Matching Items (300)
Filtering by
- All Subjects: engineering
- All Subjects: Machine Learning
- Creators: Barrett, The Honors College
Description
The goal of this thesis project was to build an understanding of supersonic projectile dynamics through the creation of a trajectory model that incorporates several different aerodynamic concepts and builds a criteria for the stability of a projectile. This was done iteratively where the model was built from a foundation of kinematics with various aerodynamic principles being added incrementally. The primary aerodynamic principle that influenced the trajectory of the projectile was in the coefficient of drag. The drag coefficient was split into three primary components: the form drag, skin friction drag, and base pressure drag. These together made up the core of the model, additional complexity served to increase the accuracy of the model and generalize to different projectile profiles.
ContributorsBlair, Martin (Co-author) / Armenta, Francisco (Co-author) / Takahashi, Timothy (Thesis director) / Herrmann, Marcus (Committee member) / Mechanical and Aerospace Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Effective communication and engineering are not a natural pairing. The incongruence is because engineering students are focused on making, designing and analyzing. Since these are the core functions of the field there is not a direct focus on developing communication skills. This honors thesis explores the role and expectations for student engineers within the undergraduate engineering education experience to present and communicate ideas. The researchers interviewed faculty about their perspective on students' abilities with respect to their presentation skills to inform the design of a workshop series of interventions intended to make engineering students better communicators.
ContributorsAlbin, Joshua Alexander (Co-author) / Brancati, Sara (Co-author) / Lande, Micah (Thesis director) / Martin, Thomas (Committee member) / Industrial, Systems and Operations Engineering Program (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Solar panels need to be both cost effective and environmentally friendly to compete with traditional energy forms. Photovoltaic recycling has the potential to mitigate the harm of waste, which is often landfilled, while putting material back into the manufacturing process. Out of many, three methods show much promise: Full Recovery End-of-Life Photovoltaic (FRELP), mechanical, and sintering-based recycling. FRELP recycling has quickly gained prominence in Europe and promises to fully recover the components in a solar cell. The mechanical method has produced high yields of valuable materials using basic and inexpensive processes. The sintering method has the potential to tap into a large market for feldspar. Using a levelized cost of electricity (LCOE) analysis, the three methods could be compared on an economic basis. This showed that the mechanical method is least expensive, and the sintering method is the most expensive. Using this model, all recycling methods are less cost effective than the control analysis without recycling. Sensitivity analyses were then done on the effect of the discount rate, capacity factor, and lifespan on the LCOE. These results showed that the change in capacity factor had the most significant effect on the levelized cost of electricity. A final sensitivity analysis was done based on the decreased installation and balance of systems costs in 2025. With a 55% decrease in these costs, the LCOE decreased by close to $0.03/kWh for each method. Based on these results, the cost of each recycling method would be a more considerable proportion of the overall LCOE of the solar farm.
ContributorsMeister, William Frederick (Author) / Goodnick, Stephen (Thesis director) / Phelan, Patrick (Committee member) / Mechanical and Aerospace Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This thesis project focused on determining the primary causes of flight delays within the United States then building a machine learning model using the collected flight data to determine a more efficient flight route from Phoenix Sky Harbor International Airport in Phoenix, Arizona to Harry Reid International Airport in Las Vegas, Nevada. In collaboration with Honeywell Aerospace as part of the Ira A. Fulton Schools of Engineering Capstone Course, CSE 485 and 486, this project consisted of using open source data from FlightAware and the United States Bureau of Transportation Statistics to identify 5 primary causes of flight delays and determine if any of them could be solved using machine learning.
The machine learning model was a 3-layer Feedforward Neural Network that focused on reducing the impact of Late Arriving Aircraft for the Phoenix to Las Vegas route. Evaluation metrics used to determine the efficiency and success of the model include Mean Squared Error (MSE), Mean Average Error (MAE), and R-Squared Score.
The benefits of this project are wide-ranging, for both consumers and corporations. Consumers will be able to arrive at their destination earlier than expected, which would provide them a better experience with the airline. On the other side, the airline can take credit for the customer's satisfaction, in addition to reducing fuel usage, thus making their flights more environmentally friendly.
This project represents a significant contribution to the field of aviation as it proves that flights can be made more efficient through the usage of open source data.
ContributorsRosenbloom, Yonatan (Author) / Chavez Echeagaray, Maria Elena (Thesis director) / Govindillam, Sreenivasan (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor)
Created2024-05
Description
The “flipped classroom” approach entails the reversal of traditional teaching methods, such that students engage with instructional content independently before class, and in-class time is dedicated to active learning, problem-solving, and collaborative activities. This paper predominantly consists of literature review. This paper explores the impact of the flipped classroom model on student engagement, comprehension, and critical thinking skills. The findings aim to contribute valuable insights into the potential benefits and limitations of the flipped classroom model in the realm of engineering education, shedding light on its applicability as a transformative instructional strategy for enhancing student learning outcomes and preparing future engineers for the demands of their profession.
