Engineering Commons^™

A Data-Driven Framework For Analyzing And Predicting Social Media Engagement During Rumor Propagation, Joseph E. Faza

Master's Theses

The spread of rumors on social media has become a significant concern, as platforms like X (formerly known as Twitter) enable rapid dissemination of unverified information. These rumors can shape public perception and behavior, making it crucial to understand the dynamics of their spread. The main objective of this study is to explore how users interact with rumor-related tweets and identify key factors that predict tweet engagement. By analyzing tweets from seven different rumor events, this research aims to uncover patterns in user engagement and provide insights into the spread of misinformation. The study utilized a dataset of tweets from …

Effective And Sustainable Strategies For Federally Qualified Health Centers To Engage Young Adults, Olivia Mcnulty

Master's Theses

Federally qualified health centers (FQHCs) are instrumental in providing top tier healthcare and other resources to underserved populations. Whether they administer services in house or refer patients to other providers, FQHCs aim to provide comprehensive primary and preventative care services to people of all ages. They offer a range of services, from doctor and dental appointments to mental health and substance abuse counseling, regardless of a patient’s insurance status. To receive funding, FQHCs must follow the regulations and quality standards set forth by groups like the Joint Commission on Accreditation of Healthcare Organizations (JCAHO) and the Health Resources and Services …

Simulating Electric Vehicle Short-Notice Wildfire Evacuation In California Rural Communities, Gudrun Derickson

Master's Theses

The transportation sector in California has begun a shift toward adopting Electric Vehicles (EVs) as a primary source of individual and corporate mobility. The US Government and the State of California are initiating public-sector financed charging station infrastructure to help in this change-over to EVs. Automobile companies and private enterprises are also heavily investing in Battery Electric Vehicle (BEV) infrastructure going forward. The state of California is subject to natural disasters such as Fire, Earthquakes, and periodic flooding. Increasing numbers of BEVs may add new challenges to mass evacuations that are often associated with natural disasters. This work focuses on …

Subnational Map Of Poverty Generated From Remote-Sensing Data In Africa: Using Machine Learning Models And Advanced Regression Methods For Poverty Estimation, Lionel N. Hanke

Master's Theses

According to the 2020 poverty estimates from the World Bank, it is estimated that 9.1% - 9.4% of the global population lived on less than $1.90 per day. It is estimated that the Covid-19 pandemic further aggravated the issue by pushing more than 1% of the global population below the international poverty line of $1.90 per day (WorldBank, 2020). To provide help and formulate effective measures, poverty needs to be located as exact as possible. For this purpose, it was investigated whether regression methods with aggregated remote-sensing data could be used to estimate poverty in Africa. Therefore, five distinct regression …

Minimizing Leakage In Thin Walled Structures Printed Through Selective Laser Melting, Andrew Spencer Yap

Master's Theses

In this project, the scan strategy of selective laser melting (SLM) for thin walled structures was investigated by changing laser parameters and tool path. Producing thin walled structures is difficult due to defects such as warpage and porosity. A layer on the SLM 125 consists of hatch volume, fill contours, and borders, however, for thin walls, hatch volume can become unavailable, resulting in a solely border/fill contour laser tool path.

Three central composite designs (CCD) were created to optimize the laser parameters of borders to minimize leakage rate and porosity. The two factors changed were border laser power and scanning …

Modeling And Solving The Outsourcing Risk Management Problem In Multi-Echelon Supply Chains, Arian A. Nahangi

Master's Theses

Worldwide globalization has made supply chains more vulnerable to risk factors, increasing the associated costs of outsourcing goods. Outsourcing is highly beneficial for any company that values building upon its core competencies, but the emergence of the COVID-19 pandemic and other crises have exposed significant vulnerabilities within supply chains. These disruptions forced a shift in the production of goods from outsourcing to domestic methods.

This paper considers a multi-echelon supply chain model with global and domestic raw material suppliers, manufacturing plants, warehouses, and markets. All levels within the supply chain network are evaluated from a holistic perspective, calculating a total …

Perishable Food Waste Reduction Through Technological Implementation At The Retail Level Of The Food Supply Chain, Cassandra Harriman

Master's Theses

Food waste has become a disaster of global proportion that the world can no longer turn a blind eye to. This paper aims to reduce food waste at the retail level of the food supply chain by recommending and quantifying the effects of current technology that can be implemented in traditional supermarkets. This research recommends that retailers implement electronic shelf labels in stores and employ dynamic pricing of perishable products, leading to reduction of food waste. No prior research had considered the primary goal of reducing food waste while preserving retailer profit through technological implementation. This paper quantifies the effects …

Understanding The Impact Of The Covid-19 Pandemic Within Educational Communities Using Longitudinal Analysis, Alexa Steidl

