41530 research outputs found
Sort by
Mechanical Properties of Polymer Matrix Nanocomposites Reinforced with Varying Carbon Nanotube Geometries
No full textThis study serves as part of an introduction to nanocomposite research at California Polytechnic State University, San Luis Obispo, and attempts to form an observational comparison between the performance of various CNT-Epoxy nanocomposites under drop weight testing. As a continuation of research on CNT-Epoxy nanocomposites, this study specifies three geometries of Multi-walled carbon nanotubes: straight (MWSCNTs), helical (MWHCNTs), and OH-functionalized straight (FMWSCNTs); and it compares their impact resistances to neat epoxy samples. Based on the total number of failed samples under a normalized impact energy of 0.335J/mm, it is observed that FMWSCNTs increase the impact resistance of Epoxy panels at the greatest rate. Additionally, according to the number of observed cracks in the failed samples, MWSCNTs and MWSCNTs demonstrated a similar smaller improvement in impact resistance when compared to the Neat samples
AI Integration for IntelliSAR
Get PDFIntelliSAR aims to integrate AI techniques into Search and Rescue (SAR) operations, building on the foundation laid by previous SURP initiatives. IntelliSAR’s core elements include a front-end for SAR forms, a comprehensive command center dashboard, and AI-driven components designed to enhance SAR decision-making. During summer, our efforts focused on streamlining the user interface by integrating various machine learning models into a unified, interactive dashboard. Our models predict critical factors such as missing persons’ behavior, potential locations, and resource requirements, with the goal of optimizing response times and improving the effectiveness of SAR teams
Integration of Augmented Reality on Engineering Education
No full textThis project focuses on enhancing the educational experience in structural dynamics by integrating augmented reality (AR) into the ME 318 Mechanical Vibrations lab. The experiment, centered around a cantilever beam, involves conducting both theoretical and experimental modal analysis to study mode shapes and natural frequencies. By using AR headsets, students can visualize animated mode shapes superimposed on the physical beam, allowing for a more intuitive understanding of structural behavior. The integration of AR not only improves the accuracy of identifying key dynamic properties but also modernizes the lab experience, replacing outdated equipment with a streamlined, MATLAB-based process
Drive to Succeed: Empowering Underserved Communities through Autonomous Driving Education
Get PDFAutonomous vehicle (AV) technology represents the leading edge of innovation in transportation and holds immense potential to transform industries across the globe, with California at the forefront. However, access to education and technical training in this field has often been out of reach for students in underserved communities. The “Drive to Succeed” project endeavors to bridge this gap by introducing autonomous driving technology to high school students in communities where access has traditionally been limited. We propose an outreach program specifically designed to address the underrepresentation of marginalized groups in technology sectors and cultivate the next generation of engineers from diverse backgrounds.
Focusing on San Luis Obispo County, California, where nearly half of K-12 students identify as Hispanic or Latino, this pilot program will offer a dynamic curriculum to stimulate interest in STEM fields. Hands-on education kits and structured, engaging lessons will cover the fundamentals of autonomous driving principles – both theoretical and practical. Students will learn technical concepts such as embedded systems, firmware programming, sensor interfaces, motion planning, control, and perception, all tailored to autonomous driving. “Drive to Succeed” aims to equip students with the knowledge and skills necessary to make meaningful contributions to the field while opening doors to exciting and rewarding career paths in engineering and technology.
The “Drive to Succeed” program aligns with the College of Engineering’s commitment to broaden participation and foster a more diverse workforce. This project resonates with the National Science Foundation’s (NSF) call under the BPE program for revolutionary approaches to engineering education that emphasize inclusivity and equity as cornerstones of excellence. Our ultimate goal is to create a model program with the potential to inspire and replicate similar initiatives nationwide, helping to ensure that the technological advancements of the future reflect and benefit the full spectrum of our society
Optimizing Resume Authenticity and ATS Compatibility with LLM Feedback Integration
Get PDFResume generation using Large Language Models (LLMs) like ChatGPT is becoming increasingly popular for automating the creation of customized resumes, but significant user modification is often required before submission. Common issues include poor alignment with job descriptions, inflated qualifications, and lack of authenticity, which undermine the effectiveness of LLM-generated resumes. This project addresses these challenges by integrating feedback from Applicant Tracking Systems (ATS) to guide LLMs in producing resumes that accurately reflect an applicant’s qualifications and better align with job-specific requirements. By optimizing the model\u27s output through ATS feedback, the project aims to create more authentic, tailored, and ATS-compatible resumes, reducing the need for manual edits and improving candidates\u27 chances of passing automated filters and securing interviews
Targeting Federated Learning: A Study of Membership Inference Attacks on Healthcare Data
Get PDFThis study investigates the vulnerabilities of federated learning models in the healthcare domain, specifically focusing on membership inference attacks (MIA). Federated learning allows local models to train on sensitive healthcare data without sharing the data itself, making it an attractive method for protecting privacy. However, even in this decentralized framework, models remain vulnerable to MIAs, where attackers can infer whether certain data points were used to train a model by analyzing model updates. Using the Texas100 dataset, this study demonstrates that as the number of local models increases, the attack accuracy of MIAs also increases due to higher bias variations and model specialization. The proposed MIA model operates in a white-box setting, comparing global model updates with local model biases to identify the origin of sensitive data contributions from local participants. The findings underscore the need for stronger privacy protections in federated learning, particularly when applied to sensitive healthcare data
Incorporation of GNSS Technology for Water-Level Instruments
Get PDFOur goal was to take an existing water-level measuring embedded system and upgrade the GNSS module for the purpose of getting the elevation of the device within an error of 1 cm. Main milestones for the project included deploying a successful field test at a known survey point, using software-based post processing to improve the GNSS solution point, and implementing robust hardware and software for the water-level embedded system such that it was easily scalable
