Artificial Intelligence and Robotics Commons^™

Sentinel: Evaluating Occlusion-Centered Next-Best-View Selection Using Rgb-Derived Pseudo-Geometry, Paul Nassar

Master's Theses

Three-dimensional cameras provide direct geometric measurements, but their cost, weight, power requirements, and calibration constraints can limit their use in various lightweight or large-scale sensing systems. A potential alternative is to use conventional two-dimensional RGB cameras together with geometric reconstruction models that infer a partial three-dimensional representation from images. This thesis evaluates that possibility for next-best-view (NBV) selection through Sentinel, an occlusion-centered system for static, object-centric scenes with known camera poses and intrinsics. Sentinel converts source RGB observations into pseudo-geometry using monocular depth or point-map predictions, combines those predictions with camera-ray evidence, identifies occluded unknown regions, and selects a candidate …

Predicting Student Belonging In Computing Education: A Multimodal Machine Learning Approach Using Eeg And Survey Data, Hannah Moshtaghi

Master's Theses

Measuring students’ sense of belonging, characterized by feelings of acceptance, inclusion, and encouragement from teachers, remains a significant challenge in computing education. Prior research has associated this multidimensional construct with positive academic outcomes and has identified instructors’ growth- and fixed-mindset messaging as a potential influence. However, belonging is a complex and deeply personal experience that is difficult to capture through direct observation alone. Current measurement methods rely on self-report surveys, which may not capture every aspect of an experience that can also involve emotional and cognitive responses.

This thesis investigates whether combining EEG data recorded during a belonging questionnaire with …

Ai Interview Helper: A Tool For Assisting Search And Rescue Long-Profile Interviews, Dylan P. Starink

Master's Theses

In Search and Rescue (SAR) operations, time pressure and limited interviewer experience can lead to missed opportunities when interviewing a missing person’s friends and family. This thesis presents a real-time, end-to-end system that provides context-aware follow-up question suggestions as interviews unfold. Leveraging large language models (LLMs) and agentic design patterns, the system is intended to support interviewers by helping them identify relevant follow-up questions and pursue potentially overlooked lines of inquiry.

The system was evaluated through three mock interviews with two SAR interviewer participants across two events. Given the limited sample size, the results provide early insights into the feasibility …

Trace: Temporal Rhetorical Analysis And Consistency Evaluation For Legislative Speech, David Hernandez

Master's Theses

Legislators frequently discuss the same policy issues across multiple hearings and legislative sessions, sometimes maintaining consistent positions and other times modifying or reframing their stance over time. Understanding how these positions evolve is important for analyzing political discourse and democratic accountability, yet identifying such shifts at scale remains difficult.

We introduce TRACE (Temporal Rhetorical Analysis and Consistency Evaluation), a system built on the Digital Democracy Database (DDDB) for detecting rhetorical inconsistency in California legislative hearing testimony. TRACE organizes utterances into speaker-anchored timelines indexed by bill and session, then applies hybrid semantic retrieval — combining dense BGE embeddings with BM25 lexical …

Integer Quantization And Embedded Deployment Of Cnn Star Trackers For Cubesats, Meora R. Giusiano

Master's Theses

A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the detection and centroiding stage, offering improved sub-pixel accuracy and recovering faint stars that classical thresholds lose to stray light and sensor noise. The improvement comes at higher computational cost; the PolySat systemboard targeted in this work lacks the floating-point hardware these networks assume.

This thesis closes the gap between floating-point desktop evaluation and embedded integer deployment. Nine encoder-decoder CNN …

What Makes A Modern Attention Implementation?, Brian H. Slonim

Master's Theses

Since the seminal assertion by Vaswani et al. in 2017 that “Attention Is All You Need,” transformer models have risen to ubiquity due to their ability to learn extremely complex patterns from sequence data, culminating in the unprecedented generative capabilities of large language models. These models’ strength lies in their scale: hundreds of millions (e.g., BERT-LARGE) to billions or trillions of learned parameters. Running inference with these models, let alone training them, would be intractable without significant innovations in the hardware and software that support them. This need has driven an enormous demand for GPU compute and associated software ecosystems, …

High-Resolution Queries, Low-Resolution Context: Scaling Vision Transformers With Asymmetric Spatial Reduction, James M. Dwyer

Master's Theses

Vision Transformers (ViTs) have demonstrated great performance on image classifica tion benchmarks, however, the quadratic complexity of the self-attention mechanism with respect to sequence length limits their scalability to higher resolution inputs. The attention score matrix grows as O(N2) in both compute and memory, where N is the number of patch tokens, making ViTs computationally expensive and memory intensive for applications that require real-time inference or operate under resource constraints.