Master's Theses

At California State University, Los Angeles and California Polytechnic University, San Luis

Obispo, a longitudinal survey was created in response to the COVID-19 pandemic for students within their respective engineering departments. A combination of nonparametric and longitudinal analysis is performed to evaluate the impacts of the transition to a virtual educational environment and the stressors brought on by the global pandemic. Additional qualitative evaluation is performed to gain insight and make program recommendations to enhance the resilience of individuals in the academic systems. Results demonstrate a large shift in circumstances immediately at the start of the pandemic, with a variety …

Transfer Learning Approach To Powder Bed Fusion Additive Manufacturing Defect Detection, Michael Wu

Master's Theses

Laser powder bed fusion (LPBF) remains a predominately open-loop additive manufacturing process with minimal in-situ quality and process control. Some machines feature optical monitoring systems but lack automated analytical capabilities for real-time defect detection. Recent advances in machine learning (ML) and convolutional neural networks (CNN) present compelling solutions to analyze images in real-time and to develop in-situ monitoring.

Approximately 30,000 selective laser melting (SLM) build images from 31 previous builds are gathered and labeled as either “okay” or “defect”. Then, 14 open-sourced CNN were trained using transfer learning to classify the SLM build images. These models were evaluated by F1 …

Comparison Of Classification Algorithms And Undersampling Methods On Employee Churn Prediction: A Case Study Of A Tech Company, Heather Cooper

Master's Theses

Churn prediction is a common data mining problem that many companies face across industries. More commonly, customer churn has been studied extensively within the telecommunications industry where there is low customer retention due to high market competition. Similar to customer churn, employee churn is very costly to a company and by not deploying proper risk mitigation strategies, profits cannot be maximized, and valuable employees may leave the company. The cost to replace an employee is exponentially higher than finding a replacement, so it is in any company’s best interest to prioritize employee retention.

This research combines machine learning techniques with …

Combining Machine Learning And Empirical Engineering Methods Towards Improving Oil Production Forecasting, Andrew J. Allen

Master's Theses

Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) …

Design Of A Printed Circuit Board For A Sensorless Three-Phase Brushless Dc Motor Control System, Joshua Castle

Master's Theses

The use of brushless motors has increased in recent years due to superior performance characteristics compared with alternatives. The operation of a brushless motor is dependent upon a separate controller which is often in the form of a printed circuit board. As such, the size and performance capability of the controller can restrict the performance of the overall motor control system so advancements of these controllers further the potential use of BLDC motors. This project outlines the design of a PCB based, sensorless motor controller for operation of a three-phase BLDC motor powered by a 24 V, high current external …

Characterization Of Resistance Change In Stretchable Silver Ink Screen Printed On Tpu-Laminated Fabrics Under Cyclic Tensile Loading, Corey R. Sutton

Master's Theses

A stretchable silver ink was screen printed to TPU sheets, then tensile coupons of the TPU, both bare and laminated to cotton, Denim and spandex fabric, were subjected to 1000 cycles of 20% uniaxial strain. In-situ resistance measurements of printed traces were processed to generate datasets of maximum and minimum resistance per cycle. A mechanistic fit model was used to predict the resistance behavior of the ink across TPU/fabric levels. The results show that traces strained on TPU laminated to spandex (polyester) fibers had an average rate of increase in resistance significantly lower than that of traces strained on bare …

Application Of Big Data Analytics In Agriculture Supply Chain Management, Sankara Narayanan Mangalam Ananthapadmanabhan

Master's Theses

The increasing trend in frequency of natural disasters in tandem with globalization of business makes the agricultural supply chain significantly vulnerable to disruption. This thesis presents a pragmatic approach for creating a Business Continuity Model that can notify supply chain planners when there is an increase in risk of agriculture supply chain disruption due to natural disasters. The methodology presented in this thesis applied big data analytics and machine learning algorithms along with agriculture product related exponential decay function to create a regionalized composite risk score, that incorporated both direct and indirect risk associated with the Agriculture Fresh Supply Chain. …

Using Computer Vision To Build A Predictive Model Of Fruit Shelf-Life, Nandan G. Thor

Master's Theses

Computer vision is becoming a ubiquitous technology in many industries on account of its speed, accuracy, and long-term cost efficacy. The ability of a computer vision system to quickly and efficiently make quality decisions has made computer vision a popular technology on inspection lines. However, few companies in the agriculture industry use computer vision because of the non-uniformity of sellable produce. The small number of agriculture companies that do utilize computer vision use it to extract features for size sorting or for a binary grading system: if the piece of fruit has a certain color, certain shape, and certain size, …

