Industrial Technology Commons^™

Cross-Facility Reliable Deep Learning Based Beef Marbling Assessment Via Unsupervised Domain Adaptation Regression, Samuel Vinson

Biological and Agricultural Engineering Undergraduate Honors Theses

Inconsistent quality grading in beef production leads to inefficiencies, economic disparity, and consumer mistrust. While USDA meat grading traditionally relies on skilled visual inspectors, these human evaluations suffer from cross-facility variability and subjectivity. This paper introduces the first known application of unsupervised domain adaptation regression for cross-facility beef marbling score prediction—an innovation that improves generalization across diverse environments in the beef supply chain. Utilizing numerical scores ranging from 100-900, the research employed convolutional neural networks (CNNs), including ResNet, VGG, and AlexNet architectures. The study specifically introduced and validated a unified unsupervised domain adaptation regression method using the ResNet-50 architecture to …

Reliability Modeling And Improvement Of Critical Infrastructures: Theory, Simulation, And Computational Methods, José Carlos Hernández Azucena

Graduate Theses and Dissertations

This dissertation presents a framework for developing data-driven tools to model and improve the performance of Interconnected Critical Infrastructures (ICIs) in multiple contexts. The importance of ICIs for daily human activities and the large volumes of data in continuous generation in modern industries grant relevance to research efforts in this direction. Chapter 2 focuses on the impact of disruptions in Multimodal Transportation Networks, which I explored from an application perspective. The outlined research directions propose exploring the combination of simulation for decision-making with data-driven optimization paradigms to create tools that may provide stakeholders with optimal policies for a wide array …

Smart Cities-A Structured Literature Review, Jose Sanchez Gracias, Gregory S. Parnell, Eric Specking, Edward A. Pohl, Randy Buchanan

Industrial Engineering Faculty Publications and Presentations

Smart cities are rapidly evolving concept-transforming urban developments in the 21st century. Smart cities use advanced technologies and data analytics to improve the quality of life for their citizens, increase the efficiency of infrastructure and services, and promote sustainable economic growth. Smart cities integrate multiple domains, including transportation, energy, health, education, and governance, to create an interconnected and intelligent urban environment. Our research study methodology was a structured literature review using Web of Science and Google Scholar and ten smart city research questions. The research questions included smart city definitions, advantages, disadvantages, implementation challenges, funding, types of applications, quantitative techniques …

Automation Of Life Cycle Assessment, Jacob Hickman

Graduate Theses and Dissertations

An automation program, named Jacob LCA, was created to help perform life cycle assessment (LCA). The program uses a template file to perform controlled and consistently ordered actions with the LCA program, SimaPro, and effectively removes the need for manual user input. It can be set to run using data from one or more life cycle inventory (LCI) files, which allows for rapid iteration and testing of data. It also partially addresses some of the limitations of LCA by establishing a procedure through which temporal and spatial variations in data can be integrated into LCI files and then passed to …

Efficient Routing For Disaster Scenarios In Uncertain Networks: A Computational Study Of Adaptive Algorithms For The Stochastic Canadian Traveler Problem With Multiple Agents And Destinations, Neel Chanchad

Graduate Theses and Dissertations

The primary objective of this research is to develop adaptive online algorithms for solving the Canadian Traveler Problem (CTP), which is a well-studied problem in the literature that has important applications in disaster scenarios. To this end, we propose two novel approaches, namely Maximum Likely Node (MLN) and Maximum Likely Path (MLP), to address the single-agent single-destination variant of the CTP. Our computational experiments demonstrate that the MLN and MLP algorithms together achieve new best-known solutions for 10,715 instances. In the context of disaster scenarios, the CTP can be extended to the multiple-agent multiple-destination variant, which we refer to as …

A Multi-Criteria Ranking System For Prioritizing Maintenance Of Levee Systems In Arkansas, Nguyen Danh Phan

