Digital Commons Network^™

Smartphone Based Object Detection For Shark Spotting, Darrick W. Oliver

Master's Theses

Given concern over shark attacks in coastal regions, the recent use of unmanned aerial vehicles (UAVs), or drones, has increased to ensure the safety of beachgoers. However, much of city officials' process remains manual, with drone operation and review of footage still playing a significant role. In pursuit of a more automated solution, researchers have turned to the usage of neural networks to perform detection of sharks and other marine life. For on-device solutions, this has historically required assembling individual hardware components to form an embedded system to utilize the machine learning model. This means that the camera, neural processing …

Academic Senate - Minutes, 10/31/2023, Academic Senate

Academic Senate Minutes

No abstract provided.

Decades Of Eelgrass Meadow Dynamics Across The Northeast Pacific Support Seascape-Scale Conservation, S. H. Munsch, Ryan K. Walter, B. L. Sanderson, L. Reshitnyk, J. K. O'Leary, P. M. Kiffney, M. Hessing-Lewis, T. G. Gerwing, C. A. Endris, W. B. Chesney, K. M. Beheshti, F. L. Beaty

Physics

Eelgrass meadows provide vital nearshore habitats and ecosystem services, but they have declined from human stressors and conservation efforts are now widespread. Dynamic ecosystems like eelgrass meadows naturally rearrange as disturbance and recruitment unfold across seascapes. However, some decisions that protect eelgrass only consider extant meadows, thus ignoring the potential for change. Here, we report decades of eelgrass dynamics observed across the northeast Pacific. Our observations support conservation expanded to the seascape scale, which includes potentially inhabitable areas along with extant meadows. We found that total seascape meadow area changed over time, and changes within seascapes were often asynchronous. Some …

Signatures Of Feedback In The Spectacular Extended Emission Region Of Ngc 5972, Thomas Harvey, W. Peter Maksym, William Keel, Michael Koss, Vardha N. Bennert, S. Drew Chojnowski, Ezequiel Treister, Carolina Finlez, Chris J. Lintott, Alexei Moiseev, Brooke D. Simmons, Lia F. Sartori, Megan Urry

Physics

We present Chandra X-ray Observatory observations and Space Telescope Imaging Spectrograph spectra of NGC 5972, one of the 19 ‘Voorwerpjes’ galaxies. This galaxy contains an extended emission-line region (EELR) and an arcsecond scale nuclear bubble. NGC 5972 is a faded active galactic nucleus (AGN), with EELR luminosity suggesting a 2.1 dex decrease in L_bol in the last ∼5 ×10⁴ yr. We investigate the role of AGN feedback in exciting the EELR and bubble given the long-term variability and potential accretion state changes. We detect broad-band (0.3–8 keV) X-ray emission in the near-nuclear regions, coincident with the [O III …

Trustguard: Containment Architecture, Michael Hu, Sophie Russ, Stephen Beard

College of Engineering Summer Undergraduate Research Program

All software security relies on proper execution at the hardware level. This research extends work on containment architectures, which ensure that any ill effects of malicious or buggy hardware are contained within the system. This is accomplished by a small, security hardware component, called the Sentry, validating communication before it leaves the system. This research assesses the advantages and disadvantages of using the CHISEL hardware language, from a security and verification standpoint. Further, this research investigates more efficient Merkle trees to optimization caching within the Sentry chip to improve performance and power utilization.

Improving Semantic Document Classification Accuracy By Integrating Human-Crafted Knowledge, Zachary Weinfeld, Lubomir Stanchev

College of Engineering Summer Undergraduate Research Program

Document classification is a pivotal task in various domains, warranting the development of robust algorithms. Among these, the Bidirectional Encoder Representations from Transformers (BERT) algorithm, introduced by Google, has proven to perform well when fine-tuned for the task at hand. Leveraging transformer architecture, BERT demonstrates stellar language understanding capabilities. However, the integration of BERT with a range of techniques has shown potential for further enhancing classification accuracy. This work investigates several techniques that leverage semantic understanding to improve the performance of document classification models trained with BERT. Specifically, we explore three methods. First, we will balance corpuses afflicted by imbalanced …

Machine Learning Prediction Of Hea Properties, Nicholas J. Beaver, Nathaniel Melisso, Travis Murphy

College of Engineering Summer Undergraduate Research Program

High-entropy alloys (HEA) are a very new development in the field of metallurgical materials. They are made up of multiple principle atoms unlike traditional alloys, which contributes to their high configurational entropy. The microstructure and properties of HEAs are are not well predicted with the models developed for more common engineering alloys, and there is not enough data available on HEAs to fully represent the complex behavior of these alloys. To that end, we explore how the use of machine learning models can be used to model the complex, high dimensional behavior in the HEA composition space. Based on our …

Exploring Approaches To Engage K-12 Students In Learning Computational Thinking Using Collaborative Robots, Zoila Anuri Kanu

College of Engineering Summer Undergraduate Research Program

Minority students are largely underrepresented in the STEM field. The goal for this project was to develop a program which promotes the inclusion of computation skills among students and help them work collaboratively with the use of human – robot interaction. Robots are such a strong tool that can be used to enhance computational thinking and engage students towards a technical field. Through workshops and readings about computational thinking we worked on building a block-based program that introduces the uses of robots as teaching tool for computational thinking.

