Matching Items (57)
Description
Machine learning algorithms have a wide variety of applications and use cases. They are robust in the sense that they can continue to learn and improve long after they have been deployed without much programmer supervision. One key area that machine learning has been used for is in the detection and classification of objects in images and videos. This so-called computer vision has typically been used by companies to extract user information from the images and videos that they post. Meta (formerly known as Facebook) had been using such algorithms to automatically tag users in pictures that were uploaded to the Facebook website up until November 2021 [1]. Although these algorithms have been used to exploit user’s privacy, they can also be used to help ensure this privacy.
For this creative project, I developed a machine learning model that could detect faces in a given picture and identify the area of the picture that these faces took up. Training a model from scratch can take millions of images of data and hundreds of hours on powerful GPUs. Since I didn’t have access to those resources, I began with a pre-trained model known as VGG16 by Karen Simonyan & Andrew Zisserman. From there, I took 90 pictures of myself and annotated where in the image my face was located. Since 90 pictures wouldn’t be enough data for this algorithm, I used an image augmentation algorithm to randomly crop, flip, change brightness, change gamma, and recolor the images to expand the dataset. In total, I used 5400 images to train the algorithm.
The machine learning model had a loss value that hovered around 0.1 thanks to the VGG16 model. It was able to accurately detect my face and also adapt whenever I moved my face horizontally and vertically across a camera. However, the model struggled to draw a bounding box whenever I moved my face forward or backward in the camera shot.
ContributorsGutierrez, Ariel (Author) / Osburn, Steven (Thesis director) / Panchoo, Anthony (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05
Description
“Mix Mix Tayo: The Many Pieces in Our Stories'' is a written reflection, exploring the creation of the dance documentary, Carried Across the Water as well as the community event, Mix Mix Tayo. The ideas behind these works are centered in storytelling, filipino american identity and community. This research explores the use of film, dance, event production and the mixing of elements to create new wholes in order to communicate these ideas. These works were imagined in response to a call that was felt from people actively searching for healing, community and ancestral knowledge.
ContributorsCurry, Nicole (Author) / Standley, Eileen (Thesis advisor) / Fitzgerald, Mary (Committee member) / Nascimento, Eliciana (Committee member) / Arizona State University (Publisher)
Created2020
Description
For my creative project thesis, I have designed and developed a video game called Amity Academy. Amity Academy is a strategic resource management simulator that aims to subvert genre expectations and challenge generally accepted definitions of success and leadership both in-game and in the real world. It does so by moving the focus away from amassing large amounts of in-game currencies and becoming politically or militarily dominant towards caring for the denizens of the social unit the player controls. The player acts as an administrator at a school where they must make decisions on how to best run the institution. Although they are allowed to lead the school however they see fit, the emphasis is on prioritizing strong interpersonal and intracommunity relationships and connections and the wellbeing and happiness of those under their ward. Amity Academy is also part of the newly-emerging “wholesome” or “comfy” game genre. Unlike serious strategy games that can be stressful, Amity Academy presents a self-paced, low-stakes situation. This mood is further encouraged by calming environmental noises and music, a gentle color palette, and a charming art style. The game feels domestic and quaint, almost reminiscent of a Jane Wooster Scott or Mary Singleton painting. You can download and play Amity Academy here: https://mvaughn8.itch.io/amity-academy
ContributorsVaughn, Meghan (Author) / Kobayashi, Yoshihiro (Thesis director) / Holmes, Jeffrey (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor)
Created2021-12
Description
In 2010, two gamma-ray /x-ray bubbles were detected in the center of the Milky Way Galaxy. These bubbles extend symmetrically ≈ 30, 000 light years above and below the Galactic Center, with a width of ≈ 27, 000 light years. These bubbles emit gamma-rays at energies between 1 and 100 giga-electronvolts, have approximately uniform surface brightness, and are expanding at ≈ 30, 000 km/s. We believe that these Fermi Bubbles are the result of an astrophysical jet pulse that occurred millions of years ago. Utilizing high-performance computing and Euler’s Gas Dynamics Equations, we hope to find a realistic simulation that will tell us more about the age of these Fermi Bubbles and better understand the mechanism that powers the bubbles.
ContributorsWagner, Benjamin Leng (Author) / Gardner, Carl (Thesis director) / Jones, Jeremiah (Committee member) / Computing and Informatics Program (Contributor) / Department of Information Systems (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
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'DOPE SICK' is an experimental film exploring love addiction set to original narrative form poetry.
ContributorsContreras, Stefano (Author) / Nascimento, Eliciana (Thesis director) / Benavides, Adam (Committee member) / Barrett, The Honors College (Contributor) / Historical, Philosophical & Religious Studies, Sch (Contributor) / The Sidney Poitier New American Film School (Contributor)
Created2024-05
Description
This paper describes the Divine Decisions project, an experiment on the synthesis of physical and digital design techniques in the field of video game design and development. The project is inspired by unique types of video game input devices like the Nintendo R.O.B, the digital twin technologies utilized in Activision Blizzard’s Skylanders series, and the narrative themes present in titles such as Undertale and Fear and Hunger, with the ultimate goal of creating a uniquely immersive experience that enhances the user’s sense of agency and responsibility for their choices. Divine Decisions examines how the use of physical, interactive elements can affect how an audience experiences a digital narrative and how they choose to interact with it.
ContributorsCraven, Jonah (Author) / Kautz, Luke (Thesis director) / Kirtz, Jaime (Committee member) / Barrett, The Honors College (Contributor) / School of Human Evolution & Social Change (Contributor) / Computing and Informatics Program (Contributor) / Arts, Media and Engineering Sch T (Contributor)
Created2024-05