Digital Commons Network^™

Ensemble Machine Learning To Predict Family Consent For Organ Donation, Md Ehsan Khan

Graduate Dissertations and Theses

There is ever increasing disparity between number of organs needed for transplantation and numbers available for donation to save lives. As a result, thousands of people die every year waiting for organs. Therefore, it is now more important than ever before to take serious actions to decrease this disparity. One way to bridge gap between organ demand and supply is to increase family consent for organ donation. This research studied the factors associated with family consent. Machine Learning approach had been used in very few literature to understand factors related to family consent. This study uses six Ensemble Machine Learning …

Service Consistency In Vehicle Routing, Kunlei Lian

Graduate Theses and Dissertations

This thesis studies service consistency in the context of multi-period vehicle routing problems (VRP) in which customers require repeatable services over a planning horizon of multiple days. Two types of service consistency are considered, namely, driver consistency and time consistency. Driver consistency refers to using the fewest number of different drivers to perform all of the visits required by a customer over a planning horizon and time consistency refers to visiting a customer at roughly the same time on each day he/she needs service. First, the multi-objective consistent VRP is defined to explore the trade-offs between the objectives of travel …

Robust Vehicle Routing In Disaster Relief And Ride-Sharing: Models And Algorithms, Yinglei Li

Graduate Dissertations and Theses

In this dissertation, the variants of vehicle routing problems (VRPs) are specifically considered in two applications: disaster relief routing and ride-sharing. In disaster relief operations, VRPs are important, especially in the immediate response phase, as vehicles are an essential part of the supply chain for delivering critical supplies. This dissertation addresses the capacitated vehicle routing problem (CVRP) and the split delivery vehicle routing problem (SDVRP) with uncertain travel times and demands when planning vehicle routes for delivering critical supplies to the affected population in need after a disaster. A robust optimization approach is used for the CVRP and the SDVRP …

Examination And Utilization Of Rare Features In Text Classification Of Injury Narratives, Hsin-Ying Huang

Open Access Dissertations

Thanks to the advances in computing and information technology, analyzing injury surveillance data with statistical machine learning methods has grown in popularity, complexity, and quality over recent years. During that same time, researchers have recognized the limitations of statistical text analysis with limited training data. In response to the two primary challenges for statistical text analysis, dimensionality reduction and sparse data, many studies have focused on improving machine learning algorithms. Less research has been done, though, to examine and improve statistical machine learning methods in text classification from a linguistic perspective.

This study addresses this research gap by examining the …

Impact Of Rfid Information-Sharing Coordination Over A Supply Chain With Reverse Logistics, Juan Jose Nativi Nicolau

Open Access Dissertations

Companies have adopted environmental practices such as reverse logistics over the past few decades. However, studies show that aligning partners inside the green supply chain can be a substantial problem. This lack of coordination can increase overall supply chain cost. Information technology such as Radio Frequency Identification (RFID) has the potential to enable decentralized supply chain coordinate their information. Even though there are research that address RFID on traditional supply chain, few researches address how to coordinate RFID information sharing in a green supply chain. We study, through simulation experiments, two types of RFID information-sharing coordination under different configurations related …

Metrics Of Critical Pair Identification, Zixu Zhang

Open Access Theses

Critical Pair Identification works as a potential assistive tool for human air traffic controllers by identifying potentially dangerous situations that are not detected by proposed automated separation assurance systems. This concept specifically considers conflicts that might arise if aircraft unexpectedly deviate from their planned flight path in the near future. Five metrics of the critical pair concept, Critical Pair Count, Time to Risk Exposure, Lead Time, Risk Exposure Duration and Blunder Sensitivity Index, have been developed and mathematically defined to characterize the safety level of an aircraft pair or a volume of air space. Algorithm that computes proposed metrics is …

Taming Tail Latency For Erasure-Coded, Distributed Storage Systems, Jingxian Fan

Open Access Theses

Nowadays, in distributed storage systems, long tails of responsible time are of particular concern. Modern large companies like Bing, Facebook and Amazon Web Service show that 99.9th percentile response times being orders of magnitude worse than the mean. With the advantages of maintaining high data reliability and ensur- ing enough space eciency, erasure code has become a popular storage method in distributed storage systems. However, due to the lack of mathematical models for analyzing erasure-coded based distributed storage systems, taming tail latency is still an open problem.

In this research, we quantify tail latency in such systems by deriving a …

Grouping Techniques To Manage Large-Scale Multi-Item Multi-Echelon Inventory Systems, Anvar Abaydulla

Graduate Theses and Dissertations

Large retail companies operate large-scale systems which may consist of thousands of stores. These retail stores and their suppliers, such as warehouses and manufacturers, form a large-scale multi-item multi-echelon inventory supply network. Operations of this kind of inventory system require a large number of human resources, computing capacity, etc.

