Engineering Commons^™

Extracting Patterns In Medical Claims Data For Predicting Opioid Overdose, Ryan Sanders

Graduate Theses and Dissertations

The goal of this project is to develop an efficient methodology for extracting features from time-dependent variables in transaction data. Transaction data is collected at varying time intervals making feature extraction more difficult. Unsupervised representational learning techniques are investigated, and the results compared with those from other feature engineering techniques. A successful methodology provides features that improve the accuracy of any machine learning technique. This methodology is then applied to insurance claims data in order to find features to predict whether a patient is at risk of overdosing on opioids. This data covers prescription, inpatient, and outpatient transactions. Features created …

Optimizing Block-Stacking Operations With Relocation, Hueon Lee

Graduate Theses and Dissertations

The focus of the dissertation is developing the optimization problem of finding the minimum-cost operational plan of block stacking with relocation as well as devising a solution procedure to solve practical-sized instances of the problem. Assuming changeable row depth instead of permanent row depth, this research is distinguished from conventional block stacking studies.

The first contribution of the dissertation is the development of the optimization problem under the assumption of deterministic demand. The problem is modeled using integer programming as a variation of the unsplittable multi-commodity flow problem. To find a good feasible solution of practical-sized instances in reasonable time, …

Contributions Of Role-Playing Games: Advantages Of Incorporating Social Media In Disaster Response, Erin Mullin

Graduate Theses and Dissertations

After a disaster, emergency managers need to know who needs help, what type of help they need, and how soon they need it. Traditionally, they have relied on 911 calls and ground assessments to collect this information. Because the needs of a population are not able to be identified in a timely manner by ground assessments and because individuals are often unable to get through to 911, many civilians in distress turn to social media outlets as a last-ditch effort to obtain the services they need. Due to the uncertainty concerning the accuracy of social media posts, responding to disaster …

Dynamic Prediction Of Treatment Outcomes For Recurrent Tuberculosis Patients, Nicole Hayes

Industrial Engineering Undergraduate Honors Theses

Tuberculosis (TB) is a disease that affects people around the world, especially people in underdeveloped countries. TB is one of the top ten causes of death globally so improvement in understanding diagnosis and treatment of TB affected patients could lead to major improvements in world health. This thesis research evaluated relapse patients specifically, deeming a relapse patient as one who has either been cured or completed their last treatment and then is diagnosed with TB again.

This research uses dynamic predictive modeling, based upon the random forest algorithm, to predict treatment outcomes for recurrent TB patients using demographic and follow-up …

Probabilistic Models For Order-Picking Operations With Multiple In-The-Aisle Pick Positions, Jingming Liu

Graduate Theses and Dissertations

The development of probability density functions (pdfs) for travel time of a narrow aisle lift truck (NALT) and an automated storage and retrieval (AS/R) machine is the focus of the dissertation. The multiple in-the-aisle pick positions (MIAPP) order picking system can be modeled as an M/G/1 queueing problem in which storage and retrieval requests are the customers and the vehicle (NALT or AS/R machine) is the server. Service time is the sum of travel time and the deterministic time to pick up and deposit a pallet (TPD).

Our first contribution is the development of travel time pdfs for retrieval operations …

Data Visualization Of Treatment Outcomes For Tuberculosis Patients, Joy Jenkins

Industrial Engineering Undergraduate Honors Theses

Tuberculosis is an infectious disease, and different treatments have been discovered over the years. However, patients may develop various drug resistance levels that affect the likelihood of becoming cured or dying. In this study, we sought to employ data visualization to explore the relationship between treatment trajectory, as indicated by smear and culture results in the follow-up tests and patient outcomes. A large sample of patients have been broken down by demographics including age, gender, and drug resistance status. Sankey diagrams were used to visualize the pathway progression of the patients over time split between two time periods- months 0-6 …

Simulating Alternative Tuberculosis Diagnosis Methods In Underdeveloped Countries, Luke Turner

