Matching Items (688)
Filtering by
- Creators: Computer Science and Engineering Program
Description
Major Depressive Disorder (MDD) is a common mental disorder that can affect individuals at nearly every stage of life. Women are especially vulnerable to MDD in part, from ovarian hormone level fluctuations. In this thesis, I focused on MDD using a rat model in middle-age to explore potential sex differences in response to a corticosterone (CORT) – induced depressive-like state. Estradiol (E2), a naturally occurring steroid sex hormone in humans and rats, is implicated in mood changes, which is especially prominent during the menopause transition. CORT, a stress hormone, was used to create a depressive-like state in middle-aged female (F) and male (M) rats with their gonads surgically removed. This produced the following independent treatment groups: Sex (F, M), CORT (vehicle = V ml/kg, C 40mg/kg), E2 (V 0.1 ml, E 0.3µg/0.1ml). CORT and E2 injections were injected daily, s.c) for 7 days before behavioral testing began and continued throughout the study when behavior was assessed. For my honor’s thesis, I focused on the social interaction test and elevated plus maze to investigate whether CORT enhanced social avoidance and anxiety, and whether E2 mitigated the CORT effects. In the social interaction test, three new behaviors were assessed (interacting, grooming, and immobility) to better understand exploratory and anxiety profiles of the rats, and these behaviors were quantified over two 5-minute periods in the 10-minute trial. These new quantifications showed that for the female rats, C+E and V+V enhanced the interaction with the novel rat significantly more than an inanimate object, which was not observed in the females given CORT only or E2 only. The males in all conditions showed a significant preference for side with the novel rat compared to the object, however no treatment differences were observed. In both sexes, the overall time spent interacting decreased in the second five minutes of quantification compared to the first five minutes. No effects were observed with grooming or immobility, in part from the high variability across rats. For EPM, female rats treated with CORT and E2 exhibited a lower anxiety index than compared to female rats given CORT only, indicating that E2 mitigated the depressive-like effects of CORT. Males showed no CORT or E2 effects. The result in part supported my hypothesis, as the CORT-treated females exhibited reduced socialization and E2 improved socialization in CORT-treated females, as this was seen in the F-C-E group. Interestingly, CORT failed to produce a depressive-like effect in males in both behavioral tests, which was an unexpected outcome. These results suggest that administration of E2 with CORT mitigated the depressive-like state created by CORT in female rats, however failed to produce these outcomes in males. The outcome of this work will give us insight into the potential mechanisms that may contribute to sex differences with MDD.
ContributorsSladkova, Sara (Author) / Conrad, Cheryl (Thesis director) / Amdam, Gro (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor) / School of Life Sciences (Contributor)
Created2024-05
Description
In 2022, a previous team of computer science and accounting students worked together to design and build a fully-functioning website to automate accounting transactions. They created dynamic accounting applications using software frameworks such as React and Express. They then used the services provided by Amazon Web Services to make the website available online. The stakeholders of the project wanted to expand upon the services provided by the website so they entrusted our team with implementing new features and applications to the software system. Using the same software frameworks and services of the previous team, we redesigned the website and increased its functionality to better meet the needs of accounting automation.
ContributorsJain, Sejal (Author) / Macabou, Elise (Co-author) / Lim, Jonathan (Co-author) / Villani, Jacob (Co-author) / Chen, Yinong (Thesis director) / Hunt, Neil (Committee member) / Barrett, The Honors College (Contributor) / Department of Information Systems (Contributor) / Computer Science and Engineering Program (Contributor) / School of Public Affairs (Contributor) / Dean, W.P. Carey School of Business (Contributor)
Created2024-05
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
Little is known about the state of Arctic sea ice at any given instance
in time. The harshness of the Arctic naturally limits the amount of in situ data that can be collected, resulting in gathered data being limited in both location and time. Remote sensing modalities such as satellite Synthetic Aperture Radar (SAR) imaging and laser altimetry help compensate for the lack of data, but suffer from uncertainty because of the inherent indirectness. Furthermore, precise remote sensing modalities tend to be severely limited in spatial and temporal availability, while broad methods are more accessible at the expense of precision. This thesis focuses on the intersection of these two problems and explores the possibility of corroborating remote sensing methods to create a precise, accessible source of data that can be used to
examine sea ice at local scale.