In this research, three kinds of grouping techniques are investigated to make the large-scale inventory system “easier” to manage. The first grouping technique is a network based ABC classification method. A new classification criterion is developed so that the inventory network characteristics are included in the classification process, and this criterion …

Safety Performance Prediction Of Large-Truck Drivers In The Transportation Industry, Emily Moneka Francis Xavier

Graduate Theses and Dissertations

The trucking industry and truck drivers play a key role in the United States commercial transportation sector. Accidents involving large trucks is one such big event that can cause huge problems to the driver, company, customer and other road users causing property damage and loss of life. The objective of this research is to concentrate on an individual transportation company and use their historical data to build models based on statistical and machine learning methods to predict accidents. The focus is to build models that has high accuracy and correctly predicts an accident. Logistic regression and penalized logistic regression models …

The Effect Of Process Parameters And Surface Condition On Bond Strength Between Additively Manufactured Components And Polymer Substrates, Bharat Bhushan Chivukula

Graduate Theses and Dissertations

Additive patching is a process in which printers with multiple axes deposit molten material onto a pre-defined surface to form a bond. Studying the effect of surface roughness and process parameters selected for printing auxiliary part on the bond helps in improving the strength of the final component. Particularly, the influence of surface roughness, as established by adhesion theory, has not been evaluated in the framework of additive manufacturing (AM). A full factorial design of experiments with five replications was conducted on two levels and three factors, viz., layer thickness, surface roughness, and raster angle to examine the underlying effects …

Best Matching Processes In Distributed Systems, Mohsen Moghaddam

Open Access Dissertations

The growing complexity and dynamic behavior of modern manufacturing and service industries along with competitive and globalized markets have gradually transformed traditional centralized systems into distributed networks of e- (electronic) Systems. Emerging examples include e-Factories, virtual enterprises, smart farms, automated warehouses, and intelligent transportation systems. These (and similar) distributed systems, regardless of context and application, have a property in common: They all involve certain types of interactions (collaborative, competitive, or both) among their distributed individuals—from clusters of passive sensors and machines to complex networks of computers, intelligent robots, humans, and enterprises. Having this common property, such systems may encounter common …

Service-Level Based Response By Assignment And Order Processing For Warehouse Automation, Zijian He

Open Access Theses

Along with tremendous growth of online sales in this Internet era, unprecedented intensive competition in shortening the delivery time of orders has been occurring among several major online retailers. On the other hand, the idea of customer-oriented service creates a trend of diversified pricing strategy. Different price options are offered to cater to diversified needs of customers. It has become an urgent need for online sales industries to provide the differentiated service levels for different classes of customers with different priorities based on the charging prices and resource constraints of the supply network.

In response to the challenges mentioned above, …

Incorporating A New Class Of Uncertainty In Disaster Relief Logistics Planning, Emre Kirac

Graduate Theses and Dissertations

In recent years, there has been a growing interest among emergency managers in using Social data in disaster response planning. However, the trustworthiness and reliability of posted information are two of the most significant concerns, because much of the user-generated data is initially not verified. Therefore, a key tradeoff exists for emergency managers when considering whether to incorporate Social data in disaster planning efforts. By considering Social data, a larger number of needs can be identified in a shorter amount of time, potentially enabling a faster response and satisfying a class of demand that might not otherwise be discovered. However, …

Markov-Based Ranking Methods, Baback Vaziri

Open Access Dissertations

Ranking methods are an essential tool to help make decisions. This dissertation document examines different aspects of the theory and application of pairwise comparison ranking methods, specifically those that use Markov chains. First, a new method is developed to solve a traditional recruiting problem, and is shown to improve the predictive power of its ranking. Next, modifications are made to an existing method that theoretically improves the reliability, while maintaining the rank integrity. Last, a framework is developed that defines a fair and comprehensive ranking method, and several popular methods are evaluated in their ability to adhere to the said …

Risk Estimation Toward A Natural History Model For Low Grade Glioma Patients, Anh Thi Hoang Pham

Graduate Theses and Dissertations

Glioma is a common type of primary brain tumor that represents 28% of all brain tumors and 80% of malignant tumors. According to a recent study by the Centers for Disease Control and Prevention (CDC), gliomas account for 53%, 35% and 29% of all brain tumors (68%, 74% and 81% of malignant brain tumors) among children (aged 0-14), teenagers (aged 15-19) and young adults, respectively. Gliomas are often diagnosed through radiological imaging and histopathology. There are two main groups of gliomas following World Health Organization’s classification: Low grade gliomas (LGG), or grade I and II gliomas; and high grade gliomas …

