Engineering Commons^™

Enhancing Ad/Adrd Management Through Ihelpcare: A Compliant And Culturally Sensitive Ai-Driven Digital Healthcare Platform, Trisha Bhowmick

Master's Theses

The digital healthcare field is expanding fast, and now it requires platforms that use advanced technology and maintain robust data security and compliance practices. In the present paper, we present the main structure, key methods, and compliance strategies of the digital healthcare system iHelpCare, which, while fully meeting the HIPAA/GDPR requirements, provides health services more accessible, efficient, and inclusive. The proposed platform is powered by AI for personalized care solutions, with the main emphasis on preventive health management and providing tools for people with disabilities.

iHelpCare achieves real-time patient monitoring while securing medical data management and easy communication between patients, …

Llm-Powered Question Answering For Object States In Virtual Reality, Shiyi Ding

Master's Theses

Recent advances in large language models (LLMs) and multimodal large language models (MLLMs) enable natural language–based querying in virtual reality (VR). However, VR environments are highly localized, personalized, and dynamic, making it challenging for general-purpose models to answer environment-specific queries or reason about subtle object state changes. To address these challenges, this thesis develops two systems for 3D question answering in VR.

First, we present RAG-VR, the first retrieval-augmented 3D question-answering system designed for VR. RAG-VR augments an LLM with external knowledge retrieved from a localized knowledge database and includes a pipeline for extracting environmental and user-related information. To improve …

Per- And Poly-Fluoroalkyl Substances Fate Across California Wastewater Treatment Plants: A Meta-Analysis Of Formation, Distribution, And Persistence, Elizabeth Reineke

Master's Theses

Per- and poly-fluoroalkyl substances (PFAS) are persistent contaminants that move through municipal and industrial wastewater systems with limited attenuation. As a result, they are increasingly detected in drinking water supplies. Despite growing regulatory concern, a systems-level understanding of PFAS behavior across multiple treatment facilities and watershed settings remains incomplete. This study compiled influent, effluent, and biosolids datasets from more than one hundred California wastewater treatment plants to evaluate PFAS occurrence, transformation, and partitioning across diverse treatment configurations. Analytical steps included calculating removal efficiencies, assessing precursor-to-product oxidation, evaluating co-contaminant correlations, and grouping facilities by process design to quantify configuration-specific fate patterns. …

Origami-Inspired Pneumatic Soft Robotic Gripper, Conor J. Schott

Master's Theses

This thesis presents the design and evaluation of a vacuum-actuated, origami-based soft robotic gripper. A custom Sea Urchin crease pattern forms a lightweight folding skeleton that collapses radially under vacuum. The system emphasizes low cost and accessibility through laser cutting, 3D printing, and silicone molding. The Sea Urchin geometry was selected after digital and physical screening of candidate crease patterns for smooth folding, low strain concentration, and uniform inward motion. The folding skeleton is laser cut from 4 mil drafting film and folded into a compliant core. Four membrane configurations were developed: an origami gripper with a 36-inch balloon (Design …

Short-Arc Angles-Only Initial Orbit Determination For Leo And Geo Objects Using A Genetic Algorithm, Joseph R. Piini

Master's Theses

An ever-growing interest in utilizing space for scientific, commercial, and defense applications has led to an exponential rise in orbital debris recent years. With this sharp increase in space objects comes a greatly increased risk of potential collisions, necessitating an increase in Space Situational Awareness. In order to best mitigate the risk of future collisions in an increasingly congested space environment, it is crucial to be able to accurately determine the orbits of these new objects for trajectory tracking. This process is initial orbit determination (IOD), and is especially difficult when only observation angles are available for short observation times. …

Real Time Markerless 3d Hand Tracking For Intuitive Robotic Arm Control, Dylan G. Featherson

Master's Theses

This thesis presents a real-time, markerless motion-capture system for intuitive control of a multi-degree-of-freedom robotic arm. Using two synchronized RGB cameras and stereo-vision triangulation, the system reconstructs the three-dimensional position of a user’s hand without the need for physical markers or wearable sensors. The reconstructed 3D coordinates are mapped directly to the end-effector position of the Quanser QArm, a four-degree-of-freedom educational manipulator. Developed entirely in Python, the system integrates stereo camera calibration, 3D hand tracking with MediaPipe, coordinate transformation, and inverse kinematics into a unified real-time control pipeline operating at approximately 200 Hz. Calibration is performed through a checkerboard-based stereo …