Ethics And Social Justice For Ai In Data Science, Arya Ramchander, Kylene Nicole Landenberger

College of Engineering Summer Undergraduate Research Program

The advances of AI raise several critical questions about human values and ethics, highlighting the need for researchers and developers to consider the ethical implications and the risks of neglecting them. In the past few years, student researchers have developed an AI model that allows users to test their surveys for possible breaches of subject confidentiality. This allows the users to gauge the ethicality of their proposal. This summer, we have expanded on this research and launched an interactive model for students and researches to assess their current work for ethical and social justice implications. Using Langchain and Figma, we …

Dei: Exploring Academic Reflections Using Natural Language Processing To Create A Roadmap Of Student Success And Foster Inclusive Engineering Education, Rajvir H. Vyas, Nidhi Raviprasad

College of Engineering Summer Undergraduate Research Program

Every year, the College of Engineering (CENG) students and faculty reach out to admitted students through “Text-a-Thon” programs to answer their questions about being a student at Cal Poly. In order to improve CENG outreach efforts, we analyzed these text conversations to predict the likelihood of an admitted student accepting an offer of admission from Cal Poly. Through our research, we discovered key factors that play a role in a student committing to Cal Poly through data-based insights. Additionally, we successfully used a human-on-the-loop system to help create Machine Learning (ML) models that predict satisfaction of response by way of …

Ai For Search And Rescue - Locating A Missing Person, David Hernandez, Sai Rama Balakrishnan, Timmy Chin, Aditya Manikonda, Vasanth Pugalenthi

College of Engineering Summer Undergraduate Research Program

Building on the work done initially as a SURP 2021 project and continued through 2021-23, the focus for this summer project will be on the use of computer technology for locating a missing person. Over the last year, we developed the digital equivalents of about 30 paper-based S&R forms and the infrastructure to collect the respective information. In their current use, these paper forms are filled out by search teams, collected in a command post, and reviewed by search coordinators. This process is time-consuming, prone to errors and loss of information, and relies heavily on the experience, skills, and mental …

Development Of User Interface And Testing Harness, Jacob Amezquita, William Albertini

College of Engineering Summer Undergraduate Research Program

No abstract provided.

Integrating Human Expert Knowledge With Openai And Chatgpt: A Secure And Privacy-Enabled Knowledge Acquisition Approach, Ben Phillips

College of Engineering Summer Undergraduate Research Program

Advanced Large Language Models (LLMs) struggle to produce accurate results and preserve user privacy for use cases involving domain-specific knowledge. A privacy-preserving approach for leveraging LLM capabilities on domain-specific knowledge could greatly expand the use cases of LLMs in a variety of disciplines and industries. This project explores a method for acquiring domain-specific knowledge for use with GPT3 while protecting sensitive user information with ML-based text-sanitization.

Research Project Poster Presentation: Cultural Normalization Of Risk?: Exploring Brain Injury In The National Football League Using Sociocultural Analysis, Ali V. Willing, Jafra D. Thomas

Kinesiology and Public Health

Background. This presentation began as an undergraduate end-of-term course project focused on sport, media, and American popular culture (April to June 2023). The poster presentation was originally presented at the 2023 annual conference of the Southwest Chapter of the American College of Sports Medicine (SWACSM), following peer-review acceptance of the project summary statement (i.e. abstract) for conference presentation.

Purpose. The presentation is published here to Cal Poly Digital Commons as a resource to future students and professionals studying topics covered in the presentation (e.g. sociological theories, cultural values and risks, sports ethic).

Resources. This webpage has several resources described below. …

Executive Committee - Agenda 9/26/2023, Academic Senate

Academic Senate Agendas

No abstract provided.

Gender Discrimination In The Classroom: How Teaching Policies Can Help Close The Gap, Olivia Wycoff

sprinkle: an undergraduate journal of feminist and queer studies

No abstract provided.

