Completed Thesis Projects

Traffic Network Travel Time by Nithin Gopidi

Traffic Network Travel Time by Nithin Gopidi 2016-05-05 10:18:57

Nithin completed his thesis in May 2016.

Nithin created novel methods for deriving the speed and travel time distributions of emergency response vehicles across a traffic network.  He applied these methods to GPS data gathered from hundreds of thousands of routes by the Austin Fire Department.  His analysis allows for the identification of key intersections in the transportation network, where traffic control devices can be installed for maximum impact.  A traffic control device changes a stop signal prior to the arrival of the emergency response vehicle to an intersection.

Goto feature

Regression for Army Recruiting by Sandra Jackson

Regression for Army Recruiting by Sandra Jackson 2016-03-11 13:14:22

Sandra completed her report in May 2016.

In order to maintain military strength, the United States Army is consistently challenged with recruiting new soldiers. Currently the Army evaluates its recruiting capacity by calculating a weighted average of the previous four years of recruiting data. This report provides: (1) a description of the current method of calculating recruiting capacity; (2) an alternative approach for the calculation; and (3) an evaluation process and corresponding results to identify effective recruiting capacity methods. Specifically, the study analyzes the effectiveness of multiple linear regression and Poisson regression models to compute recruiting capacity. Surprisingly, even though essentially all previous literature on recruiting suggests Poisson regression to model recruiting arrival rates, we show strong empirical evidence that multi-linear regression is a better modeling tool than Poisson regression for the recruiting data. On out-of-sample tests involving 32 competing models, the negative log-likelihood for the multi-linear regression models is, on average over all the models, 11% smaller than the corresponding Poisson regression model. On.....

More , Goto feature

Texas Antiviral Release by Travis Chambers

Texas Antiviral Release by Travis Chambers 2016-03-11 12:56:14

Travis completed his thesis in March, 2015.

Influenza pandemics pose a serious threat to the global population. According to the United States Department of Health and Human Services in 2014, the Spanish flu of 1918 killed almost 100 million people worldwide and Simonsen, Spreeuwenberg, and Lustig in 2013 estimated that the Swine flu more recently killed approximately 180,000 people. Government agencies, from the United States Centers for Disease Control and Prevention down to state and local regions, are prepared to respond to potential influenza pandemics with antiviral, vaccine, and social interventions. Mathematical models can guide policies to saves lives. In this thesis, we create an optimization model, implemented in the online tool Texas Antiviral Release Scheduling (TAVRS) that provides the optimal geotemporal antiviral release schedule to advise decision makers at the Texas Department of State Health Services. We input the antiviral release schedule into an independent disease-spread simulation model to measure the effectiveness of the optimal release schedule. While the TAVRS optimal antiviral release schedule performs comparably to a simple population-proportionate.....

More , Goto feature

Kanban Supply System at Bethesda Medical Center

Kanban Supply System at Bethesda Medical Center 2015-10-21 14:00:49

Andy completed his thesis in September 2014.

Managing the distribution of medical supplies to clinical units within a hospital is a key component of a hospital’s administrative costs. In an attempt to control costs, Walter Reed National Military Medical Center (WRNMMC) installed a two-bin kanban system across multiple departments. In this thesis, we analyze the effectiveness of the kanban system from two viewpoints: organizational benefits—defined as the process of organizing the supply-chain into the two-bin kanban system—and inventory benefit—defined as the effects of staging the resupply in a two-bin fashion. We analyze two years of data, across twelve departments, comprising almost 375,000 items ordered. The results show significant organizational benefits to the hospital overall, and a steady-state in inventory costs. The data did not show consistent results across individual departments, with departments experiencing increases, decreases, and steady-states for both benefits. Additionally, we note that there is further room for WRNMMC to exploit the kanban system's ability to optimize inventory sizes via the two-bin kanban process.

Goto feature

Network Design by Christian Klaus

Network Design by Christian Klaus 2014-09-08 11:24:08

Christian completed his PhD at NPS in March 2014.

We define and solve two network-design problems. In the first, (1) a defender uses limited resources to select a portfolio of paths or design a sub-network; (2) an attacker then uses limited attack resources to destroy network arcs, and then (3) the defender operates the damaged network optimally by finding a shortest path. The solution identifies a network design that minimizes post-attack path length. We show how the tri-level problem is equivalent to a single-level mixed integer program (MIP) with an exponential number of rows and columns, and solve that MIP using simultaneous row and column generation. Methods extend to network operations defined through general flow constructs. The second problem considers a stochastic logistics network where arcs are present randomly and independently. Shipping from a source to a destination may be delayed until a path connecting the two is available. In the presence of storage capacity, cargo can be shipped partway. The problem's solution identifies the storage locations that minimize the cargo's waiting time for shipment. We develop and demonstrate practical methods to solve this.....

