Computer Engineering Commons^™

Ai-Driven Biomarker Discovery & Progression Modeling For Precision Diagnosis Of Glaucoma, Cheng Huang

Computer Science and Engineering Theses and Dissertations

This dissertation presents a comprehensive study on the integration of artificial intelligence (AI) for glaucoma diagnosis and retinal image analysis. Leveraging multimodal imaging data including fundus photography, Optical Coherence Tomography Optical Coherence Tomography (OCT) and Optical Coherence Tomography Angiography (OCTA), the research develops a suite of deep learning frameworks designed to detect early glaucomatous changes with high precision, robustness, and interpretability. A series of novel architectures are introduced, spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models, all designed to enhance diagnostic accuracy and generalizability across diverse populations. To facilitate reproducible and scalable ophthalmic AI research, this work …

From Retrieval To Generation: Building And Evaluating An Ai Accompanist For Piano Duets With An Anticipatory Music Transformer, Sai Ruthvik Uppala

Masters Theses

Systems that accompany a live musician, such as ACCompanion, work by retrieval: they hold a written accompaniment and stretch its timing to follow the soloist, so they can only accompany music whose second part already exists as a score. This thesis asks whether that second part can instead be generated, and specifically whether a machine learning model can write an accompaniment for a piece whose score it has never seen. A player performs the primo, the melody; a model produces the secondo, the accompaniment; and a score follower places the generated notes against the live performance. If this works, a …

How Do Governments Combat Jihad Online?, Noah Cook

Honors College Theses

Since the September 11th, 2001 attacks, jihadist groups like ISIS, al-Qaeda, and al-Shabaab have used the internet as a tool for recruitment, radicalization, and propaganda dissemination. Since then, governments, non-governmental organizations, and private companies have developed strategies to combat jihadism on the internet. This paper examines how these actors have worked to mitigate the digital jihadist footprint and its effects by analyzing three main approaches to countering violent Islamist extremism on the internet: counter narrative initiatives, awareness-raising programs, and content removals. This paper finds that each of these methods has its own strengths and weaknesses. Counter narrative campaigns show the …

Creating An Updated Risc-V Platform With Hypervisor Support, Carter A. Glatt

Masters Theses

Virtualization has become an important methodology for implementing security and efficiency in embedded systems design. Virtualized environments provide flexibility and scalability of user-space environments, as hardware capabilities allow for multiple environments to run concurrently using the same hardware without impacting system performance or cost metrics. The ability to implement virtualized environments is fundamentally based on the instruction set architecture (ISA), which implements the necessary commands to facilitate the interface between physical hardware and virtual components.

RISC-V is an open-source ISA that can be used to generate platforms that support virtualization through the use of the H-Extension ISA. Previous research into …

Evaluating Diagnostic Information Preservation In Weakly Supervised Medical Imaging, Vinceline Bertrand

Electronic Theses and Dissertations

Weakly supervised medical imaging models trained with coarse image-level labels often report strong performance on metrics such as accuracy and AUC. This thesis argues that these metrics can be misleading: a model may succeed on a coarse diagnostic task while failing to preserve the fine-grained information needed for consequential clinical decisions. It makes this failure measurable through the diagnostic gap, defined as the divergence between coarse and fine-grained diagnostic preservation, across three connected studies. The first shows that near-perfect ovarian ultrasound accuracy reflects visual separability rather than pathological understanding. The second measures the diagnostic gap in a mammographic pipeline, where …

Tackling Oversmoothing, Heterogeneity, And Label Distributions For Robust Graph Learning, Yufei Jin

Electronic Theses and Dissertations

With the tremendous development of graph neural networks, graph learning has become a dominant solution applied to various applications naturally integrated with graph structures, including traffic networks [82], molecule networks [40, 22, 1, 30, 32], social networks [4], etc. While most existing graph learning solutions can handle homogeneous graphs (graphs with a single node type and a single edge type) and homophily graphs (graphs where node labels tend to be the same as their neighbors) for multi-class node classification downstream tasks well, in real world applications, graph structures can be more complex with heterogeneous graphs (graphs with multiple node types …