Analyzing Patterns In Hofstede’S Cultural Dimensions Towards Individual Ai Receptiveness For Affective Experiences, Maggie Yang

Master's Theses

The use of artificial intelligence (AI) has significantly advanced efficient decision-making, with trust in algorithmic decisions shown to vary by cultural upbringing [1]. As AI becomes increasingly embedded in everyday life, it is essential to examine how cultural values affect trust in AI in subjective contexts that extend beyond purely quantitative analysis, like the personal interpretation of art. This work utilizes Hofstede’s cultural dimensions to investigate potential patterns in receptiveness towards AI predictions during art interpretation, providing insight into individual susceptibility to bias in AI-assisted affective analysis.

The study leveraged a cultural dimension survey and a custom Java program connected …

Retrieval Augmented Framework For Deepfake Audio Detection, Avinash Saxena

Master's Theses

The widespread use of AI-based audio deepfakes threatens severely to undermine media integrity and public trust. Speech synthesis techniques have improved dramatically in voice conversion (VC) and text-to-speech (TTS) in recent years, making forgeries sound highly realistic, and concerns are raised about possible malevolent uses. Existing state-of-the-art techniques for identifying fake speech have proven to be effective in some cases but are still limited in application and robustness when faced with novel attacking strategies, different acoustic conditions, or alternative linguistic domains. To address some of these limitations, the current research presents a novel deepfake audio detection system based on personalized …

Towards A Generalized And Optimized Apriori Approach, Artem Abdikov

Master's Theses

Apriori is a machine learning algorithm developed in 1994 by R. Agrawal and R. Srikant for association rule mining purposes. This family of algorithms takes transactional data and analyzes relationships between variables in large datasets. The typical output of such algorithms is a prediction that if users choose item X, it is highly likely that they will also choose item Y. Apriori is known to be a robust algorithm and is used by many large companies in order to analyze user tendencies and even make recommendations. Although Apriori is a powerful algorithm, its original implementation is known to have limitations, …

Development Of New Design Criteria For Coastal Highway Embankment Under Wave-Induced Loading, Udaya Bilas Panta

Master's Theses

In the face of intensifying hurricanes and rising sea levels, Louisiana’s coastal highways, lifelines for communities and commerce, stand increasingly vulnerable. This thesis introduces a pioneering methodology for designing geosynthetic-reinforced highway embankments capable of withstanding wave-induced loading and rapid drawdown scenarios, the most critical failure condition identified in coastal environments. By integrating statistical wave modeling, advanced numerical simulations using SEEP/W and SLOPE/W, and a comprehensive parametric analysis, the study develops a novel hybrid regression formula that accurately predicts optimal reinforcement lengths based on site-specific geotechnical and hydraulic parameters. Validated against Hurricane Katrina data and real-world soil profiles from Cameron Parish, …

Exploring The Effectiveness Of Virtual Reality Learning Through Use Of Visual Eye-Tracking Analytics (Veta) And Biological Measurements, Mckinley Anne Sherman

Master's Theses

Virtual Reality (VR) offers an immersive and interactive platform for experiential learning. The purpose of this thesis was to evaluate the relationship between physiological responses and cognitive workload within a VR learning environment and to explore VR as an effective instructional tool. This research compared participant engagement, stress, and learning performance within a 6th-grade science module developed in VR by incorporating biometric data collected via Polar H10 heart rate monitor and Varjo Areo VR headset eye-tracking. Thirty-three participants completed a pre-lesson demographic survey, post-lesson survey, VR sickness questionnaire, and the NASA Task Load Index (NASA-TLX). While completing the lesson, the …

A Convolutional Neural Network Approach To Breast Cancer Tumor Boundary Detection, James Leah Matlosz

Master's Theses

Breast cancer is the second most common form of cancer and often goes undetected in its initial stages due to its subtle symptoms. As the tumors grow, they become more difficult to surgically remove with clean borders. To minimize the chance of recurrence, a 2D convolutional neural network is developed in this work for delineating tumor boundaries. Specifically, the U-shaped network model is trained, validated, and tested with longitudinal MRI scans of patients diagnosed with breast cancer and undergoing neoadjuvant therapy. For training, image masks were generated as ground truths using signal enhancement ratio segmentation, thresholding, and contour detection. The …