Graduate Theses and Dissertations

There are 208,009 properties in Arkansas that have more than a 26% chance of being severely affected by flooding over the next 30 years, which represents 13% of all properties in the state. A levee system is designed to reduce the flooding risk for urban and rural communities; however, most of the state's levees have been significantly outdated or built with engineering standards less rigorous than current best practices. The Levee Safety Action Classification (LSAC), as recorded in the National Levee Database (NLD), communicates the risk associated with living behind a particular levee and assists local, state, and federal stakeholders …

Using Reinforcement Learning To Improve Network Reliability Through Optimal Resource Allocation, Henley Wells

Graduate Theses and Dissertations

Networks provide a variety of critical services to society (e.g. power grid, telecommunication, water, transportation) but are prone to disruption. With this motivation, we study a sequential decision problem in which an initial network is improved over time (e.g., by adding or increasing the reliability of edges) and rewards are gained over time as a function of the network’s all-terminal reliability. The actions during each time period are limited due to availability of resources such as time, money, or labor. To solve this problem, we utilized a Deep Reinforcement Learning (DRL) approach implemented within OpenAI-Gym using Stable Baselines. A Proximal …

Advancing Statistical Learning And Decision Modeling Using Irregularly-Sampled Multivariate Data For Managing Respiratory Diseases, Maryam Alimohammadi

Graduate Theses and Dissertations

Complex healthcare systems require efficient and effective data-driven decision making in various aspects. As patient data becomes more available, advanced statistical learning and machine learning techniques are applied to improve data-driven decision making. However, patient health data, including clinical trial data, medical records, and electronic health records, are associated with several challenges. Patient health data includes medical information of a patient that may includedemographics, information relating to their health or illness, medications and treatments, etc. They are a combination of static and time series variables, with many censoring and missingness in the data, and are irregularly sampled in most cases. …

Machine Learning For Early Detection Of Pediatric Sepsis, Glory Manson-Endeboh

Graduate Theses and Dissertations

Sepsis is a host response to infection in both adults and children. It contributes to approximately 1.7 million cases annually with nearly 270,000 annual deaths in the United States. In the United States, the financial burden of sepsis on survivors and their families including the hospitals is over $4.8 billion, at approximately $64,280 per hospitalization. The first goal of this thesis research is to develop efficient machine learning models to predict pediatric sepsis accurately for inpatients. The second objective is to develop machine learning methods to determine how early sepsis can be detected to mitigate mortality. We examine data collected …

Scheduling, Complexity, And Solution Methods For Space Robot On-Orbit Servicing, Susan E. Sorenson

Graduate Theses and Dissertations

This research proposes problems, models, and solutions for the scheduling of space robot on-orbit servicing. We present the Multi-Orbit Routing and Scheduling of Refuellable On-Orbit Servicing Space Robots problem which considers on-orbit servicing across multiple orbits with moving tasks and moving refuelling depots. We formulate a mixed integer linear program model to optimize the routing and scheduling of robot servicers to accomplish on-orbit servicing tasks. We develop and demonstrate flexible algorithms for the creation of the model parameters and associated data sets. Our first algorithm creates the network arcs using orbital mechanics. We have also created a novel way to …

Ensemble Tree-Based Machine Learning For Imaging Data, Reza Iranzad

Graduate Theses and Dissertations

In particular medical imaging data, such as positron emission tomography (PET), computed tomography (CT), and fluorescence intravital microscopy (IVM), have become prevalent for use in a wide variety of applications, from diagnostic purposes, tracking diseases' progress, and monitoring the effectiveness of treatments to decision-making processes. The detailed information generated by medical imaging has enabled physicians to provide more comprehensive care. Although numerous machine learning algorithms, especially those used for imaging data, have been developed, dealing with unique structures in imaging data remained a big challenge. In this dissertation, we are proposing novel statistical tree-based methods with more efficient and more …

Analyzing Vulnerabilities In The Northwest Arkansas Highway Network Using Mathematical Optimization, Brandon Jerome

Industrial Engineering Undergraduate Honors Theses

The highway and bridge network is a critical infrastructure that allows for the free transportation of citizens and enables truck-borne freight transportation. Disruption of this system could be caused by a terrorist attack, natural disaster, growth of population, required repairs and upgrades, or collapse caused by old age or malfunction. In the event of a disruption cities and regions can experience increased traffic and supply chain shortages, thus causing cascading effects throughout surrounding areas. With this motivation, we develop a network interdiction optimization model to identify a limited subset of roads that, if disrupted, causes the greatest increase in the …