Development And Testing Of A Computer Vision Pose Estimation System For Planar Mobile Robots, Andrew Jones

Master's Theses

This thesis details the development and testing of a computer vision-based real-time pose estimation system for differential drive robots. A single camera with a fisheye lens is used to locate ArUco markers placed at fixed locations and attached to robots. Using the OpenCV library, the Perspective-n-Point (PnP) problem is solved to facilitate the transformation of 2-D robot positions in an image to world-frame coordinates. An analytical solution is presented to estimate robot poses based on a single PnP solution, rather than solving the PnP problem for each pose estimate. Pose information is relayed to individual robots using a multi-microcontroller architecture …

Hyperchaotic Noise Generation For Adversarial Encryption In Privacy-Preserving Image Classification, Neeraja Beesetti

Master's Theses

Artificial intelligence systems make useful predictions by taking in data and returning a classification, recommendation, or decision. Obtaining that prediction, however, requires sharing the data first. This creates a fundamental privacy challenge in machine learning: users must expose their data to receive a valuable prediction. Machine learning systems increasingly rely on cloud-based image classification for this reason, transmitting images from edge devices to remote servers rather than running large models locally. This creates a conflict between the accuracy a classifier requires and the privacy a data owner wants. Traditional encryption destroys the image structure on which a classifier depends, while …

Evaluation Of General Voronoi Diagram Decomposition For Harmonic Fields In Navigation Of Dynamic Environments, Franco Abullarade

Master's Theses

Harmonic potential fields provide provably minimum-free navigation, but any change to the workspace geometry invalidates the field and forces a costly global recomputation, typically restricting them to static environments. This thesis extends the harmonic map framework of Vlantis et al., which maps the free workspace onto a unit disk and uses an atlas of per-region transformations, to dynamic indoor settings. First, we replace their manually annotated room partition with an automatic decomposition based on the Generalized Voronoi Diagram, allowing the atlas to be built from an arbitrary occupancy grid in an automated way. Second, we introduce a localized repair procedure …

Modular Verification For Network-On-Chip Designs Using Probabilistic Verification And Assume-Guarantee Reasoning, Nicholas Waddoups

All Graduate Theses and Dissertations, Fall 2023 to Present

To satisfy increasing demands for computer chip performance in personal computing, mobile devices, and commercial server computing, a modern computer chip is constructed with tens (or hundreds) of small individual computing modules. Each of these modules must communicate with one other to share information about the running state of a computer. Historically, when chips were a few modules a simple communication method sufficied. However, as the number of modules in a chip grew, a more effecient method was needed in order to maintain performance across the system as a whole. A Network-on-Chip (NoC) design is the de-facto communication method for …

Developing A Rapid Urban Forest Assessment System For Sustainable City Greenification, Daniel Gonzalez

Master's Theses

This thesis presents the Rapid Urban Forest Assessment (RUFA) system, a web-based platform that integrates urban tree inventories and aerial tree detection to assess forest health across California’s census-designated places. RUFA combines inventoried tree records with coordinates detected from high-resolution multispectral imagery using convolutional neural networks, then computes a composite RUFA Score from four metrics: canopy cover percentage, trees per capita, tree diversity (TD-50), and tree evenness. The thesis addresses two engineering challenges in building the dashboard: querying and aggregating over seven million tree records in real time, and rendering spatial summaries at multiple zoom levels without recomputing cluster assignments …

Secure And Compassionate Dementia Care: Non-Intrusive Remote Monitoring Of Falls, Wandering, And Agitation, Awan-Ur- Rahman

Master's Theses

Alzheimer’s disease and related dementias (ADRD) present significant safety challenges, as affected individuals may experience falls, wandering, agitation, and a progressive decline in independence. Although continuous monitoring can enable timely intervention, many existing systems rely on cameras or wearable devices, which may introduce concerns related to privacy, comfort, and sustained use. This thesis explores privacy-preserving and non-intrusive remote monitoring through two complementary studies. The first study presents an ambient Wi-Fi channel state information framework for recognizing agitation and eight daily activities. The proposed approach translates behavioral and physiological markers commonly captured by wearable sensors into the Wi-Fi sensing domain. The …

