflows and introduces an "artist-in-the-loop" system tailored for image generation models like Stable Diffusion. This system aims to deepen the artist's engagement and understanding of the creative process. Additionally, a novel tool, the Latent …

Autonomous Bottling And Packaging System - Mechanical Bottling Portion, Kathryn Gray

Honors College Theses

This report details the complete mechanical design of an autonomous bottling automation system. This system is fully integrated with a bottling and packaging system. The scope of the full project is to successfully bottle and cap twelve small bottles (approximately 68 cm3) in under three minutes and thirty seconds. The bottles shall be filled with an “electrolyte” and water mixture, and the mixture should be fully mixed. To complete this task, two tanks will dispense liquid (one electrolyte, and one water) into the bottles. Each tank shall have a measuring chamber, that will fill with the correct amount of volume …

A Comprehensive Review Of Fischer-Tropsch Synthesis Processes To Produce Sustainable Diesel And Aviation Fuel, Joseph C. Steinagel

Honors College Theses

The greatest threat known to humankind today is global warming. It affects every nation on the planet and the natural order of all living things. Consequently, this ongoing crisis necessitates action to scientifically revolutionize important areas of society, including researching modern adaptations of the transportation industry. In that regard, it has been determined that an effective short-term answer to eliminating carbon emissions is to produce sustainable fuels that run cooperatively with the well-established machines of today. Sustainable aviation fuel (SAF) is one such topic of interest, and the Fischer-Tropsch synthesis process is an effective way of producing SAF. To that …

Brain Computer Interface-Based Drone Control Using Gyroscopic Data From Head Movements, Ikaia Cacha Melton

Honors College Theses

This research explores the potential of using gyroscopic data from a person’s head movement to control a DJI Tello quadcopter via a Brain-Computer Interface (BCI). In this study, over 100 gyroscopic recordings capturing the X, Y and Z columns (formally known as GyroX, GyroY, GyroZ) between 4 volunteers with the Emotiv Epoc X headset were collected. The Emotiv Epoc X data captured (left, right, still, and forward) head movements of each participant associated with the DJI Tello quadcopter navigation. The data underwent thorough processing and analysis, revealing distinctive patterns in charts using Microsoft Excel. A Python condition algorithm was then …

Variable Design Stent To Prevent Stent Failure In Areas Of High Mobility In Peripheral Artery Disease Patients, Emmie Stevens, Brennan Toepfer, Lexi Graves

Honors Theses

As senior biomedical engineering students at the University of Mississippi, we were tasked with a senior project to find an unmet clinical need in the healthcare industry and design a way to solve it. Our team, consisting of Hannah Dunn, Lexi Graves, Emmie Stevens, and Brennan Toepfer, decided to improve upon current stents to create a stent more suited to treating Peripheral Artery Disease (PAD), especially in high-impact areas, such as the back of the knee joint. Stents placed in the back of the knee have a high level of stent failure due to the high movement of the knee …

Minimizing Patient Migration: Enhancing Safety And Comfort For Patients And Caregivers In Bedridden Care, Danielle Pasquini

Honors Theses

Biomedical engineering seniors at the University of Mississippi embark on a senior project aimed at addressing an unmet clinical need. Our team, consisting of Kelsie Hand, Christian Miller, and Danielle Pasquini, identified a prevalent issue of bedridden patients slipping down in bed, leading to increased repositioning by caregivers. This not only impacts patient comfort but also poses risks of complications such as pressure ulcers and caregiver injuries. In our efforts to tackle the issue of patient slippage among bedridden individuals, our team introduced a novel solution comprising a non-slip vest for patients and a corresponding non-slip sheet attachment. This integrated …

An Overview Of The Product Development Process For A Lounging Grove Chair: The Rebel Lounge, Gracey Massengill

Honors Theses

This report focuses on the process of completing my senior capstone project for the Center for Manufacturing Excellence with my teammates, Andrew Brady, Carter Doss, Brooke Grissinger, and Karson Wardell. It explains the development, design and manufacturing of the Rebel Lounge Chair, a comfortable, portable and versatile chair made with the University of Mississippi Grove in mind and the prospective customers that would purchase such a chair. The report describes the phases of brainstorming, market research, prototyping, manufacturing process development, and accounting analysis that the Rebel Lounge capstone team went through to create their product.