Implementing The Cms+ Sports Rankings Algorithm In A Javafx Environment, Luke Welch

Industrial Engineering Undergraduate Honors Theses

Every year, sports teams and athletes get cut from championship opportunities because of their rank. While this reality is easier to swallow if a team or athlete is distant from the cut, it is much harder when they are right on the edge. Many times, it leaves fans and athletes wondering, “Why wasn’t I ranked higher? What factors when into the ranking? Are the rankings based on opinion alone?” These are fair questions that deserve an answer. Many times, sports rankings are derived from opinion polls. Other times, they are derived from a combination of opinion polls and measured performance. …

Supervised Representation Learning For Improving Prediction Performance In Medical Decision Support Applications, Phawis Thammasorn

Graduate Theses and Dissertations

Machine learning approaches for prediction play an integral role in modern-day decision supports system. An integral part of the process is extracting interest variables or features to describe the input data. Then, the variables are utilized for training machine-learning algorithms to map from the variables to the target output. After the training, the model is validated with either validation or testing data before making predictions with a new dataset. Despite the straightforward workflow, the process relies heavily on good feature representation of data. Engineering suitable representation eases the subsequent actions and copes with many practical issues that potentially prevent the …

Predicting The Likelihood And Scale Of Wildfires In California Using Meteorological And Vegetation Data, Matthew Walters

Graduate Theses and Dissertations

Wildfires have devastating ecological, environmental, economical, and public health impacts through the deterioration of water and air quality, CO2 emissions, property damage, and lung illnesses. The early detection and prevention of wildfires allow for the minimization of these risks. The use of Artificial Intelligence (AI) in wildfire detection and prediction has been highly researched as a tool to assist firefighters in stopping wildfires in its early stages. The three common wildfire prediction categories include image and video detection, behavior prediction, and susceptibility prediction. Data such as climate, weather, vegetation, satellite images, and historical wildfire data is most commonly used. Many …

21st Century Leadership: Leadership In Challenging Times, Adam Morris

Operations Management Presentations

Our global society has experienced unprecedented changes in the last couple years. The COVID-19 pandemic created drastic changes to our personal and professional lives. We went to a virtual work and learning environment almost overnight. People in leadership positions had to make impossible decisions on items no one has ever experienced. With all the changes that are happing in our world, what does it take to be a leader in today’s global society? Do basic leadership principles from 30 years ago still apply? Watch the latest installment of the MSEM/MSOM Lunch & Learn Webinar Series that will discuss these leadership …

Tools & Visualization Techniques Available To Support The Operations Manager, Kirk Michealson

Operations Management Presentations

Most organizations provide their employees the Microsoft Office Tools Suite with Excel. The University of Arkansas Master of Science in Operations Management (MSOM) Program has included Excel as a foundational aspect of the program for the last 7 years. In that time, Microsoft has increased the Excel capabilities dramatically. Simultaneously, business intelligence analytics interest has increased, and Tableau has been created as a visual analytics platform to help users see and understand data for modern business intelligence. As a result, to support the Operations Manager the MSOM Program has developed a new course to present the additional tools and visualization …

Third Party Risk Management And Cyber Supply Chain Risk Management, Jerald Garner

Operations Management Presentations

Today’s business environment continues to be a challenge. Businesses whether small, or large leverage third-party vendors to provide critical services like data handling (security, transmitting, and storage), cloud storage/applications, and systems security monitoring.