A Tabu Search, Augment-Merge Heuristic To Solve The Stochastic Location Arc Routing Problem, Tiffany L. Yang

Graduate Theses and Dissertations

The location arc routing problem (LARP) is a network optimization problem combining strategic facility location decisions and tactical or operational vehicle routing decisions for customer demand located on arcs of a network. The LARP seeks to locate facilities, or depots, and create vehicle delivery routes to minimize costs. The total cost is comprised of three components: fixed facility locations costs, fixed route creation (or vehicle acquisition) costs, and variable arc traversal costs. The applications of the LARP are varied and often include public services such as mail delivery, garbage collection, and street sweeping. In all of these applications, the magnitude …

Use Of Response Surfaces In The Design Of A Simple Step Stress Accelerated Test Plan, Alexander H. Wong

Graduate Theses and Dissertations

In designing accelerated testing plans, cost is a factor that is missing in much of the literature. This paper explicits considers cost by developing an optimization model with the objective to minimize costs for a simple step stress accelerated test plan. Two methodologies are employed. One is an optimization approach in which an attempt is made to quantify the behavior of a series-parallel hardware system over all stages of testing using a response surface, and then an optimization model is used to determine the settings for stresses and failure mode modifications for all stages of testing prior to the start …

The Casualty Transportation Of Ebola Outbreak In Liberia: A Simulation Study, Hyejin Cho

Open Access Theses

In this paper, we have solved the unique problem of casualty transportation problem under Ebola by developing dynamic policies for vehicle routing in order to provide practical decision support. The objective of the proposed model is to minimize the total transmission risk. We describe the problem with real- constraints and parameters based on the empirical data of the 2014 Ebola outbreak in Liberia. The casualty transportation problem is a variant of Dynamic Pick-up and Delivery Problems (DPDP), in which a vehicle is dispatched to demand location in real time and it then transports the demands to the aimed area (destination). …

Developing Agent-Based Simulation Models Of Task Performance Of Cognitively Diverse Teams, Megan Marie Nyre

Open Access Theses

Team-oriented work dominates industry, government, and academic areas with the goal of solving increasingly complex problems. However, the scope and external validity of traditional human factors research is inherently limited by the time and resources required to conduct laboratory studies. The model described in this thesis integrates simulation with human factors by providing an operationalized model that incorporates cognitive diversity and domain expertise. Convergence and functionality of the model have been established through a series of analyses, and a clear path for future research has been identified. By integrating simulation methods into human factors subject areas, researchers may be able …

Enhancing A Flight Dispatcher Display For Safer Flight Operations, Jeongjoon Boo

Open Access Theses

This study assesses capability of flight dispatchers to adopt enhancements on their display that enables detection of flights in abnormal activities and investigation of the causes. Three approaches were used. First, the expected function for enhancements was designed by collecting information from different places about what technologies are available for consideration. Second, hierarchical task analysis was conducted based on data collected by interviewing a former flight dispatcher in order to assess operational capability to handle the enhancement. Third, based on the results of first two approaches, a display prototype that includes the enhancement was developed and evaluated for usability and …

Creating Quality Metrics For The Capital Facilities Delivery Industry, Kelsey D. Lamb

Graduate Theses and Dissertations

A standard for industry-wide quality metrics, similar to safety metrics, for the capital facilities delivery industry is investigated and developed with the goal to motivate industry-wide adoption of this new quality metric program. A survey of the literature found key differences between capital facilities and other industries, mainly that other industries focus on the quality of the product while capital facilities focus on maintaining the cost and schedule of a project. Creating a framework that can be used across the industry can potentially lead to uniform improvement of quality for the entire industry. Quality is defined for the capital facilities …

Understanding Technology Diffusion And Spatial Accessibility In The Home Healthcare Industry, Mehmet Serdar Kilinç

Graduate Theses and Dissertations

Home healthcare is becoming an important alternative to institutionalized care. It not only reduces costs but also increases health outcomes and patient satisfaction. However, the availability and efficiency of home healthcare services need to be improved as the aging population increases in the US. Hence, understanding home healthcare utilization and access are the essential steps to develop strategies ensuring effective and sustainable services to patients.