Industrial Engineering Undergraduate Honors Theses

Tuberculosis is the deadliest infectious disease in the world; it is especially rampant in underdeveloped countries because they do not have the infrastructure, technology, or funding to properly combat the infection. However, the development of portable point-of-care diagnosis machines can reverse this epidemic as they far surpass conventional laboratory identification. The question now is where to place these machines, which is a difficult decision with a lack of data. Therefore, a flexible simulation model is created to test the implementation of these machines with different countries and configurations. The simulation tests the baseline model and three proposed implementations of the …

Characterizing Truck Parking Shortages In Arkansas: A Data Analytical Approach, Morgan Hartsell

Industrial Engineering Undergraduate Honors Theses

The Truck Parking Problem occurs when drivers have met the daily driving limit and encounter a decision between driving over time or parking in unauthorized locations. This research applies data analytics to gain further knowledge to characterize the truck parking shortage in Arkansas. Truck parking shortages are a serious problem that truck drivers face daily and is complex due to Hours of Service (HOS) regulations restrictions on legal parking areas and design. Existing research includes a one-day annual survey which compiles where public rest stops, businesses, and private rest stops are utilized by truck drivers. This research expands on the …

Modeling Of Complex Parts For Industrial Waterjet Cleaning, Braden James

Graduate Theses and Dissertations

Industrial high-pressure waterjet cleaning is common to many industries. The modeling in this paper functions inside a collaborative robotic framework for high mix, low volume processes where human robot collaboration is beneficial. Automation of pressure washing is desirable for economic and ergonomic reasons. An automated cleaning system needs path simulation and analysis to give the operator insight into the predicted cleaning performance of the system. In this paper, ablation, the removal of a substrate coating by waterjet, is modeled for robotic cleaning operations. The model is designed to work with complex parts often found in spray cleaning operations, namely parts …

An Engineered Approach To Site Selection: Determining Where Facilities Should Be Located, Kerry Melton

Operations Management Presentations

The importance of facility location has dramatically increased over the last several years as the U.S. economy has expanded and different metropolitan areas and markets have experienced population growth, infrastructure changes, labor availability improvements, and better technologies. Global competition has also created the need to further drive down costs and strategize the location of facilities such as distribution centers, freight consolidation centers, retail stores, manufacturing plants, supplier locations for raw materials, farms to grow crops, port facilities, etc. Due to the importance of facility location, this presentation will consider and evaluate several traditional and more modern methods for determining the …

Supply Chain Risk, Ed Pohl

Operations Management Presentations

Supply chains are becoming more and more extended, leaner, and complicated. Not only has the global economy contributed to the complication and risk of our supply chains, we also face significant potential challenges with technology, economic, environmental changes, and social issues. Practitioners have never experienced so many challenges at one time in their career and these challenges are coming in ways we never anticipated. In this presentation, we will address the nature of supply chain risk in today’s world, how to identify the greatest risks in your supply chain, and strategies for mitigating the risks. Examples of specific risk factors …

Project Selection: The $1 Trillion Decisions, Leonard Nethercutt

Operations Management Presentations

This webinar will discuss project selection with a focus on both strategic and fi­nancial factors. Project selection directly influences the future results of a busi­ness either positively or negatively over time. During this presentation, we will examine the important link between strategic management, project management, and operations management to create future results and value. You will learn project selection methods and tips to help your organization make a positive impact on the future of your business.

The Role Of Artificial Intelligence In Business Decision Making, Chase Rainwater

Operations Management Presentations

When we think of artificial intelligence, we often are drawn to the self-driving cars, voice-based home technologies and automated online interactions that fill the news and drive our daily activities. However, the root of these advancements, machine learning, is a predictive analytics technique that has much broader applicability. With the age of “big data” and the buzz around “data science” continuing to grow, decision-makers are asking themselves if emerging technologies, such as machine learning, can help improve business processes.

In this seminar we will demystify the fundamental concepts that comprise machine learning. The differences between supervised and unsupervised learning, as …