Towards Automated And Explainable Insider Threat Response In Electronic Health Records: A Role-Aware Machine Learning Framework, Luca Lippi Ornstil

Master's Theses

Healthcare remains a prime target for cyberattacks, with insider misuse and credential compromise posing major risks to Electronic Health Records (EHRs). This thesis introduces a role-aware, explainable anomaly detection and response framework integrated with OpenEMR to address post-authentication threats. Four models—Local Outlier Factor (LOF), Isolation Forest, Autoencoder, and Graph Neural Network (GNN)—detect behavioral deviations across temporal, device, and role-based features, with LOF serving as the primary runtime detector. A configurable policy engine maps anomaly severity to proportional actions, from email alerts to read-only restrictions or account suspension, all reversible and auditable. Evaluation on real EHR logs shows the system’s operational …

Development Of A Colorectal Cancer Spheroid Model To Improve The Accuracy Of Preclinical Drug Testing, Jillian Trilevsky

Master's Theses

Colorectal cancer is the second leading cause of cancer related deaths worldwide. It currently affects millions of people across the globe and is only expected to increase in impact over the coming years. The most common treatment for metastatic colon cancer is chemotherapy, however, the development of chemotherapeutic drugs is a long and expensive process. A large portion of this development process is spent in preclinical drug testing. However, the models used often lack enough physiological relevance to guarantee the drug’s success in a clinical trial. Due to this gap in testing, researchers seek to develop a more physiologically relevant …

Using Hydraulic Simulations To Determine The Effects Of Tidal Behavior And Riparian Restoration On Chorro Creek, Jonathan L. Maas

Master's Theses

This thesis examines how tidal backwater effects and riparian restoration influence flooding in the Chorro Creek watershed, a major tributary to the Morro Bay Estuary on California’s Central Coast. Restoration efforts, including levee removal, floodplain reconnection, and revegetation have attempted to improve ecological function and reduce sediment transport. However, recent flood events suggest that these changes may also affect local hydraulics in ways not fully anticipated, particularly under the influence of tides and sea level rise. To analyze these dynamics, a two-dimensional HEC-RAS model was developed using LiDAR terrain, historical imagery, and field data collected from pressure and ultrasonic gauges. …

Experimental Study Of Gas-Dynamic Heating In Hartmann-Sprenger Tubes For Rocket Engine Ignition, Jacob T. Huff

Master's Theses

Ignition systems for chemical rocket engines typically rely on hypergolic propellants or auxiliary electrical hardware to supply the energy required to initiate combustion. The resonance igniter is a simple and robust alternative to these conventional methods, capable of inducing autoignition of non-hypergolic propellants without an external ignition source. At the core of this concept is the Hartmann-Sprenger Tube (HST), a device in which a high-velocity jet of gas impinges on a resonance cavity. This interaction establishes self-sustaining gas oscillations within the cavity that heat the propellants to their autoignition temperature. To facilitate the development of a functional resonance igniter at …

Enhancing Non-Player Character Dialogue In Video Gages: An Evaluation Of Large Language Model-Generated Responses, Lam P. Quach

Master's Theses

As video games increasingly emphasize narrative depth and player immersion, the quality of Non-Player Character (NPC) dialogue has become crucial for creating engaging gaming experiences. This thesis investigates the potential of Large Language Models (LLMs) to generate high-quality NPC dialogue by comprehensively evaluating four state-of-the-art models: Gemma 3 27B, Mistral 7B, QWEN 2.5, and LLAMA 3.1. The study employs a mixed-methods approach, combining human evaluation (N=50 participants) with AI-based assessment across five key benchmarks: coherence, personality expression, engagement, style/tone appropriateness, and overall quality. Participants evaluated 32 dialogue samples (8 per model) generated for a fantasy game context featuring two distinct …

Sparse-Data Orbit Estimation In Low Earth Orbit Using The Markov Chain Monte Carlo Ensemble Gaussian Mixture Filter, Nicholas J. Oden