Due to out-of-the-box brainstorming and …

Spin Coating Multilayer Polymer Films To Improve The Consistency And Longevity Of Interval Drug Release, Katherine Nevils

Honors Theses

Treatment-resistant depression (TRD) is a clinical diagnosis for patients suffering from major depressive disorder (MDD). An inadequate response to the dosage or duration of antidepressant medication can lead to the diagnosis of TRD. This diagnosis is common in up to 50% of patients with MDD following treatment. Microdosing of classical psychedelics such as lysergic acid diethylamide (LSD) has been shown to have positive cognitive and therapeutic effects on patients with TRD. However, issues of patient compliance to the complex regimen and abuse/diversion of the schedule I controlled substances remain unresolved. The goal of this project is to create an implantable, …

Creating A Collapsible Sling Lift Capable Of Transporting Patients Between Various Locations, Cameron Delaney Hillman, Macey Jewell Ross, Lydia Noel Miller

Honors Theses

As Senior Biomedical Engineering students at the University of Mississippi, we, Lainey Hillman, Lydia Miller, and Macey Ross, are required to complete a final senior capstone for our department. This project aims to provide a solution to a current unmet clinical need in the healthcare industry, thus our team sought to improve the lack of transportability of sling lifts. The current sling lifts on the market display numerous issues: heavy, bulky, use confined to certain areas, and use specific for only one type of transportation. To combat these problems, we designed a sling lift that was lightweight, collapsible, safe, and …

Creating A Collapsible Sling Lift Capable Of Transporting Patients Between Various Locations, Macey Jewell Ross, Cameron Delaney Hillman, Lydia Noel Miller

Honors Theses

As Senior Biomedical Engineering students at the University of Mississippi, we, Lainey Hillman, Lydia Miller, and Macey Ross, are required to complete a final senior capstone for our department. This project aims to provide a solution to a current unmet clinical need in the healthcare industry, thus our team sought to improve the lack of transportability of sling lifts. The current sling lifts on the market display numerous issues: heavy, bulky, use confined to certain areas, and use specific for only one type of transportation. To combat these problems, we designed a sling lift that was lightweight, collapsible, safe, and …

Population At Risk: The Design And Production Of The Pollinator Plaza, Shane Houston Stephens

Honors Theses

This report focuses on the development and manufacturing of the Pollinator Plaza, a high-quality bug house created to combat pollinator population loss. According to countless studies, pollinator populations have seen a dramatic decrease in recent years, and this product was developed to address these alarming statistics by providing a suitable habitat for pollinators. A market analysis was used to identify our potential clientele and cost point. This research played an integral part in the design of the Pollinator Plaza, which was developed using AutoCAD software. This design became a reality through the construction of a physical prototype.

The Pollinator Plaza’s …

Synthesis And Analysis Of A Novel Magnetic Surfactant, Donovan Turpin

Honors Theses

Researchers in the University of Mississippi Chemical Engineering Department have suggested that chelation of a large magnetic transition metal, namely dysprosium, into the large polar head group of a surfactant could result in a magnetic surfactant. This project was aimed at synthesizing a surfactant with a large enough head group and negative charge (specifically EDTA) to support this ion and demonstrating that the chelation process was successful. If so, the molecule would ideally be capable of forming micelles which could extract oily substances from water using a strong magnet—possibly applicable to environmental crises like oil spills.

NMR analysis has suggested, …

The Effects Of Uv Degradation On Polycarbonate Plastics Under Dynamic Compressive Loading, Hannah Bradford

Honors Theses

The objective of this experiment was to analyze the dynamic properties of polycarbonate plastics subjected to accelerated ultraviolet (UV) exposure. This was done by subjecting rods of polycarbonate plastic to UV degradation in a QUV accelerated weathering machine for 375, 750, and 1500-hours. These rods were then tested under dynamic compression using a Split-Hopkinson Pressure Bar at an average strain rate of 1600/s. The Split-Hopkinson pressure bar works by rapidly compressing a sample between 3 axial rods sending an elastic wave through the sample. The strain gauges on the incident rod and the transmission rod transformed the elastic wave deformation …

Practical Static Binary Instrumentation Attacks Against Binary Stylometry, Justin Lee Carpenter

Masters Theses, 2020-current

Binary stylometry aims to find the features in a binary computer program and use them to identify the developers of the corresponding source code. Despite the noises in the code compilation process from the compiler, assembler, linker, and library functions, two existing studies based on machine learning for binary stylometry have reported high success rates (Alrabaee, Shirani, Wang, Debbabi, and Hanna 2018; Caliskan, Yamaguchi, Dauber, Harang, Rieck, Greenstadt, and Narayanan 2018). In this thesis, we first observe that both existing studies are based on a largely benign security model and assume that the binaries used in testing and prediction are …

Effect Of Waste Covid-19 Masks On Compaction Characteristics Of Silty-Clay Soil, Sydney K. Lawson