More , Goto feature

Reconfigurable Army Hospital by Trisha Cobb

Reconfigurable Army Hospital by Trisha Cobb 2014-09-08 10:44:07

Trisha completed her thesis at NPS in December 2013.

We will never know the operational battle space of the future, so medical assets need tobe flexible and agile to conform to a variety of environments and threats. We utilize amultistage optimization model and data from past contingency operations to analyze potential configurations of a robust theater deployable hospital. The current Army theater deployable hospital has 248-beds, and our analysis shows it is over-capacitated for the current brigade centric force structure. Based on our analysis, the optimal role 3 medical treatment facility is between 44-beds and 124-beds, with smaller wards, and the ability to combine hospitals to create larger hospitals. The smaller role 3 medical treatment facility better suites the tactical and operational employment of medical assets, and supports the strategic plans for regionally aligned forces.

Goto feature

Complex Casualty Care by Elizabeth Farrar

Complex Casualty Care by Elizabeth Farrar 2014-02-12 10:45:47

Liz completed her thesis at NPS in September 2013.

This study analyzes data from 182 Comprehensive Combat and Complex Casualty Care (C5) amputee patients with the goal to better understand the factors that influence their care. The data was provided from the Navy Bureau of Medicine and Surgery while visiting the Naval Medical Center at San Diego. The analysis examines two response variables, opiate drug usage and duration in the C5 program, as a function of a number of exploratory variables, including patient demographics, injury type, and appointment statistics. Logistic and linear regression models are used for data analysis. The study concludes that an increase in attendance to physical therapy, occupational therapy, and pain management and rehabilitation appointments correlates with an increased likelihood in reduced opiate usage. The study also concludes that the percentage of cancelled appointments is positively associated with the amputee’s duration in the program for non-Caucasian patients, patients with an improvised explosive device injury, and amputees with an upper-extremity amputation lower- and upper-extremity amputation.

Goto feature

Warehouses for a Stochastic Network by Christian Klaus

Warehouses for a Stochastic Network by Christian Klaus 2013-08-20 13:44:29

Christian Klaus is currently a Ph.D. student in the Operatoins Research Department at the Naval Postgraduate School.  His thesis topic is on designs for network reliability.  He delivered versions of this talk at ISMP 2012 and INFORMS 2012.  This part of his thesis has to do with increasing the reliability of a stochastic logistics network by introducing warehouses.  This complex operations research problem grew out of a related thesis by Meredith Dozier, on the DoD's transportation of humanitarian assistance cargo.

Goto feature

High Explanatory Power Model of FMD by Diwya Alok

High Explanatory Power Model of FMD by Diwya Alok 2013-03-27 11:42:53

Diwya completed his thesis at NPS in March 2013.   His work aims at creating relatively simple models that capture most of the variability in a state-of-the-art FMD simulator.  The abstract of his thesis is:

A study conducted by Carpenter, O’Brien, Hagerman and McCarl in 2011 estimates the economic impact of a foot and mouth disease (FMD) epidemic in the United States to be $2.3–$69.0 billion. We simulate an outbreak of FMD across central California using the InterSpread Plus simulation package. We use an experimental design that produces 102,400 epidemic simulation runs. Using the data from the simulations, we identify 16 critical disease and control parameters that have the greatest effect on the spread of FMD. A statistical model based on these 16 parameters and their interactions captures approximately 85% of the variability of the simulation model.

The main takeaways of our analysis of FMD spread are as follows. The two most critical disease parameters are initial condition and local spread. The most critical disease control parameters are market movement and surveillance. Our experimental results indicate that if a typical premise sends an animal to market every 2.2.....

More , Goto feature

IED Detection through Image Segmentation by Danny Heerlein

IED Detection through Image Segmentation by Danny Heerlein 2013-02-20 15:00:47

Danny completed his thesis in September of 2012.  Danny's thesis creates novel algorithms for the automatic creation of training images, and automatic detection of IEDs in the field.  The abstract of his thesis is:

This thesis creates algorithms to preprocess colored images in order to segment IEDs. IEDs are usually concealed and camouflaged and therefore more difficult to segment than other objects. We address the increased difficulty with three key contributions: 1) Our algorithm automatically divides a user-defined background area into smaller areas. We generate separate color models for each of these areas to ensure that a color model includes only colors that appear in the same area of the background. 2) We compress each of these complex color models into a statistical model. This increases the number of background models we can hold simultaneously in working memory, and allows us to generate a set of background models that describes a complete environment. 3) We estimate the initial object labels based on the color distance to the background. This approach allows us to generate color models for IEDs without user input that labels parts of the IED.

