Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
- Publication Type
Articles 1 - 3 of 3
Full-Text Articles in Physical Sciences and Mathematics
Graph-Based Learning, Jason Gronn
Graph-Based Learning, Jason Gronn
Honors Projects
An educational approach to teaching students based on prerequisite knowledge they may or may not have is presented. This approach represents educational content in the form of a graph, where edges link each topic to the prerequisites of that topic. A proof-of-concept website is created based on this approach, where qualitative results are observed and a number of conclusions are drawn. Some of the findings are that, while it can prevent users from being confused by lacked prior knowledge, the users may instead be confused by the presentation of the graph structure. The work finds that the approach is workable, …
The Social Pot: A Social Media Application, Reid Long
The Social Pot: A Social Media Application, Reid Long
Honors Projects
The Social Pot is a web application that allows a user to post to Instagram and X simultaneously from one place. The user creates a Social Pot Account and from there can set their Instagram username and password within the home page. Once the user attempts to post, it will redirect them to login to X which once successful will make the tweet. Used the API 'instagram-private-api'. User needed to give access to my X Project which in turn gave an Auth token (via X redirect URL). The auth token was then sent to my endpoint in order to get …
Statistically Principled Deep Learning For Sar Image Segmentation, Cassandra Goldberg
Statistically Principled Deep Learning For Sar Image Segmentation, Cassandra Goldberg
Honors Projects
This project explores novel approaches for Synthetic Aperture Radar (SAR) image segmentation that integrate established statistical properties of SAR into deep learning models. First, Perlin Noise and Generalized Gamma distribution sampling methods were utilized to generate a synthetic dataset that effectively captures the statistical attributes of SAR data. Subsequently, deep learning segmentation architectures were developed that utilize average pooling and 1x1 convolutions to perform statistical moment computations. Finally, supervised and unsupervised disparity-based losses were incorporated into model training. The experimental outcomes yielded promising results: the synthetic dataset effectively trained deep learning models for real SAR data segmentation, the statistically-informed architectures …