41530 research outputs found
Sort by
Exploring Synthetic Data Generation for Machine Learning and Statistical Analysis
No full textIn the data-driven machine learning and statistical analysis world, real-world data availability is often constrained by privacy concerns, access restrictions, or resource limitations. To address these challenges, synthetic data provides a groundbreaking solution, enabling academics and data scientists to generate artificial datasets that mimic real-world data for model development and testing in a controlled, privacy-preserving environment. The syntheticDatasets package represents an R-based counterpart to Python\u27s widely-used Scikit-learn dataset generators, adapted to meet the needs of statisticians, educators, and data scientists primarily working in the R programming ecosystem.
This thesis explores the design and implementation of the syntheticDatasets package, focusing on key decisions about noise structure, collinearity, class distributions, and feature complexity. By analyzing these considerations, we demonstrate how the package effectively bridges the gap between R and Python\u27s Scikit-learn, offering robust tools for generating synthetic data tailored to regression, classification, clustering, and statistical modeling tasks. The package provides flexibility in parameter customization and built-in visualization capabilities, enhancing its utility for exploratory data analysis and educational purposes
A Computational Approach to Space Trajectory Optimization
No full textWith space becoming increasingly accessible, the need for sophisticated space trajectory design has surged, as we challenging existing computational capabilities. This project tackles the intricate and computationally demanding task of spacecraft trajectory optimization and real-time orbit determination by developing and benchmarking advanced numerical algorithms integrated into Cal Poly’s mission design platform, PolySpace. Leveraging cutting-edge Python routines and interfaces with NASA’s General Mission Analysis Tool (GMAT), the research addresses mission-critical scenarios, including multi-gravity-assist interplanetary missions and efficient solar-electric orbit transfers. Benchmarking the solution approach against past missions, the project ensures rigorous accuracy and reliability. This experience will help bring research into a classroom environment and empower students with practical, industry-relevant experience. The project will also advance Cal Poly’s Astronautics capabilities, complementing and expanding upon the CubeSat progra
Multi-Material Printer Development
No full textSurgeons require pre-surgical models to practice procedures and improve success rates. However, the current process of creating physical models for practice using 3D printing is limited to producing homogeneous mimics of the human body, while the human body is a heterogeneous structure composed of multiple materials with varying properties, including bones, muscles, and skin. Additive manufacturing methods cannot easily print multiple materials simultaneously, as current AM machines only print homogeneous material, unlike the human body. In this proposal, we aim to develop a multi-material additive manufacturing system, from software to hardware, to manufacture pre-surgical models. We will investigate multi-material AM methods by modifying existing filament extrusion printers
Evaluating the Accuracy of Gen AI Detecting Misinformation
No full textThis research project will investigate the ability of advanced Large Language Models (LLMs) to identify and assess misinformation across diverse forms of media, including text, images, and video. In an age where misleading content spreads rapidly across digital platforms, evaluating the reliability and integrity of AI systems tasked with fact-checking is critical. We will develop a comprehensive dataset composed of factual and misleading examples drawn from various well-known and reliable fact-checking organizations. Each item will be independently reviewed and transparently labeled to ensure reproducibility. We will then prompt a curated group of state-of-the-art LLMs—including GPT-4, Claude, Gemini, Perplexity, Grok, and Meta\u27s LLaMA—to return a misleadingness score and a self-reported confidence score for each item. These responses will be evaluated against ground-truth labels to assess each model\u27s accuracy and consistency. Ultimately, we will develop a tool that allows users to input various types of media. The tool will then collect responses from multiple LLMs and use a statistical model to determine its own score for how misleading the information is and the confidence in that statement. This tool will use LLMs to fact-check other LLMs, avoiding bias or hallucination from a single inaccurate answer/model. The project emphasizes reproducibility, open-source tooling, and ethical safeguards to ensure that all findings are verifiable and responsibly communicated
Spacecraft Reaction Wheel Simulation Testbed
No full textThere are three typical methods used to control the attitude (or orientation) of spacecraft in orbit. They are momentum exchange devices (reaction wheels and control moment gyroscopes), magnetic torquers, and thrusters (both cold and hot gas). The PolySim research group is currently developing a spacecraft attitude dynamics simulator utilizing reaction wheels. The simulator floats on a spherical air bearing and is balanced to accurately simulate the rotational motion of a spacecraft in orbit (not including the orbital motion). As a continuation of that project, we have completed the development of spacecraft attitude simulator using cold gas thrusters to control the altitude of the simulator. With the completion of the Cold Gas Thruster platform, we now have a single axis low friction test bead that can be used to develop other spacecraft attitude control technologies. The goal of this project is to design, develop, manufacture, and test a reaction wheel that can be assembled and characterized by other upper division undergraduate students. The project will require completion of several tasks. First, the mechanical and the electrical systems must be developed and designed. This includes the microcontroller and power system, including motors and batteries. Next, the student will design a feedback control including simulations in Matlab and Simulink. Next, the development of the microcontroller used to implement the control law and all code must be completed. Finally, the full system will be tested with hardware results compared to simulations developed in Matlab and Simulink
Evaluating the Effectiveness of Ultrasound-Hot Plate and FlackTek Mixing in Nanocomposite Panel Fabrication