This thesis investigates whether the key and value sequences of the self-attention mechanism can be compressed using the local spatial structure of the image — while keeping queries at full …

Scorespeak: An Agentic System For Natural Language Control Of Musical Scores, Nathan S. Lim

Master's Theses

With the recent popularization of large language models (LLMs), natural language has become one of the most accessible and powerful ways for people to interact with creative tools. Although they have become common in mainstream domains like image and audio editing, there is currently no robust AI-based system that can reliably turn free-form language into edits for symbolic musical scores. This gap represents a missed opportunity to improve human workflows for creating and editing sheet music, but it is also a fundamental limitation for other agentic music systems; without a robust mechanism for translating free-form language into structured scores, AI …

Political Inconsistency Detection Across Legislative Speech And Public Communications, Scott M. Pramuk

Master's Theses

Political actors communicate about legislation across multiple contexts, including committee hearings, recorded votes, and public-facing press releases. Differences between these forms of communication can provide useful signals for journalists and researchers seeking to understand how legislators present policy positions to different audiences.

This thesis extends the Digital Democracy Project, a legislative transparency initiative that provides access to California state legislative hearing transcripts, voting records, and related legislative data. Specifically, this work incorporates publicly accessible, legislator-authored news releases into the Digital Democracy Database and develops a pipeline for analyzing legislative communication across multiple sources. The system collects news releases from California …

Multimodal Machine Learning For Soil Burn Severity Mapping Across California Wildfires, Sanjana Checker

Master's Theses

Accurate mapping of soil burn severity (SBS) is critical for post-fire watershed management, erosion risk assessment, and ecological recovery planning, yet traditional field-based approaches remain costly, time-intensive, and spatially limited. This thesis presents a machine learning pipeline for wall-to-wall SBS classification across California wildfires using multi-sensor satellite imagery, terrain derivatives, and bioclimatic covariates. Field-collected SBS observations (n = 2,180) from 52 wildfires occur- ring between 2013 and 2025, sourced from the U.S. Forest Service and CAL FIRE, were used to train and evaluate multiple classification architectures within a Google Earth Engine and Google Cloud-based prediction framework. After upsampling the unburned …

Using Ensemble Disagreement To Stabilize Conformal Prediction Under Distribution Shift, Patrick D. Murphy

Master's Theses

Semantic segmentation of eelgrass from drone imagery is crucial for coastal habitat monitoring, restoration, and management, as these habitats continue to see rapid changes due to climate change and human influence. However, the reliability of generalizing a deployed classification model relies on both high-accuracy segmentation as well as robust uncertainty quantification that holds up when conditions change over years or locations. Conformal prediction (CP) is a method that converts a classifier's output into prediction sets with a guaranteed average coverage level for in-distribution data. However, the “vanilla” conformal score can often under-cover in hard or out-of-distribution (OOD) regions under drift. …

Neurosymbolic Counterpoint Generation, Paul D. Jarski

Master's Theses

Recent advancements in generative artificial intelligence have revolutionized music generation, yet research has predominantly focused on raw audio synthesis over music in symbolic form, i.e. a score. This thesis presents the first neurosymbolic model designed to generate imitative Renaissance counterpoint in symbolic (MIDI) format. By leveraging an autoregressive Transformer architecture, this research explores the capacity of deep learning models to manage independent voices and strict stylistic constraints.

We compare multiple data representation strategies with distinct tokenization methods. The proposed model incorporates a symbolic component that enforces fundamental contrapuntal rules. Additionally, this thesis contributes a preprocessed dataset of Renaissance polyphony, in …

Video Generation Techniques For Novel View Synthesis With Flow-Matching Transformers, Xiuyuan Qiu

Master's Theses

Novel view synthesis (NVS) aims to generate images of a scene from unseen camera viewpoints. Recent work, such as Stable Virtual Camera, shows that large-scale image diffusion models like Stable Diffusion can be adapted for pose-conditioned view synthesis by incorporating video-generation techniques with camera conditioning. In this thesis, we introduce MVFlow, a new NVS model that extends this approach to a different image generation architecture: a flow-matching diffusion transformer, specifically FLUX.1, which has demonstrated strong performance in image synthesis. We evaluate MVFlow under varying input view counts and pose distance settings. Our results show that this architectural transfer is feasible; …

A Literature Review On Ethics In Medical Diagnostic Ai & Analysis Therein, Connor J. Turetzky