Keywords: Flipped, classroom, engineering
ContributorsJones, Shepherd (Author) / Hjelmstad, Keith (Thesis director) / Chatziefstratiou, Efthalia (Committee member) / Barrett, The Honors College (Contributor) / Civil, Environmental and Sustainable Eng Program (Contributor)
Created2024-05
Description
Manually determining the health of a plant requires time and expertise from a human. Automating this process utilizing machine learning could provide significant benefits to the agricultural field. The detection and classification of health defects in crops by analyzing visual data using computer vision tools can accomplish this. In this paper, the task is completed using two different types of existing machine learning algorithms, ResNet50 and CapsNet, which take images of crops as input and return a classification that denotes the health defect the crop suffers from. Specifically, the models analyze the images to determine if a nutritional deficiency or disease is present and, if so, identify it. The purpose of this project is to apply the proven deep learning architecture, ResNet50, to the data, which serves as a baseline for comparison of performance with the less researched architecture, CapsNet. This comparison highlights differences in the performance of the two architectures when applied to a complex dataset with a multitude of classes. This report details the data pipeline process, including dataset collection and validation, as well as preprocessing and application to the model. Additionally, methods of improving the accuracy of the models are recorded and analyzed to provide further insights into the comparison of the different architectures. The ResNet-50 model achieved an accuracy of 100% after being trained on the nutritional deficiency dataset. It achieved an accuracy of 88.5% on the disease dataset. The CapsNet model achieved an accuracy of 90% on the nutritional deficiency dataset but only 70% on the disease dataset. In comparing the performance of the two models, the ResNet model outperformed the other; however, the CapsNet model shows promise for future implementations. With larger, more complete datasets as well as improvements to the design of capsule networks, they will likely provide exceptional performance for complex image classification tasks.
ContributorsChristner, Drew (Author) / Carter, Lynn (Thesis director) / Ghayekhloo, Samira (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05
Description
The InceptionTime model is a tool modified for time series regression. For the first time in history, Read Montague’s lab at Virginia Tech has developed methods to measure neurotransmitters in the human brain using InceptionTime to analyze fast-scan cyclic voltammetry (FSCV) data. FSCV has been around for decades and has been previously used to study concentrations of the neurotransmitter dopamine. However, unlike older analysis techniques such as principal component regression, InceptionTime can distinguish between catecholamines such as dopamine, norepinephrine, and serotonin, thereby vastly increasing FSCV’s utility. This paper serves as an investigation of the InceptionTime model, its applications in FSCV experiments, and provides information about electrochemical concepts that are integral in understanding the value of this research.
ContributorsAger, Katrina (Author) / McClure, Samuel (Thesis director) / Brewer, Gene (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor)
Created2024-05
Description
Supply chain management is a complex field that deals with a variety of ever-changing factors, and artificial intelligence has the opportunity to create lots of value and drive efficiency if organizations can implement it effectively. This thesis examines the different types of AI based on functionality and capability and provides a brief overview of the history behind artificial intelligence. Different supply chain functions including demand forecasting, inventory management, route optimization, supply transparency, and safety and sustainability were analyzed before and after adding AI systems. After examining AI missteps and successes in recent years, a detailed roadmap was created to help decision-makers deal with the numerous complexities when implementing AI technology within a business to improve the supply chain.
ContributorsHildebrand, Ryan (Author) / Printezis, Antonios (Thesis director) / Pofahl, Geoffrey (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor) / Department of Supply Chain Management (Contributor)
Created2024-05
Description
This thesis explores strategies to enhance visibility and engagement within local music ecosystems using a data-driven approach that leverages streaming platform data. It employs a two-pronged approach, consisting of a Proof of Concept (PoC) and a Business Model Canvas (BMC). The PoC involves the development and refinement of two novel machine learning-based music recommendation algorithms, specifically tailored for local stakeholders in the Valley Metro area. Empirical testing of these algorithms has shown a significant potential increase in visibility and engagement for local music events. Utilizing these results, the study proposes informed revisions to the existing streaming BMC, aiming to better support local music ecosystems through strategic enhancements derived from the validated PoC findings.
ContributorsEllini, Andre (Author) / Clarkin, Michael (Co-author) / Bradley, Robert (Co-author) / Mancenido, Michelle (Thesis director) / Sirugudi, Kumar (Committee member) / Barrett, The Honors College (Contributor) / Mechanical and Aerospace Engineering Program (Contributor)
Created2024-05
Description
The performance of modern machine learning algorithms depends upon the selection
of a set of hyperparameters. Common examples of hyperparameters are learning
rate and the number of layers in a dense neural network. Auto-ML is a branch
of optimization that has produced important contributions in this area. Within
Auto-ML, multi-fidelity approaches, which eliminate poorly-performing configurations
after evaluating them at low budgets, are among the most effective. However, the
performance of these algorithms strongly depends on how effectively they allocate
the computational budget to various hyperparameter configurations. We first present
Parameter Optimization with Conscious Allocation 1.0 (POCA 1.0), a hyperband-
based algorithm for hyperparameter optimization that adaptively allocates the inputted
budget to the hyperparameter configurations it generates following a Bayesian sampling
scheme. We then present its successor Parameter Optimization with Conscious
Allocation 2.0 (POCA 2.0), which follows POCA 1.0’s successful philosophy while
utilizing a time-series model to reduce wasted computational cost and providing a
more flexible framework. We compare POCA 1.0 and 2.0 to its nearest competitor BOHB
at optimizing the hyperparameters of a multi-layered perceptron and find that both
POCA algorithms exceed BOHB in low-budget hyperparameter optimization while
performing similarly in high-budget scenarios.
ContributorsInman, Joshua (Author) / Sankar, Lalitha (Thesis director) / Pedrielli, Giulia (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05