Honors College Theses

The present study aims to explore the effect of adding shredded waste Covid-19 masks to silty-clay soil on the soil’s compaction characteristics for beneficial use in embankment, the subgrade of roadways, or backfill. This was accomplished by using two different types of masks: blue surgical masks and KN95 masks. Both mask types were hand shredded into half-inch sections using safety-scissors. The maximum dry density (MDD) and optimum moisture content (OMC) are the two most important compaction characteristics, and they were determined by the Standard Proctor Compaction Test (ASTM D698 / AASHTO T99). The change of both the MDD and OMC …

Navigating The Relationships Among Food Waste Practices, Environmental Intentions, And Sustainability Knowledge Of Students, Merri Claire Minshew

Honors College Theses

Colleges and university campuses are among the greatest food wasters in the US due to combined over production and plate waste from consumers. While some schools have developed programs aimed at reducing and sustainably managing food waste, much of it ends up in landfills and produces greenhouse gas emissions. The overall goal of the research was to collect a comprehensive data set on university students’ food waste practices and behavior, environmental and sustainability knowledge, and environmental intentions. For probing relationships among these drivers, a structural equation model and student survey was developed. The survey of 37 questions was collected on …

The Conceptual Design, Analysis And Optimization Of A Hydrogen Combustion And A Hydrogen Fuel-Cell Powered Aircraft, Michael Kiely

McKelvey School of Engineering Graduate Student Theses & Dissertations

In the effort to combat climate change worldwide, the aviation industry faces particularly complex design challenges in designing new, emission free vehicles. One potential solution to this problem is the use of hydrogen fuel as a means of propulsion. Hydrogen fuel has many benefits over traditional jet fuel such as a higher gravimetric energy density; however, it requires the aircraft to carry large, pressurized, cryogenic fuel tanks. This thesis examines the design challenges, potential solutions, and the analysis methods for the design of a short to medium range hydrogen powered commercial airliner. To accomplish this goal, a comprehensive conceptual design …

Effects Of Magnetite Particle Morphology On Adsorption Of Copper Ions From Aqueous Solutions, Alisa Hashley

Graduate Theses & Non-Theses

Adsorptive processes can be used for metal contaminant removal. This work addresses magnetite, a magnetic iron oxide, as the adsorbent for use in an adsorptive removal system, known as the continuous flow material recovery system (CFMR), developed by Leitzke et al. [1]. Though the system is effective in removing contaminants from aqueous solution, efforts to further improve efficiency are being made. One way to improve the efficiency of the CFMR is to analyze the magnetite particles being used and investigate how the particle properties effect adsorption. The author’s research is presented and discussed here to describe the effects magnetite particle …

Potential Impact Of Proposed Medical Device On Hospital Acquired Anemia, Sam Menzie

Masters Theses

Evacuated tubes are the industry standard for drawing blood and have improved phlebotomist and patient safety as well as paved the way for laboratory automation. Current practices using evacuated tubes do not allow caregivers to control the volume of blood drawn, leading to blood waste in hospital settings. This overdrawing of blood has led to the prevalence of iatrogenic anemia, or hospital acquired anemia (HAA). HAA represents a significant risk to patients, leading to increased adverse conditions, and a higher consumption of hospital resources. This study seeks to model the efficacy of a potential new medical device. The proposed device …

Development Of Protocol To Evaluate The Effectiveness Of The Labor Assist Device, Samantha M. Spurr

Masters Theses

The Labor Assist Device (LAD) was designed to reduce the muscle fatigue experienced by women during childbirth to decrease the number of unnecessary cesarean deliveries and injuries to nurses. The purpose of this thesis is to develop a protocol for a future study to assess the effectiveness of the LAD at reducing muscle fatigue. While multiple parameters were investigated in this pilot study, the major parameter needed to develop the future protocol is the muscle fatigue rate in women contracting their muscles to simulate pushing during labor. The muscle fatigue rates are estimated in this study using a surface electromyography …

Evaluating The Effect Of Noise On Secure Quantum Networks, Karthick Anbalagan

Master's Theses

This thesis focuses on examining the resilience of secure quantum networks to environmental noise. Specifically, we evaluate the effectiveness of two well-known quantum key distribution (QKD) protocols: the Coherent One-Way (COW) protocol and Kak’s Three-Stage protocol (Kak06). The thesis systematically evaluates these protocols in terms of their efficiency, operational feasibility, and resistance to noise, thereby contributing to the progress of secure quantum communications. Using simulations, this study evaluates the protocols in realistic scenarios that include factors such as noise and decoherence. The results illustrate each protocol’s relative benefits and limitations, highlighting the three-stage protocol’s superior security characteristics, resistance to interference, …

Structured Light Radial-View Endoscope Imaging Development For Evaluation Of Human Tissue, Xiyan Li

McKelvey School of Engineering Graduate Student Theses & Dissertations

In this thesis, we improved an existing structured light methodology to more accurately estimate tissue optical properties imaged in a single snapshot. The developed approach is a major enhancement of the traditional three-phase spatial frequency domain imaging system: It greatly simplifies the operational procedure while also maintaining high accuracy in optical property measurements .