Hardware-In-The-Loop Evaluation Of Sensor-Source Selection For Prosthetic Locomotion Intent Recognition, Victoria Asencio-Clemens

Master's Theses

Active lower-limb prostheses use intent-recognition systems to identify a user’s locomotion mode and select an appropriate control strategy, but sensor configurations that perform well offline may be unsuitable for resource-constrained embedded hardware. Existing sensor-selection methods generally prioritize classification accuracy without directly accounting for processing latency, memory usage, or other hardware-dependent requirements. To address this limitation, this thesis develops a hardware-in-the-loop source-selection framework for embedded classification of level walking, ramp ascent, ramp descent, stair ascent, and stair descent using multimodal biomechanical data from transtibial amputee participants. Subject-specific linear support vector machine classifiers were evaluated using trial-held-out validation, and candidate configurations from …

A Maintainable Extensible And Performant Compiler Toolchain For The Trustguard Architecture, Ethan N. Emery

Master's Theses

TrustGuard is a hardware architecture implementing a CAVO (Containment Architecture with Verified Output) model, which provides security guarantees by bootstrapping trust of a system to a hardware component known as the Sentry. Rather than verifying an entire system, TrustGuard re-executes trusted computation on the Sentry and validates the host system's execution before allowing values to pass to the outside world, thereby containing the effects of erroneous computation. Implementing this architecture in practice without hardware modifications to a host CPU requires a compiler toolchain capable of automatically generating instrumented binaries for both the untrusted host and the trusted Sentry from C …

Understanding The Correlation Between Prediction Performance And Trust In Ai Through Scenario-Based Tasks, Likhitha Kammara

Theses and Dissertations

Trust in artificial intelligence is commonly assessed through self-reported scales or behavioral reliance, yet behavioral reliance is retrospective and can only be observed after a decision has already been made. This thesis examines whether prediction accuracy — a user's ability to predict what an AI system will recommend before its output is revealed — can serve as a prospective correlate of trust in the same empirical sense as behavioral reliance. The study was conducted in two phases using scenario-based AI decision tasks across disaster response, healthcare, and infrastructure restoration contexts, employing a between-group design in which participants either predicted AI …

Evaluating Machine Learning Models On Classification Of Novel Cyber Attacks In The Healthcare Domain, Promise Ehimen

Dissertations, Theses, and Projects

The increasing adoption of the Internet of Medical Things (IoMT) has improved healthcare delivery through connected medical devices while simultaneously expanding the cybersecurity risks facing healthcare organizations. Although machine learning based intrusion detection systems have demonstrated high detection accuracy, their ability to respond reliably to previously unseen cyberattacks remains uncertain. This study investigated how a Neural Network model and a Logistic Regression model classified novel cyberattacks within the IoMT environment. The Neural Network and Logistic Regression models were both trained and tested using a subset of the CICIoMT2024 benchmark dataset. The Neural Network achieved 99.82% test accuracy and a 0.94 …

Improving The Fpga Radio Design Cycle: Implementing Dvb-S2 Modulation Using Verilator And Gnu Radio, Seth Pellegrino

Dissertations and Theses

In embedded digital radio systems, a central challenge is meeting the real-time throughput required to process the samples--especially for space-bound ultra-wideband SDRs which must handle more than 100 Gbps entirely onboard. An FPGA's programmable logic offers sufficient potential, but realizing a particular radio flow is a project usually fraught with defects and long turnaround times. We simulated Verilog modules in a custom harness that adapted a Verilated model to GNU Radio, which allowed for breaking down a complicated radio flow (here, DVB-S2 modulation) into a series of well-bounded problems each with clear criteria for success. The framework, built on open …

Rthermal: Gate Level Power And Thermal Simulation For 3d-Stacked Chips, Peter Xiong

Master's Theses

As the number of transistors in modern processors increases, heat dissipation has become a major bottleneck to scalability. The use of 3D stacking further intensifies this problem, as heat from multiple layers can accumulate vertically. These challenges create a growing need for tools that can accurately and efficiently simulate the thermal behavior of 3D chips during design and validation. Several existing tools model thermal behavior for 3D-stacked chips and can simulate average heat over large spatial regions or long time intervals. However, when heat is concentrated in a small area or over a short time window, such models can miss …