Greenhouse Gas Emissions And Fire Behavior Impacts Following California Fuel Treatments, Lindsay M. Senechal

Master of Science in Environmental Sciences and Management Projects

Fuel treatments are being increasingly applied across California landscapes as communities struggle to recover from wildfire disasters nationwide. Increased funding for treatments stems from grants under CARB’s Greenhouse Gas Reduction Fund and funding requires reports accounting the yielded benefits from these fuel treatments. Using data from real-world local scale fuel treatments, I used the forest simulation model FVSFEE and fire behavior software IFTDSS to quantify GHG emission benefits and fire behavior impacts 70 years after treatment. Results suggest that fuel treatments do not yield significant GHG benefits, and fire behavior impacts (conditional flame length) are minimal but overall show slight …

Establishing A Monitoring Framework To Evaluate Impacts Of Grazing Exclusion And Inform Restoration At Santa Rita Ranch, Annie Booth, Annie Booth

Master of Science in Environmental Sciences and Management Projects

Santa Rita Ranch is a 1,750-acre cattle ranch in Templeton, California, that was privately owned and continuously grazed for the past 70 years. In 2021, The Land Conservancy of San Luis Obispo (LCSLO) acquired the property, and in the winter of 2022, they built a fence that bisects the ranch, excluding the cattle from 800 acres to preserve the riparian habitat. The LCSLO is currently defining the ecological baseline for the ranch to inform future management decisions. Given that cattle grazing has many environmental tradeoffs, they wanted to establish a long-term monitoring study to understand how relieving the pressures of …

Pumping-Induced Drawdown Of Streams In Proximity To Agricultural Wells, Sara Alina Sternberg

Master of Science in Environmental Sciences and Management Projects

In the context of unprecedented drought and aquifer overdraft in California, understanding surface water and groundwater connectivity have become increasingly important. While there is a clear understanding of how wells induce drawdown in aquifers (Theis, 1935; Hantush, 1965), secondary effects on local streams have not fully been considered. Current mathematical models targeting aquifer drawdown do not address stream drawdown response in aquifer-stream systems with strong connectivity; instead, they assume the stream to be a constant head boundary. In the drought-stricken and summer-dry climate of California, streams often run dry for months out of the year, which is currently not reflected …

The Methods Of Communication And Education Used To Train Forest And Fire Personnel Through The Swanton Pacific Ranch, Christine Brittney Johnson

Master of Science in Environmental Sciences and Management Projects

California does not have a cohesive curriculum for educating and training forest and fire professionals. The Swanton Pacific Ranch Fuels Management Training Program is Cal Fire affiliated and provides online and in person training to assist in equipping fire and forest professionals throughout California with the necessary skills to be successful fire and forest practitioners and managers. An exit survey was offered to all workshop participants after the Swanton workshop concluded. The survey was answered by 331 Swanton workshop participants to assess the effectiveness of the training program, the educational practices used to teach participants, and what factors of a …

Environmental Controls On Soil Organic Matter Fractions In Post-Fire Landscapes, Alexis Heuer

Master of Science in Environmental Sciences and Management Projects

In the past few decades, the world’s climate is being altered by anthropogenic forces such as the increase in carbon dioxide (CO2) emissions due to fossil fuel combustion (Paraschiv and Paraschiv, 2020). In California, the impacts of increased CO2 concentrations have created longer fire seasons, warmer temperatures, and increased lightning strikes which allow for wildfires to become more frequent, severe, and larger in scale (Westerling et al., 2006). Wildfires of this magnitude result in acceleration of landscape scale processes such as erosion and aggregation which in turn affects soil organic matter (SOM), the basis of soil health (Gonz´alez-P´erez et al., …

Fire Effects On Soil Organic Matter In The Creek Fire, Gracie E. Doolin

Master of Science in Environmental Sciences and Management Projects

Wildfires have increased in frequency and severity over the past few decades due to the increased concertation of CO2 emissions from anthropogenic influence. Soil carbon (C) sequestration has been identified as a climate change mitigation strategy; however, the influx of large-scale wildfires has accelerated landscape processes such as erosion, reducing soil aggradation, and soil C and nitrogen (N) protection. This trend is highlighted by the Creek Fire that occurred in September 2020 and burned 379,895 acres in the Sierra National Forest. This research is designed to close the knowledge gap regarding the impact of burn severity on soil organic matter …

Identifying The Stream Depletion Paradox By Monitoring A Stream’S Response To Aquifer Pumping From Neighboring Wells, James Klueber

Master of Science in Environmental Sciences and Management Projects

Current groundwater models utilize a constant head (Dirichlet) boundary condition which assumes stream stage is fixed and does not experience any drawdown in the event of pumping from an interconnected aquifer despite the presence of stream depletion. Therefore, constant head boundary implies that streams and lakes in a groundwater model behave as an infinite supply of water when aquifer pumping occurs. This study aimed to determine if a stream located in the California Central Coast experiences drawdown and depletion when pumping occurs within an aquifer-stream system. This was achieved by measuring stream stage, aquifer water levels, stream discharge, and the …

Assessing Environmental Impact Of The Built Environment By Adopting Life Cycle Design: Using Swanton Pacific Ranch As A Case Study, Hope E. Springer