Master's Theses

Artificial Intelligence presents a very promising future in medicine. Being able to diagnose and recommend treatments quickly is vital in ensuring positive patient outcomes. However, the new technology is not without risk. In this narrative literature review, the risks of AI in terms of bias, ethics, and environmental impact will be explored through existing research. This paper will focus on research published between 2019 and 2026, highlighting the major ethical and systematic problems currently facing diagnostic AI. Historical bias in medical data has led to AI that share those biases, and humans inherit that bias creating a potential negative feedback …

An Analysis Of Neuroidal Memory Formation Within D. Melanogaster, Jerry Chang

Master's Theses

The Neuroidal model poses a neurobiologically plausible theory for modeling the brain. This symbolic network has been shown to capture realistic memorization behaviors using the JOIN algorithm. The model has also been recently improved by incorporating Watts-Strogatz small-worlds within its base structure. From the efforts of neuroscience researchers, we have access to the Drosophila melanogaster (D. melanogaster) fruit fly’s connectome, which has been found to also contain small-worlds in this thesis. By synthesizing the Ocellar Ganglion (OCG) region of Drosophila, we compare a digitized version of a real-world brain with an instance of the Neuroidal model. In this thesis, we …

Marsanywhere: Dataset And Cross-View Diffusion Model For Satellite-To-Ground View Synthesis With Mars Data, Benjamin T. Hinchliff

Master's Theses

Satellite-to-ground view synthesis aims to create a realistic ground view image from a corresponding satellite view image. This is a well-studied problem for street level imagery, with good results being achieved by using modern image synthesis techniques such as diffusion models. However, despite the public availability of satellite and ground level imagery on Mars, these techniques have yet to be applied to the domain due to difficulties in collating and processing the data into a usable form. We address this deficiency by creating a dataset consisting of ground view panorama imagery from the Perseverance rover, along with associated satellite view …

Accelerating Relationship Discovery In Chronic Lower Back Pain Through Knowledge Graph And Ontology Enhanced Large Language Models, Damon Lin

Master's Theses

Chronic 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 …

Generalized Detection Of Animal Behavior Using Accelerometers, Alexander J. Arrieta

Master's Theses

Animal mounted sensors are becoming increasingly used to passively monitor both domestic and wild animals. Advances in lightweight accelerometer and GPS technology have allowed many animals to be fitted with high accuracy sensors for extended periods of time. This leads to new opportunities to study animal behavior without direct observation. However, interpreting the raw data is difficult due to the high volume and missing context of the information. Machine learning techniques excel at extracting information from raw data streams and are excellent candidates for processing the sensor data. However, due to large variance in how different animals execute the same …

Atlas Of Ai: Power, Politics And The Planetary Costs Of Artificial Intelligence - Book Review, Jelena Popov

Feminist Pedagogy

No abstract provided.

Review Of Ai Needs You: How We Can Change Ai’S Future And Save Our Own, Tracy A. Fernandez Rysavy

Feminist Pedagogy

AI Needs You: How We Can Change AI’s Future and Save Our Own urges citizens to band together now, while A.I. is still in its nascent stages, to head off its potentially destructive repercussions and ensure that the technology serves more than just a wealthy few. While such efforts might seem out of reach in our polarized society, author Verity Harding points to three cases from history where policy was heavily influenced by multistakeholder collaborations. This review encourages educators to use the book as a way to study business ethics; out-of-the-box thinking; and intersectional, inclusive consensus-building over a top-down approach.

Building An Inclusive Ai Chatbot For Diverse Student Communities At Cal Poly: Uplift Ai, Gideon Telahun

College of Engineering Summer Undergraduate Research Program

This 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 …

Building A Novel Question-Answering System Using Retrieval-Augmented Generation For The California Fair Political Practices Commission, Saanvi Dua

Master's Theses

The California Fair Political Practices Commission (FPPC) receives a high volume of inquiries via email from public officials, the general public, and other agencies, which currently requires staff to manually search through informational documents and manuals to provide timely responses. This process is both labor- and time-intensive.

To address this challenge, we design a question-answering (QA) system that drafts responses to emailed questions by retrieving relevant information from the FPPC’s manuals using a retrieval-augmented generation (RAG) framework. Although the current implementation focuses on a single manual, the system is designed to be adaptable to the broader set of FPPC documents. …

Ecological Footprint Analysis Of Chatgpt (Gpt-3), Isabella Boulais

Computer Science and Software Engineering

Climate change is an escalating crisis that demands immediate action from all sectors, including the rapidly advancing field of artificial intelligence (AI). While AI offers climate solutions, its own environmental impact raises concerns. Unfortunately limited research due to rapid development, system complexity, and lack of standardized methodologies hinders our understanding of AI’s environmental consequences. This project aims to conduct a comprehensive ecological footprint analysis of OpenAI’s GPT-3 model that is used to power ChatGPT, establishing guidelines for assessing AI systems’ environmental impact and proposing a framework for improvement. Going beyond tracking carbon emissions, this project will outline the broader lifecycle …

