Operations Research, Systems Engineering and Industrial Engineering Commons^™

A Neural Network For Collaborative Forecasting, Abdulrahman M. Enani

Masters Theses

As the supply chain activities’ backbone, demand forecasting must be accurate. This paper proposes an artificial neural network forecasting model, which integrates and synchronizes shared information, such as sales or consumption rate among different partners, to improve the forecasting’s accuracy. This information sharing is part of the collaborative planning, forecasting and replenishment (CPFR) model, which is a supply chain model aiming to enhance the supply chain’s efficiency by jointly planning and forecasting between two or more supply chain partners that will be used as the base for production and replenishment activities. The model is validated using a tuna product sales …

A Mixed Integer Linear Programming Approach For Developing Salary Administration Systems, Taner Cokyasar

Masters Theses

Determining salary increases of executive personnel is a challenging decision process for many companies. Salary administration policies that aid in the determination of salary increases and other compensation benefits have a wide variety of advantages for both a company and its employees. This thesis develops a mathematical programming approach to create a salary administration system that recognizes the importance of performance and potential of employees for future promotions as major components of a salary increase policy for executive personnel. A number of companies all over the world use salary administration systems that integrate work performance and potential for advancement to …

Automatic Sleep Stages Classification, Maryam Zokaeinikoo

Masters Theses

In this thesis, we first develop an efficient automated classification algorithm for sleep stages identification. Polysomnography recordings (PSGs) from twenty subjects were used in this study and features were extracted from the time{frequency representation of the electroencephalography (EEG) signal. The classification of the extracted features was done using random forest classifier. The performance of the new approach is tested by evaluating the accuracy of each sleep stages and total accuracy. The results shows improvement in all five sleep stages compared to previous works.

Then, we present a simulation decision algorithm for switching between sleep interventions. This method improves the percentage …

Optimizing Cash Flows And Minimizing Simultaneous Turnovers In Operating Room Scheduling, Mohit Shukla

Masters Theses

Currently, the scheduling of surgical suites follows either an open booking or block booking framework. Under block booking, medical departments (or surgeons) that provide certain types of services (e.g. ophthalmology, orthopedics, cardiology) are assigned fixed blocks of time that are used to divide access to the operating rooms (ORs) among different specialties. Two integer-programming based methods of generating block schedules are investigated in this research. The first approach focuses on optimizing cash flows, an area not studied previously within the OR scheduling domain. Results indicate that while there is some utility of this approach in improving the liquidity of a …

Standardizing Functional Safety Assessments For Off-The-Shelf Instrumentation And Controls, Andrew Michael Nack

Masters Theses

It is typical for digital instrumentation and controls, used to manage significant risk, to undergo substantial amounts of scrutiny. The equipment must be proven to have the necessary level of design integrity. The details of the scrutiny vary based on the particular industry, but the ultimate goal is to provide sufficient evidence that the equipment will operate successfully when performing their required functions.

To be able to stand up to the scrutiny and more importantly, successfully perform the required safety functions, the equipment must be designed to defend against random hardware failures and also to prevent systematic faults. These design …