Goto feature

Foot and Mouth Disease in California by Brian Axelsen

Foot and Mouth Disease in California by Brian Axelsen 2012-07-24 10:30:45

Brian completed his thesis at NPS in June 2012.   His work creates and analyzes a state-wide simulation of a foot and mouth disease outbreaks in California. More specifically:

'Foot and mouth disease (FMD) is a highly contagious viral disease affecting cloven- hoofed domestic and some wild animals. An A hypothetical outbreak of FMD begun in California was recently estimated to have a national impact of up to $55 billion, mostly due to international trade restrictions (Carpenter, O’Brien, Hagerman, & McCarl, Carpenter et al., 2011 ). Therefore, preparedness for an outbreak is a high priority within the livestock industry, and state and federal government.

We use simulation and a designed experiment to identify robust governmental and industrial surveillance response strategies to control the spread of FMD. A strategy is considered robust if it is effective across a number of outbreak scenarios and a variety of disease spread characteristics.'

The main contributions of this thesis are: (1) the development of FMD outbreak scenarios across California that can be used in conjunction with a state-of-the-art, animal disease simulation model, and (2) the development and.....

More , Goto feature

Humanitarian Assistance Logistics by Meredith Dozier

Humanitarian Assistance Logistics by Meredith Dozier 2012-07-24 07:23:13

Meredith completed her thesis at NPS in March 2012.  Her work analyzes transportation of humaniatarian assistance cargo to Europe, but generalizes to the world-wide transportation.  The abstract of her thesis follows.

Humanitarian assistance is of growing importance to the United States and the Department of Defense’s strategic objectives.  Thus, United States combatant commands increasingly rely on humanitarian assistance cargo transportation programs to deliver material to people in need in their areas of responsibility.  This report analyzes the options available to these commands in seeking humanitarian assistance cargo transportation. The report offers a description of current operations, with a specific focus on the European area of responsibility, where these programs have had limited activity.

The analysis reaches the following conclusions: (1) currently no transportation program exists that focuses on providing a quality of service to combatant commands’ humanitarian assistance transportation needs; (2) legal, fiscal, and operational mechanisms exist and are outlined to create such a program; and (3) exclusively space-available transportation is generally.....

More , Goto feature

Healthcare Facility Locations in Bamyan, Afghanistan by Yong Kiong Teo

Healthcare Facility Locations in Bamyan, Afghanistan by Yong Kiong Teo 2011-12-13 12:56:04

Kiong completed his masters thesis at NPS in the winter of 2011.  His work concentrated on selecting good healthcare facility locations in Bamyan, Afghanistan.  The abstract of his thesis is as follows.

The facility location problem is one of the oldest and most researched operations research problems. In this thesis, we utilize facility location models to determine the optimal locations and types of medical facilities to address the healthcare needs of the people in Bamyan Province, Afghanistan. The staffing levels and materials of a local medical facility in Afghanistan are designed to cope with the healthcare needs of the people. In this thesis, the medical facilities are defined to be part of a network system. These facilities can be strategically located in order to provide essential healthcare services to the population. We investigate the location, operating cost, and accessibility of the existing and future healthcare facilities. We also look into the ethnicity problem that would affect the selection of operators for the medical facilities. Our model would lead to an increased understanding of the impact of healthcare facility locations and the selection of.....

More , Goto feature

Resiliency of the California Milk and Dairy Industry by Robert G. Alexander

Resiliency of the California Milk and Dairy Industry by Robert G. Alexander 2011-11-28 13:58:24

Rob completed his masters thesis at NPS in the fall of 2011.  His work concentrated on modeling the milk supply in California.  The abstract of his thesis is as follows.

We model the milk and dairy industry in California focusing on the production,processing, and distribution of bulk milk at the county level. We analyze the sensitivity ofthis industry when faced with worst-case disruptions, where a “worst-case” disruptioncorresponds to the greatest shortage of milk supply throughout California. The majorhighways in California are used to connect all of the counties and illustrate where thebulk milk is moving. We utilize Attacker-Defender (AD) modeling techniques todetermine where worst-case disruptions occur. This reveals vulnerabilities within themilk and dairy industry. We examine three specific scenarios: (1) a quarantine of eachcounty due to a Foot and Mouth Disease (FMD) outbreak or any other event that wouldcause the complete stoppage of production, processing and movement of milk in a countyover a seven day period; (2) 1 to 15 attacks on the milk and dairy industry in a 45 daytime period; and (3) the isolation of Northern and Southern California over a seven daytime.....

More , Goto feature


© Copyright 2004-2017 - Ned Dimitrov