Continuum Modeling Of The Densification Of W-Ni-Fe During Selective Laser Sintering, Connor M. West

Master's Theses

The purpose of this thesis is to effectively model the time history of the temperature distribution during the selective laser sintering process and use this information to investigate the resulting relative density. The temperature is a critical parameter of the process because it directly effects the overall quality of the part. First, an efficient, affordable, and reliable simulation was developed within the finite element software, Abaqus. Next, the results from the simulations were compared to the experimental results performed by Wang et al. (2016). The FEA model consisted of a 3 layer simulation. Multiple simulations at various laser recipes were …

Optimization Of Rfid System Coverage In A Manufacturing Environment, Scott D. Malatesta

Master's Theses

This paper compiles existing ideas, theories, and experiments across multiple disciplines to provide guidance for a company looking to implement an optimal RFID system in their production facility. The desire is to maximize the information received by the system while minimizing the cost. Four potential layouts of RFID antennas, two with overlapping antenna coverage and two with non-overlapping layouts, are first analyzed to understand the special coverage and the number of antennas required. The value of information is then quantified to determine whether higher coverage layouts are worth the additional costs associated with the higher number of antennas required. It …

A Simulation Model For Decision Support In Business Continuity Planning, Marissa Anne Mosunich

Master's Theses

Enterprises with a global supply network are at risk of lost revenue as a result of disruptive disasters at supplier locations. Various strategies exist for addressing this risk, and a variety of types of research has been done regarding the identification, assessment and response to the risk of disruption in a supply chain network.

This thesis establishes a decision model to support Business Continuity Planning at the first-tier supplier level. The decision model incorporates discrete-event simulation of supply chain networks (through Simio software), Monte Carlo simulation, and risk index optimization. After modeling disruption vulnerability in a supply chain network, costs …

Ergonomics Analysis Of Touchscreen Utilization As A Function Of Preferred Hand And Gender, Jordan E. Odell

Master's Theses

The growth of touchscreen technology has changed the way users interface with a wide range of computing and communication products and systems. Examples range from personal tablets and laptops to industrial applications such as process control, point-of-sales, and ticketing kiosk systems. An important area of application is the automobile industry which is designing cars with touchscreen control panels to replace the previously designed mechanical knobs and buttons. However, interacting with touchscreens does not provide the same tactile feedback as physical mechanisms, therefore they require more precise movement and visual attention, which distracts the user from the primary task.

The purpose …

Methane Production By A Packed-Bed Anaerobic Digester Fed Dairy Barn Flush Water, Sean Richard Thomson

Master's Theses

Packed-bed digesters are an alternative to covered lagoon digesters for methane production and anaerobic treatment of dilute wastewaters such as dairy barn flush water. The physical media of packed-beds retain biofilms, often allowing increased treatment rates. Previous studies have evaluated several types of media for digestion of dilute wastewaters, but cost and media fouling have setback commercial development. A major operational cost has been effluent recirculation pumping.

In the present effort, a novel approach to anaerobic digestion of flush dairy water was developed at pilot-scale: broken walnut shells were used as a low-cost packed-bed medium and effluent recirculation was replaced …

A Set Union Based Formulation For Course Scheduling And Timetabling, Jesse Paul Bukenberger

Master's Theses

The Course Timetabling Problem is a widely studied optimization problem where a number of sections are scheduled in concert with the assignment of students to sections in order to maximize the desirability of the resulting schedule for all stakeholders. This problem is commonly solved as a linear program with variables for each student or group of students with identical schedules. In this paper we explore an alternative formulation that aggregates binary student variables into integer variables denoting the number of students enrolled in a course. Our solution method assumes decomposition of the general schedule into time blocks, and applies a …

Analysis Of Environmentally Friendly Marking Ink For Military Equipment And Electronics, Liang Li

Master's Theses

Recent advancements in corrosion-resistance coating technology has reduce the use of environmentally harmful compounds such as Hexavalent Chromium by replacing Hexavalent Chromium in primers and topcoat. However, marking inks were neglected in the process. Products such as Enthone 50 series are still widely used, which contain compounds such as lead, hexavalent chromium, bisphenol A (BPA), Cadmium Sulfide, and more. Excluding catalyst compositions in Enthone, the chemicals in the ink alone contained three reproductive toxicant and numerous carcinogens. Therefore, it was essential to search and validate the performance of potential marking ink that would meet the standards in military applications.