Each business must ask themselves a few simple questions about one of their most valuable assets “Data”. If or when it leaves your secure working environment:

• How secure is your customer data in transit and storage?
• Do your third-party vendors handle your “critical information”?
  • Provide a secure environment for processing?
  • Comply with a proven Cyber Security Framework?
  • Perform a “Due Diligence” on-boarding step for the Nth vendors …

Thin Safety Margin: The Sefor Super-Prompt-Critical Transient Experiments, Ozark Mountains, Arkansas 1970–1971, Jerry Havens, Collis Geren

Arkansas Scholarly Editions

Thin Safety Margin charts the history of SEFOR, a twenty-megawatt reactor that operated for three years in the rural Ozark Mountains of Arkansas as part of an internationally sponsored program designed to demonstrate the Doppler effect in plutonium-oxide-fueled fast reactors. Authors Jerry Havens and Collis Geren draw upon this history to assess the accidental explosion risk inherent in using fast reactors to reduce the energy industry’s carbon dioxide emissions.

If a sufficiently powerful fast-neutron explosion were to cause the containment of a reactor such as SEFOR’s to fail, the reactor’s radiotoxic plutonium fuel could vaporize and escape into the surrounding …

Hidden In Plain Sight: Why Sustainment Is So Critical To The Circular Supply Chains For Technical Products, Dave Peterson

Operations Management Presentations

• Technical products are typically complex, long-lived and high-cost equipment—such as: aircraft, vehicles, ships, capital equipment/machinery and utilities infrastructure. While many technical products are manufactured via traditional linear supply chains, their useful lives often rely upon sustainment systems incorporating significant aspects of circular supply chains. This webinar takes a closer look at technical products and the critical role of systems sustainment to achieve and fulfill circular supply chains. The key takeaways from this webinar are:
  • The Earth is running out of resources which will have a direct impact upon maintaining/improving our quality of life.
  • The circular economy philosophy has definite relevance …

Critical Chain – Or Why Wedding Planners Get Ulcers, Greg Hutto

Operations Management Presentations

Planning a wedding is one of the most challenging projects in a young life… So much to do! A respected journal in the project management literature -- Southern Bride -- advises well-off young couples to escape stress and employ a professional wedding planner+. In today's webinar we will contrast two project planning methods in examining one such wedding project -- hastily planned and beset with troubles. We will shed light on the science & art of project management and possibly help our wedding planners (both professional and amateur) avoid stress-induced medical complications. In this webinar, we’ll be spending time with …

A Machine Learning Approach To Understanding Emerging Markets, Namita Balani

Graduate Theses and Dissertations

Logistic providers have learned to efficiently serve their existing customer bases with optimized routes and transportation resource allocation. The problem arises when there is potential for logistics growth in an emerging market with no previous data. The purpose of this work is to use industry data for previously known and well-documented markets to apply data analytic techniques such as machine learning to investigate the uncertainty in a new market. The thesis looks into machine learning techniques to predict miles per stop given historical data. It mainly focuses on Random Forest Regression Analysis, but concludes that additional techniques, such as Polynomial …

Deployment Policies To Reliably Maintain And Maximize Expected Coverage In A Wireless Sensor Network, Nicholas T. Boardman

Graduate Theses and Dissertations

The long-term operation of a wireless sensor network (WSN) requires the deployment of new sensors over time to restore any loss in network coverage and communication ability resulting from sensor failures. Over the course of several deployment actions it is important to consider the cost of maintaining the WSN in addition to any desired performance measures such as coverage, connectivity, or reliability. The resulting problem formulation is approached first through a time-based deployment model in which the network is restored to a fixed size at periodic time intervals. The network destruction spectrum (D-spectrum) has been introduced to estimate reliability and …

Enabling The “Easy Button” For Broad, Parallel Optimization Of Functions Evaluated By Simulation, Andrew Gibson

Graduate Theses and Dissertations

Java Optimization by Simulation (JOBS) is presented: an open-source, object-oriented Java library designed to enable the study, research, and use of optimization for models evaluated by simulation. JOBS includes several novel design features that make it easy for a simulation modeler, without extensive expertise in optimization or parallel computation, to define an optimization model with deterministic and/or stochastic constraints, choose one or more metaheuristics to solve it and run, using massively parallel function evaluation to reduce wall-clock times.