This research aims to study two main issues in the US home healthcare system: diffusion and long-term impacts of home telehealth and potential spatial accessibility of home healthcare services. Home telehealth is a promising technology …

An Adaptive Large Neighborhood Search Heuristic For The Inventory Routing Problem With Time Windows, Mina Hadianniasar

Graduate Theses and Dissertations

This research addresses an integrated distribution and inventory control problem which is faced by a large retail chain in the United States. In their current distribution network, a direct shipping policy is used to keep stores stocked with products. The shipping policy specifies that a dedicated trailer should be sent from the warehouse to a store when the trailer is full or after five business days, whichever comes first. Stores can only receive deliveries during a window of time (6 am to 6 pm). The retail chain is seeking more efficient alternatives to this policy, as measured by total transportation, …

Value Focused Inland Waterway Infrastructure Investment Decisions, Othman Boudhoum

Graduate Theses and Dissertations

Maritime transportation functions as the backbone of world trade. The U.S. inland waterway transportation system is comprised of 12,000 miles of navigable waterways that connect and move freight between the global supply chain and thirty eight States. When investing in inland waterway infrastructure, we should aim to maximize all benefits associated with the investment including flood protection, water supply, hydropower generation, recreation, and environmental impact benefits. We formulate an initial qualitative value model for the inland waterway infrastructure investment decision based on a value-focused thinking approach which allows us to holistically evaluate project investment alternatives. Given limited resources, a portfolio …

Using The Triple Bottom Line To Select Sustainable Suppliers For A Major Oil And Gas Company, Pandarinath Adarsh Sunkari

Graduate Theses and Dissertations

Companies have primarily been focusing on the financial bottom line i.e., on increasing profits by increasing revenues and reducing costs. With high energy usage and environmental change posing threats to the environment and business operations, companies are now considering sustainability. Since some global suppliers have low cost labor, Social well-being and human development has also emerged as major goals of a company performing global operations. Focusing on these three goals is termed the "Triple Bottom Line" (TBL). We study and explore the TBL benefits that could be realized by an oil and gas company by focusing on sustainable suppliers. A …

Inventory Management And Control "For A Cause", John Michael Miller

Graduate Theses and Dissertations

Companies today are changing the culture of business and beginning to involve more than just labor and money in overall decisions. Just as sustainability issues and humanitarian logistics are gaining popularity, so is the idea of using business to make a difference on society in addition to making a profit. As companies position themselves across the globe to make an impact, they employ people in third-world environments that create uncertainties on both the supply and demand sides. Also, the idea of strategically planning work with the goal of minimizing costs has been replaced by companies wanting to give more work …

Incorporating Environmental And Social Factors Into Decision-Making Of An Oil And Gas Industry To Improve Sustainability, Gaurav Dabhadkar

Graduate Theses and Dissertations

The energy industry (including the oil and gas industry) is facing unparalleled scrutiny and demands from stakeholders including investors, regulators (industry and environmental), communities, and other stakeholders. Sustainable development is one of the major concerns of the oil and gas industry. Companies are seeking to increase sustainability of their operations by considering environmental and Social concerns in addition to economic concerns. Oil and gas companies need to take decisions at different stages of the product life cycle (e.g. planning, design, exploration, production, and clean-up) which have direct or indirect impact on the organization's objectives. Addressing economic, technical, Social, and environmental …

Designing A Sustainable And Transferable Inventory Management System For Small Healthcare Facilities, Shree Frazier

Open Access Theses

Managing the costs of supplies within healthcare facilities has been a task that has plagued the health industry for many years. Many facilities are accustomed to using a par system approach. This involves bringing an inventory item to an amount sufficient for daily operation. This method often requires daily inspection by a healthcare worker, which reduces his/her time spent performing value added tasks. Employees at small healthcare facilities have multiple responsibilities, therefore they cannot afford to spend much time on inventory management. A proposed approach is the Kanban method, which allows for strict monitoring of inventory items without the need …

Application Of Bayesian Networks In Consumer Service Industry, Yuan Gao

Open Access Theses

Gao, Yuan. M.S.I.E., Purdue University. December 2014. Application of Bayesian Networks in Consumer Service Industry. Major professor: Vincent G. Duffy The purpose of the present study is to explore the application of Bayesian networks in the consumer service industry to model causal relationships within complex risk factor structures using aggregate data. An analysis of the Hawaii tourism market was conducted to find out how visitor characteristics affect their behavior and experience as consumers during the trips, and influence the tourism market outcomes represented by measurable factors. Two hypotheses were proposed regarding the use of aggregate data and the influence of …

Designing Sustainable Mentoring Programs: Examining The Role Of Social Community In The Stem College Student Experience, Joi-Lynn Mondisa

Open Access Theses

In order to begin to understand how to design programs that promote community development and produce beneficial outcomes for community members, we must first define the elements and functions of such a community. In this thesis, I define social community as an environment where like-minded individuals engage indynamic, multidirectional interactions that facilitate social support . Using a human-integrated systems approach, I propose a social community model for STEM minority mentoring programs to understand how a community's design plays a role in the learning and enrichment of its members. The social community model is comprised of three main components: program …