Master's Theses

The number of space objects (SOs) in low Earth orbit (LEO) continues to increase rapidly, creating challenges for the current ground-based tracking network, which cannot accommodate the projected growth in SOs. Catalog maintenance relies on frequent observations for reliable reacquisition, with Two-Line Element (TLE) sets typically generated daily to mitigate rapid error growth from poor TLE accuracy. This constraint limits the ability to track more objects with existing infrastructure. This work evaluates the Markov Chain Monte Carlo Ensemble Gaussian Mixture Filter (MCMC EnGMF), a nonlinear, non-Gaussian filter well-suited for sparse tracking scenarios where higher post-update accuracy is needed to reduce …

Evaluation Of The Performance Of The Traveling Wave Differential Element In Protective Relays, Niranjan Kc

Master's Theses

This thesis evaluates the dependability, security, and limitations of the traveling wave differential protection function (TW87) in modern time-domain-based protective relays, using a combination of simulations and hardware testing in a laboratory environment. Fault transients are first generated using the electromagnetic transients program model of a real, 230 kV, 65.7 km long overhead transmission line, which are then played back on real time-domain-based protective relays. Various fault scenarios are chosen to evaluate the impacts of factors such as fault inception angle, distance to fault from line terminals, fault type, fault impedance, and external faults on the relay functions’ performance. Results …

The Design Of Coplanar Waveguide Traveling-Wave Kinetic-Impedance Parametric Amplifiers, Jordan Scott Savoie

Master's Theses

Astronomical observations and many physics experiments rely on cryogenic amplifiers for readout. Current sensitivity is limited by the noise figure of high-electronmobility transistor (HEMT) amplifiers, which have proven di!cult to decrease further in recent years. Traveling-wave kinetic-impedance parametric amplifiers (TKIPAs) are an emerging class of amplifiers which have the potential to substantially improve the sensitivity of microwave low-noise amplifiers (LNAs) while also accepting relatively high input powers and amplifying over a wide bandwidth. In this thesis, I present the design, modeling, and testing procedures for coplanar waveguide (CPW) TKIPAs developed by our group at the National Radio Astronomy Observatory. Using …

Learning Structure With Multivariate Information Bottleneck And Exploration Of New Methods In Sequential Decision Making, Volodymyr Makarenko

Master's Theses

Research in useful information extraction has been motivated by the increasing demand to extract insights from unstructured data, and by the need to store and transmit great volumes of information, often originating in unstructured data such as videos. Research in rate distortion and information bottleneck paved the path for understanding and guiding the design of lossy encoders, capable of extracting relevant information. Independently, research in deep representation learning has enabled numerous applications for unstructured high-dimensional data such as images. However, the interpretability of the deep learning methods remained limited. Several desired properties of learned representations have been suggested, including disentanglement. …

Understanding And Evaluating Genomic Language Models, Aadit Kapoor

Master's Theses

Large Language Models (LLMs) have shown remarkable capabilities in interpreting complex patterns across various domains, yet their application to genomic data remains limited. We see great potential in leveraging LLMs for vital biological tasks, such as predicting transcription factor binding sites and identifying antibiotic-resistant genes. This emergent behavior positions LLMs as powerful tools for enhancing our understanding of intricate biological language. LLMs trained specifically on genomic data, such as DNA sequences, operate distinctly compared to those trained on natural language. This difference is evident not only in the architectural landscape of the models but also in the methodologies employed by …

Measurements Of Spinal Posture During Common Strawberry Picking Positions Using Inertial Measurement Units, Madeline E. Everson

Master's Theses

Physically demanding professions, such as agriculture, put people at an increased

risk for experiencing back pain. This is due to the awkward and harmful postures sustained

throughout their workday. While studies have been done demonstrating that back pain is

prevalent amongst this community, most do not collect motion capture (MoCap) data,

leaving the specifics of the kinematics, such as the amount of time spent in harmful

postures, unknown. Unfortunately, MoCap data is typically limited to that of a lab or

facility where the cameras are housed. Therefore, this study aimed to mitigate the

inaccessibility of traditional MoCap by validating that …

Integration And Testing Of A Quadruped Robot With Ros2, Jeremy S. West

Master's Theses

The Cal Poly Legged Robotics Group has been developing research and teaching platforms for agile legged robotics since 2020. These platforms are expected to provide students with opportunities to develop complete legged-robot systems from low-level control to advanced robotics tasks such as motion planning and decision making. However, the current prototyped quadruped robot lacked the software and sensing capabilities for high-level quadrupedal gaits and advanced robotic research.