ContributorsBaker, John (Author) / Cochran, Douglas (Thesis director) / Wei, Hua (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05
Description
I study some comparative statics implications of disappointment-averse preferences
for optimal portfolios. Specifically, I find that risk-averse disappointment-averse investors
increase investment in a risky asset as a result of a monotone likelihood ratio improvement in
the asset’s distribution, a subset of First Order Stochastic improvements. This gives a testable
implication between the disappointment aversion model, and alternatives, including expected
utility. I also discuss previously noted implications for disappointment aversion in helping
explain the equity premium puzzle.
ContributorsWarrier, Raghav (Author) / Schlee, Edward (Thesis director) / Almacen, Christopher (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Economics Program in CLAS (Contributor) / Computer Science and Engineering 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
This thesis investigates the quality and usefulness of "DeepDEMs" from Moon and Mars images, which are Digital Elevation Models (DEMs) created using deep learning from single optical images. High-resolution DEMs of Moon and Mars are increasingly critical for gaining insights into the slope and the elevation of the terrain in the region which helps in identifying the landing sites of possible manned missions and rovers. However, many locations of interest to scientists who use remote sensing to study the Earth or other planetary bodies have only visible image data coverage, and not repeated stereo image coverage or other data collected specifically for DEM generation. Thus, Earth and planetary scientists, geographers, and other academics want DEMs in many locations where no data resources (repeat coverage or intensive remote sensing campaigns) have been assigned for geomorphic or topographic study. One specific use for deep learning-generated terrain models would be to assess probable sites in the lunar south polar area for NASA's future Artemis III mission which aims to return people to the lunar surface. While conventional techniques (for example, needing two stereo pictures from satellites for photogrammetry) work well, this high-resolution data only covers a small portion of the planets. Furthermore, older approaches need lengthy processing durations as well as human calibration and tweaking to achieve high-quality DEMs. To address the coverage and processing time concerns, we evaluated deep learning algorithms for creating DEMs of the Moon and Mars' surfaces. We explore how the findings of this study may be used to create elevation models for planetary mapping in the future using automated methods.
ContributorsJain, Rini (Author) / Rastogi, Anant (Co-author) / Kerner, Hannah (Thesis director) / Adler, Jacob (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / Department of Information Systems (Contributor)
Created2024-05
Description
The rapid growth of published research has increased the time and energy researchers invest in
literature review to stay updated in their field. While existing research tools assist with organizing papers, providing basic summaries, and improving search, there is a need for an assistant that copilots researchers to drive innovation. In response, we introduce buff, a research assistant framework employing large language models to summarize papers, identify research gaps and trends, and recommend future directions based on semantic analysis of the literature landscape, Wikipedia, and the broader internet. We demo buff through a user-friendly chat interface, powered by a citation network encompassing over 5600 research papers, amounting to over 133 million tokens of textual information. buff utilizes a network structure to fetch and analyze factual scientific information semantically. By streamlining the literature review and scientific knowledge discovery process, buff empowers researchers to concentrate their efforts on pushing the boundaries of their fields, driving innovation, and optimizing the scientific research landscape.
ContributorsBalamurugan, Neha (Author) / Arani, Punit (Co-author) / LiKamWa, Robert (Thesis director) / Bhattacharjee, Amrita (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / Economics Program in CLAS (Contributor)
Created2024-05
Description
The COVID-19 pandemic has notably affected the mental health of preadolescents, worsening issues such as depression due to reduced social interactions and increased online activity. "Twisted," a virtual reality (VR) game, integrates Cognitive Behavioral Therapy (CBT) principles to address these issues by helping players identify, and challenge distorted thoughts caused by cognitive distortions. This thesis explores the effectiveness of using VR to enhance the therapeutic potential of game-based interventions. The game encourages players to engage in cognitive restructuring through interactive scenarios, potentially offering a more immersive and effective alternative to traditional therapeutic methods for preadolescents. The research supports the game's ability to improve mental health outcomes by allowing repetitive practice of cognitive skills in a controlled, and engaging environment.
ContributorsYadlapati, Geethika (Author) / Johnson, Mina (Thesis director) / Dolin, Penny Ann (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and 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