JOBS is supported by a new language independent, application programming interface (API) for remote simulation model evaluation and a serverless computing environment …

Quantitative Set-Based Design For Complex System Development, Nicholas J. Shallcross

Graduate Theses and Dissertations

This dissertation comprises a body of research facilitating decision-making and complex system development with quantitative set-based design (SBD). SBD is concurrent product development methodology, which develops and analyzes many design alternatives for longer time periods enabling design maturation and uncertainty reduction. SBD improves design space exploration, facilitating the identification of resilient and affordable systems. The literature contains numerous qualitative descriptions and quantitative methodologies describing limited aspects of the SBD process. However, there exist no methodologies enabling the quantitative management of SBD programs throughout the entire product development cycle. This research addresses this knowledge gap by developing the process framework and …

Scheduling Allocation And Inventory Replenishment Problems Under Uncertainty: Applications In Managing Electric Vehicle And Drone Battery Swap Stations, Amin Asadi

Graduate Theses and Dissertations

In this dissertation, motivated by electric vehicle (EV) and drone application growth, we propose novel optimization problems and solution techniques for managing the operations at EV and drone battery swap stations. In Chapter 2, we introduce a novel class of stochastic scheduling allocation and inventory replenishment problems (SAIRP), which determines the recharging, discharging, and replacement decisions at a swap station over time to maximize the expected total profit. We use Markov Decision Process (MDP) to model SAIRPs facing uncertain demands, varying costs, and battery degradation. Considering battery degradation is crucial as it relaxes the assumption that charging/discharging batteries do not …

Resilience-Driven Post-Disruption Restoration Of Interdependent Critical Infrastructure Systems Under Uncertainty: Modeling, Risk-Averse Optimization, And Solution Approaches, Basem A. Alkhaleel

Graduate Theses and Dissertations

Critical infrastructure networks (CINs) are the backbone of modern societies, which depend on their continuous and proper functioning. Such infrastructure networks are subjected to different types of inevitable disruptive events which could affect their performance unpredictably and have direct socioeconomic consequences. Therefore, planning for disruptions to CINs has recently shifted from emphasizing pre-disruption phases of prevention and protection to post-disruption studies investigating the ability of critical infrastructures (CIs) to withstand disruptions and recover timely from them. However, post-disruption restoration planning often faces uncertainties associated with the required repair tasks and the accessibility of the underlying transportation network. Such challenges are …

Efficiently Estimating Survival Signature And Two-Terminal Reliability Of Heterogeneous Networks Through Multi-Objective Optimization, Daniel Bruno Lopes Da Silva

Graduate Theses and Dissertations

The two-terminal reliability problem is a classical reliability problem with applications in wired and wireless communication networks, electronic circuit design, computer networks, and electrical power distribution, among other systems. However, the two-terminal reliability problem is among the hardest combinatorial problems and is intractable for large, complex networks. Several exact methods to solve the two-terminal reliability problem have been proposed since the 1960s, but they have exponential time complexity in general. Hence, practical studies involving large network-type systems resort to approximation methods to estimate the system's reliability. One attractive approach for quantifying the reliability of complex systems is to use signatures, …

Improving Logistics Efficiency Through Collaborative Truck Routing, Patrick Dougherty

Industrial Engineering Undergraduate Honors Theses

The logistics industry is among the world’s largest and most essential. Specifically, trucking is a massive component of the modern logistics system. In 2012, truck transportation carried 68% of all freight tonnage in the U.S. However, trucking currently faces significant problems with efficiency and sustainability. Of all miles driven by trucks yearly in the U.S., 25% are driven with empty loads and 36% are driven with underutilized loads. In addition to this economic inefficiency, the industry faces social and environmental challenges. Driver turnover rates are near 100%, and trucking accounts for a significant level of greenhouse gas emissions. One potential …

Regression Analysis Of Pacing When Running A Marathon, Hawkin Starke

Industrial Engineering Undergraduate Honors Theses

Regression analysis can be an effective way of examining performance in the marathon event. By splitting up the race into segments or in runner terminology “splits” the significance of each segment as it relates to the total finish time can be explored. Because the idea of splits is already ingrained into the minds of runners, it makes intuitive sense to use these as the metrics to define a race. Additionally, marathons generally make participant age and gender date publicly available which can then be used to find trends within specific demographics. This tailors trends to smaller groups of people, making …