Eleven …

Investigating Present And Future Interactions Between Radio Frequency Identification, Additive Manufacturing And Supply Chain Management, Michael Nobuhiro Ochi

Master's Theses

A screening experiment was paired with research observing the past, present and futures of additive manufacturing (a.k.a. rapid prototyping, 3D printing), radio frequency identification, and supply chain management. The experiment tested different properties of objects created with a desktop fused deposition modelling printer to observe if any single factors or interactions affected the read range of embedded passive UHF RFID inlay. The combination of material and infill percentage had a statistically significant effect on read range, however the analysis is weak since the data could not justify the normality assumption of ANOVA. Furthermore, the size of the effect was small …

Applying Sustainability From A Systems Perspective:, Timothy Brophy

Master's Theses

Becoming sustainable is no longer an option. Current industry methods will not be able to support the necessary changes our growing society demands. In order to keep up with ever increasing demands industry will be aimed toward making major system changes toward a fully sustainable model. As of right now only basic sustainability actions have been put in place. Industry needs to make a strategic change toward resilient systems with an end goal of evolving into fully biomimic systems. This thesis covers a brief history of production leading to the Industrial Revolution which created a need for increased sustainability efforts. …

Manufacturing Execution System (Mes) An Examination Of Implementation Strategy, Riley F. Elliott

Master's Theses

The priorities of executing the manufacturing orders generated by an MRP system are often in operational conflicts with the dynamics of the manufacturing floor. It is not uncommon for a given manufacturing order to reach the shop floor several weeks or longer after being "opened" by an MRP system where it may face a chaotic case of large queues, machine down-time, parts shortage, scrap problems and other resource management constraints. Many companies have resorted to the Manufacturing Execution System (MES) software solution to resolve these problems. This method first gained popularity in mid-90’s within the semiconductor industry. An MES approach …

A Stand-Alone Methodology For Data Exploration In Support Of Data Mining And Analytics, Michael Gage

Master's Theses

With the emergence of Big Data, data high in volume, variety, and velocity, new analysis techniques need to be developed to effectively use the data that is being collected. Knowledge discovery from databases is a larger methodology encompassing a process for gathering knowledge from that data. Analytics pair the knowledge with decision making to improve overall outcomes. Organizations have conclusive evidence that analytics provide competitive advantages and improve overall performance. This paper proposes a stand-alone methodology for data exploration. Data exploration is one part of the data mining process, used in knowledge discovery from databases and analytics. The goal of …

Rfid Technology Selection And Economic Justification For Healthcare Asset Tracking, Tyler Robert Peabody, Tali Freed

Master's Theses

Although Radio Frequency Identification (RFID) and Real-Time Location System (RTLS) technologies for inventory tracking have been growing in popularity, the healthcare industry has been reluctant to adopt these technologies. One of the primary reasons for this lack of enthusiasm has been the risk associated with electromagnetic interference between RFID/RTLS systems and medical equipment functionality. The other reason has been the substantial cost and complexity of implementing RFID/RTLS in healthcare organizations. In this study, we show that there are several ways to safely install RFID/RTLS systems to improve the inventory management processes of hospitals and clinics. We then analyze the inventory …

Reliability Analysis Of Low-Silver Bga Solder Joints Using Four Failure Criteria, Erin A. Kimura

Master's Theses

The appropriate selection of failure criterion for solder joint studies is necessary to correctly estimate reliability life. The objective of this study is to compare the effect of different failure criteria on the reliability life estimation. The four failure criteria in this study are a 20% resistance increase defined in the IPC-9701A standard, a resistance beyond 500 Ω, an infinite resistance (hard open), and a failure criterion based on X-bar and R control charts. Accelerated thermal cycling conditions of a low-silver BGA study included 0°C to 100 °C with ten minute dwell times and -40°C to 125°C with ten minute …

The Effect Of Stretch Wrap Pre-Stretch On Unitized Load Containment, Evan A. Cernokus

Master's Theses

There are three main factors affecting the stability of a palletized load that is unitized by a stretch wrapping mechanism. These factors include the type of unitized load, wrapping configuration and shipping method. The wrapping configuration is determined on the basis of the type of unitized load and shipping method. For this study, the aforementioned components were referred to as the package, the product, and the distribution environment. These components come together to make up a stretch wrapping system. The package corresponds to the stretch wrap film that is packaging the unitized load and pallet. The product corresponds to the …

Comparative Analysis Of Erp Emerging Technologies, Ryan Engebrethson

Master's Theses

This Master's Thesis compares technologies used in the architecture of Enterprise Resource Planning (ERP) Systems to evaluate the benefits and advantages of emerging technologies. The emerging technologies, Cloud Computing, Software as a Service (SaaS) and Multi-Tenancy, could significantly alter the current ERP space and become a primary part of ERP Systems of the future. A survey was sent to industry professionals to obtain feedback on their company's ERP Systems and to collect their comments on these new technologies. The survey results and related analysis show that Emerging Cloud ERP Systems outperform Traditional Legacy ERP Systems in all important characteristics - …