To address these challenges, this project developed Switch, a robotic platform that builds upon the previous BRUCE platform with significant hardware and software upgrades. Switch features a modular design that allows individual software …

Development Of A Control System For An 8-Dof Quadrupedal Robotic Research Platform, Jack Butler

Master's Theses

Quadrupedal robots offer a versatile locomotion option that can extend the operating space of a robot into uneven terrains. However, controlling these systems presents significant challenges due to nonlinearities introduced by various factors.

In this thesis, model-predictive control (MPC) is applied to an 8-DOF legged robot developed by Cal Poly’s Legged Robotics group. The MPC framework employs a lumped rigid-body model that treats the robot as a single rigid body with forces applied directly at the foot contact points. The controller is developed within the ROS2 environment, with integration of state estimation and gait-pattern generation, to provide maximum modularity and …

Mechanoregulation Of Osteogenesis And Adipogenesis Of Human Mesenchymal Stem Cells, Justin Caron

Master's Theses

Bone-related diseases (e.g., osteoporosis) are primarily treated with pharmacologic therapies that often exhibit limited efficacy and substantial side effects. Currently, bone marrow derived mesenchymal stem cells (MSCs) have become one of most important cell options in bone regeneration due to readily available sources, strong proliferation abilities, weak immune rejection responses, and strong osteogenic differentiation potential. While identifying the most effective approach to enhance osteogenic differentiation of MSCs for bone regeneration is challenging, understanding the regulatory mechanisms is crucial for improving therapeutic efficacy. Recent research has focused on developing strategies to enhance osteogenesis, which involve biophysical and biochemical stimulation. Mechanical and …

Cost-Effective Automated Uhi Mapping With Ai: A Case Study Of A Scalable Framework For Climate Equity In San José, California, Martin Alvarez Lopez

Master's Theses

Urban areas experience the Urban Heat Island (UHI) effect, with higher temperatures than rural areas, disproportionately impacting low-income communities. Mapping UHIs is a process that usually requires significant amount of human resources, and is not scalable. The lack of accurate and detailed UHI maps makes it difficult for decision makers to design effective mitigation strategies. In this work we introduce a cost-effective, scalable, and universally applicable UHI mapping framework that leverages open-source data and AI-driven feature extraction from remote sensing imagery. Using various causative factors such as city characteristics, anthropogenic heat, city canyons, and meteorological variables, we create UHI maps …

Quantization On Graph Neural Networks For Image Classification, Rithik Reddy Katpally

Master's Theses

Quantization has become a key approach for reducing storage and computational demands of deep neural networks while maintaining high accuracy. Although 8-bit quantization is well-established for convolutional architectures such as ResNet50 and MobileNetV2, its application to graph-based vision models remains underexplored. In this work, we extend quantization-aware training to Vision Graph Neural Networks (ViGs) and conduct comparisons with quantized CNNs on the CIFAR-100 dataset. To ensure parity, all models have same training hyperparameters such as learning rate, batch size, optimizer, number of epochs. We used numerous techniques to preserve performance for low-bit precision. First, Pauta Quantization clips activation outliers based …

Stead: Spatio-Temporal Efficient Anomaly Detection For Time And Compute Sensitive Applications, Andrew Gao

Master's Theses

This paper presents a new method for anomaly detection in automated systems with time and compute sensitive requirements, with unparalleled efficiency. As these systems become increasingly popular, ensuring their safety has become more important than ever. Therefore, this paper focuses on how to quickly and effectively detect various anomalies in the aforementioned systems, with the goal of making them safer and more effective. Many detection systems have been developed with great success under spatial contexts; however, there is still significant room for improvement when it comes to temporal context. While there is substantial work regarding this task, there is minimal …

Using Facial Recognition For Selective Pose Detection, William J. Parker

Master's Theses

Pose detection involves locating and identifying key body points for all individuals within a frame. This enables the ability to convert the pose into a digital format, which can then be recorded and analyzed for a variety of purposes. Advancements in the field have already opened applications in areas such as digital fitness coaches, fall detection, and virtual reality. Existing approaches primarily focus on tracking all detected individuals, which limits the practical applications when attempting to analyze a single or specific subject when there are other people in frame. Previous work has discussed integrating identification, but these approaches use identification …