Master of Science in Environmental Sciences and Management Projects

To combat the carbon emissions contributed to the atmosphere by the built environment, it is imperative that low-embodied-carbon materials choices be prioritized throughout the building design process. To achieve this, this professional project creates an Excel-based, open source, and user-friendly tool for the construction sector to make design decisions that prioritize the sustainability of structures, as one such tool does not currently exist. The use of OpenLCA software and the EcoInvent34 database are utilized to calculate the environmental impact of 25 different building materials, as well as energy and electricity consumption. Swanton Pacific Ranch (SPR) in Santa Cruz County is …

Factors Affecting California Grassland Biodiversity: Two Case Studies, Nora Bales

Master's Theses

Biodiversity loss over the last century has been significant and is projected to increase. Biodiversity loss is accelerating due to climate change and habitat loss and degradation. Biodiversity supports key ecosystem services including pollination services, climate regulation, and water filtration. Biodiversity conservation is a top priority for land managers and researchers, however many ecological studies with practical applications lack a thorough understanding of the soil environment in their study system. We conducted two case studies integrating soil and plant data to answer management questions. The first case study investigated the relationship between a threatened plant, Hooveria purpurea var. purpurea and …

Functional Nanocomposite Coatings For Use In Food Packaging, Camden N. Webb

Master's Theses

Plastics are a class of materials known for their cost and property advantages, increasing significantly in their usage worldwide. Unfortunately, these benefits come with an increasingly concerning environmental impact. A combination of inadequate disposal options and combinations of materials have led to environmental disasters that will impact generations. One of the worst areas for plastic waste is food packaging. Plastic as a material generally excels at durability and longevity, but as food packaging, it outlives its intended purpose by several orders of magnitude. This leads to plastic food packaging materials sitting in landfill or leading to the environment for hundreds …

Co-Simulation Of Active Magnetic Bearing Rotors Using Adams, Msc Apex, And Simulink, Shea A. Charkowsky

Master's Theses

Apex-Adams-Simulink co-simulation is applied to active magnetic bearing (AMB) rotors, demonstrating results unshown in literature, including continuous frequency response, and unavailable in known rotor dynamics software, including touchdown bearing impact. AMBs levitate rotors without contact, so they involve no friction, wear, lubrication, pollution, or shaft speed limits and are thus valuable for large, high-speed applications. Modeling of such rotors, necessary for safety and performance, simultaneously requires flexible body dynamics and advanced control design, but simulation programs tend to specialize in only one or the other. The co-simulation method combines multiple such programs—MSC Apex (finite element modeling), Adams (multibody dynamics), and …

Mate Choice And Sexual Conflict In A Livebearing Fish, Julia C. Kasper

Master's Theses

Eavesdropping occurs when a receiver extracts information from an interaction without directly engaging with the signaler. Eavesdropping has been shown to be an effective way of evaluating the quality of potential mates and their abilities in male-male competition, without having to directly interact with them, thereby reducing energy costs and mating harassment. Girardinus metallicus is a livebearing poeciliid fish endemic to Cuba whose mating system is dominated by mating harassment in the form of sneak copulations, persistent displaying, and male-male aggression. G. metallicus has a male specific polymorphism in both melanin coloration and behavior. Males with melanin coloration are known …

Phase Distribution Of Nickel, Chromium, And Cobalt In Seawater At Olivine-Enriched Beaches: Implications For Carbon Capture By Enhanced Silicate Weathering, Nathaniel J. Padrnos

Master's Theses

The application of olivine to coastal areas is a proposed method of removing carbon dioxide from the atmosphere for climate change mitigation. Olivine is abundant and dissolves relatively fast, but it contains trace amounts of nickel (Ni), chromium (Cr), and cobalt (Co) which may be toxic to marine biota in cases of widespread coastal olivine spreading. Prior studies have suggested that Ni concentrations in marine sediments and/or the overlying water column due to olivine dissolution could be a limiting factor for its carbon capture potential. Therefore, it is critical to understand and model the processes affecting trace metal bioavailability after …

Subject-Specific Human Knee Fea Models For Transtibial Amputees Vs Control Tibial Cartilage Pressure In Gait, Cycling And Elliptical Training, Ali Yazdkhasti

Master's Theses

Millions of individuals around the globe are impacted by osteoarthritis, which is the prevailing type of arthritis. This condition arises as a result of gradual deterioration of the protective cartilage that safeguards the ends of the bones. This is especially true of transtibial amputees, who have a significantly higher incidence of osteoarthritis of the knee in their intact limb than non-amputees. Engaging in regular physical activity, managing weight effectively, and undergoing specific treatments can potentially slow down the advancement of the disease and enhance pain relief and joint function. Nevertheless, the relationship between the type of exercise and its impact …