A Decision Support System For Conference Session Selection Using Natural Language Processing, Tillman E. Erb

Master's Theses

Conference attendees are faced with selecting from hundreds to thousands of presentations and sessions in pursuit of new findings and methods relevant to their area of interest, an overwhelming amount of information from which to clearly make a decision. To address this, we developed a decision support system leveraging natural language processing (NLP) techniques such as semantic matching. By creating and matching embeddings of conference presentation abstracts and titles, the application provides improved query matching compared to keyword searching. We introduce Session Scout, a novel conference decision support system built upon a semantic retrieval framework. Session Scout is designed to …

Topodino: Self-Supervised Topological Representation Learning For Neuronal Morphologies, Yasser Binbisher

Master's Theses

Neuronal cell types are categorized by transcriptomic identity, yet their morphological heterogeneity defies this classification. In response, researchers have adopted unsupervised graph representation learning as a tool to reveal morphological variation within single-class transcriptomic types. However, the complex geometry of neuronal morphology—especially long axons and dense dendrites—challenges graph neural networks, which struggle with message propagation across extended structures. To mitigate this, current approaches enforce sub-sampling on neuronal graphs and omit axons entirely, sacrificing critical biological features for computational efficiency. To overcome this trade-off, this thesis introduces TopoDINO, a self-supervised, topology-aware representation learning model designed to preserve the full hierarchical organization …

Minifying Deep Denoising Networks With Knowledge Distillation, Antonio L. Rozzi

Master's Theses

Hearing loss is a prevalent condition, affecting hundreds of millions globally, with a higher incidence among older adults. While hearing aids are the standard treatment, the majority of those who could benefit from hearing aids choose not to wear them, attributing this decision in large part to their inability to perform well in conversations in large groups and in noisy situations. To date, no denoising systems on commercial hearing aids are able to improve speech intelligibility. Recent advances in artificial intelligence research have shown that large deep-learning models can in fact improve speech intelligibility by removing background noise from audio. …

Adversarial Deep Reinforcement Learning For Tank Duel Simulation Using Lidar-Based Observations, Braedan Kennedy

Master's Theses

Previous research has demonstrated that reinforcement learning agents can learn to steer differential-drive robots around obstacles using 2D lidar scans as observations. However, these studies typically treat all range returns as undifferentiated obstacles—objects to avoid—without distinguishing between different object types. This thesis builds upon previous research by introducing an adversarial task in which an agent must interpret raw range readings to both avoid static obstacles and identify, pursue, and engage a hostile target.

To investigate this problem, this thesis introduces TankGame, a novel, lightweight 2D tank duel simulator. Each agent receives a 360° lidar scan, controls its motion via tread …

Opening The Black Box With Regal: A Novel Explainable Ai Approach To Uncover Key Predictors In Search And Rescue Success, Brandon Hyunjun Kim

Master's Theses

The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL …

Efficient Gan-Based Adversarial Example Generation Against Ml-Based Network Intrusion Detection Systems, Darren D. Hartono

Master's Theses

In the realm of network security, Network Intrusion Detection Systems (NIDS) are essential for identifying and mitigating malicious activities targeting networked devices. Traditionally, these systems have relied on signature-based and anomaly-based detection techniques. However, the increasing complexity and adapt- ability of cyber threats have driven the adoption of Machine Learning (ML) ap- proaches in modern NIDS, significantly improving their ability to detect a wider range of attack vectors. Despite these advancements, ML-based NIDS remain vulnerable to adversarial examples—deliberately crafted inputs designed to mislead models and trigger incorrect classifications. Originally identified in the field of computer vision, adversarial examples now pose …

Real-Time Network Simulations For Ml/Dl Ddos Detection Using Docker, Luis D. Garcia

Master's Theses

As the integration of artificial intelligence (AI) within cybersecurity continues to

grow, machine learning (ML) and deep learning (DL) models are increasingly used to

detect cyber attacks. However, these models are rarely evaluated in real-time attack

scenarios to see how subtle changes from the real networking environment can affect

their predictions. To address this issue, we propose a scalable, platform-independent

Docker testbed specifically designed for simulating real-time Distributed Denial of

Service (DDoS) attack scenarios that allows researchers to deploy and evaluate their

pre-trained, ML and DL detection models. Our framework is simple to configure

and can run across Intel and …