Adaptive Task-Driven Lidar Point Cloud Compression For Autonomous Driving, Su Hyun Kim

Master's Theses

Autonomous-driving systems generate large LiDAR point clouds, but compression can damage the sparse object-support structure needed by 3D detectors even when reconstructions appear visually plausible. This thesis asks whether adaptive LiDAR compression can preserve downstream detection better than uniform compression by allocating more fidelity to detector-relevant regions. The main study builds a mask-aware range-image codec with an encoder-decoder bottleneck, an importance head, and an adaptive quantization variant. It compares this adaptive variant package with a confirmed masked uniform baseline under one fixed RangeDet evaluation surface and one fixed KITTI validation subset. Two supporting studies bound the result: a projection-reconstruction PointPillars …

Early Failure Detection In Web Navigation Agents Via Closed Sequential Pattern Mining, Sergio Talavera

Master's Theses

LLM-based web navigation agents fail on the majority of tasks while consuming substantial computational resources before failure becomes apparent. This thesis investigates whether closed sequential pattern mining on the first K steps of agent execution traces can predict task failure early enough to enable meaningful computational savings with interpretable justification. We develop a two-phase system: an offline pipeline that symbolizes agent traces, extracts K-step prefixes, mines closed patterns via BIDE+, and ranks them by failure precision; and an online detector that matches live executions against the resulting pattern library. We evaluate on 1,544 MiniWoB++ traces across three open-weight language models …

Data Augmentation For Vision-Language-Action Models: Bridging Vision And Language, Miaosen Zhou

Master's Theses

This thesis focuses on real-time task execution and object detection for autonomous robots through dataset augmentation. We propose a data augmentation approach to address dataset imbalance in Vision-Language-Action (VLA) models across both image and text modalities during the fine-tuning process. The proposed method takes an image as input and generates a structured textual description using a prompt engineering strategy to augment the textual input. The generated augmented text includes key elements such as the task goal, scene description, reasoning, and execution plan, along with other relevant contextual information. This enriched representation improves the quality of the training data and supports …

Moral: Multimodal Reasoning For Autonomous Language Models With Sensor-Grounded Spatial Bev Rendering, Ambarish Govindarajulu Kaliamurthi

Master's Theses

Autonomous-driving vision-language models describe scenes fluently but reason poorly about metric, safety-critical spatial relationships because they do not read sensor geometry in a grounded way. This thesis presents MoRAL (Multimodal Reasoning for Autonomous Language Models), a two-stage fine-tuning pipeline that teaches a compact 2-billion-parameter VLM to decode a physics-encoded Bird’s Eye View (BEV) representation – LiDAR distance as color, object class as cluster shape, radar Doppler velocity as directional wedges – and then trains it to reason over that representation for driving decisions. Stage 2 then fine-tunes on 57,696 teacher-generated chain-of-thought examples across eight question types, using Cosmos-Reason2-8B as teacher …

The Zeal Instruction Set Architecture, Joseph A. Gerani

Master's Theses

The Instruction Set Architecture of a CPU (Central Processing Unit) determines what type of instructions the CPU is able to understand, how those instructions are encoded, and what it should output upon receiving those instructions as input. There are currently three popular ISAs meant for the consumer market: x86, RISC-V, and ARM, as well as a fourth that mostly now exists in the server market by the name of Power. One of the most important parts of an ISA is for engineers to be able to understand it and make use of it. If an ISA is too complicated, nobody …

Towards Neural Network Optimization: Addressing Issues With Corrupted Weights Within Models, Nick Najafizadeh

Master's Theses

Neural networks are a recent popular technology inspired from human brains. Much of their popularity arises from how they excel in reasoning and logic, and are generally rather efficient in their tasks. With those strengths, they are frequently used in transportation and business among many other fields. However, neural networks have many factors that can deteriorate their performance, one of the most critical being weight corruption. Therefore, it is of utmost importance to detect and handle them as soon as possible so as to minimize the negative impact on a network’s performance. The optimization of neural networks would be especially …