No full textNanomaterials have found widespread applications, particularly carbon nanotubes (CNTs) in structural applications, which have gained significant traction over the past few decades [1] [2]. Numerous experimental [3] [4] [5] [6] [7] [8] [9] [10] and analytical studies [11] have demonstrated that incorporating CNTs into an epoxy matrix can significantly enhance the mechanical properties of the composite. This study evaluates and compares the effectiveness of nanocomposite panels fabricated using two different fabrication techniques: ultra-sonication combined with a hot plate process, and the FlackTek mixer. The primary objective of the research is to investigate the impact of these processing methods on the dispersion of CNTs, uniformity of the composite matrix, and overall performance characteristics of the nanocomposite panels. The ultra-sonication and hot plate method uses high-frequency sound waves to disperse CNTs into ethyl alcohol, followed by heat-induced magnetic stirring to evenly mix the CNTs with epoxy. On the other hand, the FlackTek mixer employs high-shear forces to achieve CNTs dispersion in epoxy in a more controlled manner. The samples fabricated using two different methods will be assessed and compared on important mechanical properties such as tensile strength, tensile modulus, and strain. The study aims to provide a comprehensive understanding of how each processing technique influences the mechanical properties of nanocomposite panels. The results will offer valuable insights for optimizing the fabrication of nanocomposite panels
Accelerating Relationship Discovery in Chronic Lower Back Pain through Knowledge Graph and Ontology Enhanced Large Language Models
No full textChronic lower back pain (cLBP) is a widespread public health burden linked to anxiety, depression, and opioid addiction. Interventions aimed at treating cLBP have shown minimal improvements in pain outcomes, leading researchers to reexamine our understanding of cLBP through constructing a causal model. However, constructing causal models through Randomized Controlled Trials are often unfeasible, and relying on domain expertise requires extensive and time-consuming research, posing a serious bottleneck for designing effective treatments. To accelerate this process, we apply Knowledge Graphs, Ontologies, and Large Language Models (LLMs) to aid researchers in determining possible causal relationships. First, we demonstrate how LLMs can be harnessed to improve the construction of robust Knowledge Graphs. We illustrate how to effectively utilize LLMs for Entity Resolution, highlighting how textual context can improve performance. Then, we demonstrate how combining Knowledge Graphs and LLMs as a Retrieval Augmented Generation (RAG) system can effectively augment traditional data-driven approaches, showcasing how LLMs can complement traditional machine learning methods by bridging the gap between data and domain constraints. Finally, we present a comprehensive analysis of how ontologies can be constructed for aiding RAG systems, showing how the specificity of an ontology can significantly impact RAG systems
Concrete Mix Designs with Shrinkage Reducing Admixture
No full textThe goal of this project was to explore how shrinkage-reducing admixtures (SRAs) affect the strength and overall performance of concrete. While SRAs are typically used to help reduce shrinkage and cracking, it is less common to see how they might affect compressive strength directly. To test this, three different concrete mixes were made: a control mix with no admixture, one mix with 1% SRA, and another with 3% SRA. The idea was to compare how each mix performed under the same testing conditions
Associations Between Food Insecurity and GPA Among Full-Time California State University Undergraduates During COVID-19: The Impact of Mental Health
No full textFood insecurity is a persistent public health concern among college students that has been associated with student’s academic and mental health outcomes. This thesis examined the associations between food insecurity, academic performance (measured by GPA) and mental health (using Kessler 6 psychological distress and self-perceived mental health impacts on academic performance), among full-time undergraduate students within the California State University (CSU) system. Cross-sectional analyses were conducted using data from the Spring 2021 CSU National College Health Assessment, administered across all 23 campuses. Of the 20,167 respondents, 12,899 students were included in the analytical sample. Bivariate analyses were conducted to analyze individual relationships between each of variables of interest. A multivariate analysis using ordered logistic regression was conducted to estimate the relationship between food insecurity and GPA, adjusting for demographic and socioeconomic factors, and examining the influence of mental health problems in this relationship. Food insecurity was significantly associated with lower GPA, with food insecure students reporting higher levels of psychological distress and more frequent academic impacts related to mental health. Inclusion of both mental health variables within the adjusted models weakened the effect between food insecurity and GPA indicating partial mediation, although sociodemographic, economic, and mental health variables did not fully explain the relationship. These findings demonstrate that the connection between food insecurity and academic performance is independent, multifaceted, and influenced by sociodemographic, economic, and psychological variables. Population-level crises such as the COVID-19 pandemic may intensify existing disparities in basic needs among vulnerable college students
Star Wars: Andor – An Abolitionist Study Guide
No full textThis study guide provides a set of activities for teaching abolition through Season 1 of the speculative fiction TV series Star Wars: Andor (2022). Through the practice of critical literacy (viewing, reading, and analysis), we offer various ideas on how to engage Andor as a relevant pedagogical tool for studying and teaching abolitionist movement histories and methodologies. By guiding students through a critical analysis of this widely-circulated, mainstream cultural text, we seek to activate an abolitionist pedagogical lens that can be applied across various genres and media – making tangible connections between popular culture and political struggles writ large. These activities are relevant for students and educators wherever abolition is being taught and engaged – including high schools and undergraduate classrooms, as well as non-institutional, community- based, and/or popular educational contexts. In this article we will detail a few of the most salient connections that we see between the show and the key terms and concepts of abolition – as well as possible pedagogical activities to guide students’ discussion and inquiry