Leveraging this improved approach, we have developed a low-cost, compact, and radial-view endoscope prototype. This prototype combines affordability with high functionality and a user-friendly design. To assess the performance and reliability of our endoscope, we conducted comprehensive evaluations involving tissue-mimicking phantoms, as well as ex vivo …

Fabrication Of Two-Dimensional Material-Based Nano-Capacitors Using Bismuth Selenite (Bi2seo5) To Study Its Dielectric Properties, Major Kc

McKelvey School of Engineering Graduate Student Theses & Dissertations

In recent years, the demand for high-performance micro and nanodevices has surged, necessitating the exploration of novel dielectric materials to replace conventional silicon dioxide. Following the continuation of the Moorse law, as device dimensions reduce to nanoscale levels, the properties of silicon dioxide can degrade, leading to issues such as increased leakage current and reduced gate control. Materials with superior electrical properties, such as higher dielectric constant, lower leakage current, and better thermal stability allowing for the development of faster, more efficient, and more reliable devices are in higher demand than ever. Two-dimensional layered semiconductor nanomaterials represented by compounds such …

Robustness Of Trajectory Prediction Neural Network Models, Guocheng He

McKelvey School of Engineering Graduate Student Theses & Dissertations

The application of autonomous vehicles in real life relies on trajectory prediction models based on perception and observation of the surrounding scene. The deep neural network model has been widely proven to provide relatively stable and excellent performance in various scenarios. Many formal approaches are used as verification of the prediction results of DNN models, where Conformal Prediction is one which can provide statistical safety guarantee region for DNN models. However, so far, no research has shown that conformal prediction possesses satisfactory robustness in dealing with purposed adversarial attacks. In this paper, we propose an adversarial attack approach against trajectory …

Evaluating Neuroimaging Modalities In The A/T/N Framework: Single And Combined Fdg-Pet And T1-Weighted Mri For Alzheimer’S Diagnosis, Peiwang Liu

McKelvey School of Engineering Graduate Student Theses & Dissertations

With the escalating prevalence of dementia, particularly Alzheimer's Disease (AD), the need for early and precise diagnostic techniques is rising. This study delves into the comparative efficacy of Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) and T1-weighted Magnetic Resonance Imaging (MRI) in diagnosing AD, where the integration of multimodal models is becoming a trend. Leveraging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we employed linear Support Vector Machines (SVM) to assess the diagnostic potential of these modalities, both individually and in combination, within the AD continuum. Our analysis, under the A/T/N framework's 'N' category, reveals that FDG-PET consistently outperforms T1w-MRI across …

Integrating Implantable Bci Devices Within Bci2000 Using A Unified Framework And Toolchain For In-Vivo Research, Dhruva Mehta

McKelvey School of Engineering Graduate Student Theses & Dissertations

The field of neurotechnology research has a bright and promising future as more devices are created. However, there are still many gaps in the field as the potential for neuromodulation grows. Devices such as the Micro-Leads StimZ system and the Ripple Grapevine/Summit system help bridge that gap by allowing for a broader variety of closed-loop neuromodulation experiments to be implemented thanks to their portability and versatility. Despite these devices being on the market, however, there needs to be a method to collaborate and interact with them across multiple research institutions. BCI2000 helps to address that by creating a standardized working …

Enhancing Fpga Synthesis For Space Applications: Performance Evaluation Of Scalehls In The Adapt Project, Ruoxi Wang

McKelvey School of Engineering Graduate Student Theses & Dissertations

This thesis investigates the application of ScaleHLS, a high-level synthesis (HLS) tool, to enhance Field-Programmable Gate Array (FPGA) synthesis for space applications, with a focus on the Antarctic Demonstrator Advanced Particle-astrophysics Telescope (ADAPT) project. The study explores how ScaleHLS optimizes the transformation of C code into FPGA-compatible designs to improve computational efficiency and resource utilization.

The research details the process of adapting ADAPT's computational algorithms for FPGA using ScaleHLS, emphasizing the tool's effectiveness in streamlining the code-to-hardware translation. A performance evaluation highlights significant improvements in resource management and operational speed, demonstrating the tool's impact on FPGA synthesis.

These findings illustrate …