Pipeline Optimization Of Agentic Llms For Text-To-Sql, Peter Conant

Master's Theses

Current database interfaces limit users’ interaction to those with technical skills, creating timely roadblocks for non-technical professionals. Text-to-SQL aims to simplify database interactions by translating natural language questions into database queries, but long-standing challenges like question understanding, question-schema linking, and SQL generation have held the field back. In the AI era, foundational LLMs prove to be very capable of question understanding SQL, perform well in Schema Linking, Generation, and Evaluation tasks. However the cost to run these model is a hurdle for many organization with low funds and resources. Text-to-SQL solutions often operate across large enterprise size databases with, and …

Privacy-Preserving Intrusion Detection For The Internet Of Medical Things Using Ensemble And Federated Learning, Theyab Alsolami

Electronic Theses and Dissertations

The rapid proliferation of the Internet of Medical Things (IoMT) has transformed healthcare by enabling continuous monitoring, intelligent diagnostics, and data-driven clinical decision-making. However, this increased connectivity has significantly expanded the attack surface of healthcare systems, exposing sensitive patient data and critical medical devices to cyber threats such as intrusion and data exfiltration attacks. Ensuring both strong security and strict privacy preservation in IoMT environments remains a fundamental and unresolved challenge.

This dissertation investigates the design and evaluation of robust and privacy-preserving intrusion detection systems (IDS) for IoMT networks using advanced machine learning techniques. The research first examines the effectiveness …

Resource Constraint Evacuation Route Planning A Capacity-Aware Charge-Encoded State-Space Approach, Praveen Borra

Electronic Theses and Dissertations

Emergency Management Information Systems (EMIS) are defined as a set of tools that assist decision-makers in risk assessment and disaster response for significant multi-hazard threats and disasters. Over the past several decades, EMIS have become increasingly important for understanding, managing, and governing transportation systems during large-scale emergency events. One of the primary objectives of EMIS is to efficiently utilize spatial and network datasets to support evacuation planning, identify critical transportation patterns during emergencies, and allocate resources effectively. However, the increasing complexity and scale of modern transportation systems present significant challenges in developing reliable evacuation planning solutions.

One of the most …

Assessing Computer Vision Based Conflict Detection In Uas Traffic Monitoring Under Secure Communication Constraints, Fadjimata Issoufou Anaroua

Doctoral Dissertations and Master's Theses

The rapid growth of Unmanned Aircraft Systems (UAS) and Advanced Air Mobility (AAM) is creating a new low-altitude airspace ecosystem where drones, air taxis, service suppliers, communication networks, sensors, and ground-based monitoring systems must work together safely. Within this ecosystem, UAS Traffic Management (UTM) is expected to provide a digital framework for coordinating operations beyond traditional air traffic control. However, reliable integration also requires resilient monitoring methods that can detect non-cooperative aircraft, protect communication links, and maintain timely situational awareness under real-world constraints.

This dissertation examines how computer vision can support cooperative monitoring systems such as Remote ID and ADS-B …

Design And Fpga Deployment Of Quantized Convolutional Spiking Neural Networks For Ecg Arrhythmia Classification, Olamilekan Banjo

Electronic Theses and Dissertations

Wearable ECG monitors enable continuous cardiac surveillance, yet most remain limited to basic heart rate metrics or coarse atrial fibrillation detection, relying on cloud-based analysis that introduces latency, connectivity dependence, and battery drain. Deploying advanced multi-class arrhythmia classification directly on-device is constrained by the tight memory, power, and computational budgets of wearable hardware. This dissertation presents a Quantized Convolutional Spiking Neural Network (QCSNN) for real-time ECG arrhythmia detection on edge hardware, developed across three progressive phases.

Phase 1 introduces a separately trained two-stage QCSNN architecture — a binary classifier cascaded with a four-class classifier — trained directly via surrogate gradient …

A Machine-Learning-Based Systematic Framework For Modeling Compression And Recompression Indices For Florida Soils, Michael Morales

Doctoral Dissertations and Master's Theses

This thesis develops a machine-learning framework for estimating the compression index and the recompression index of Florida soils from routinely measured index properties, and reports two studies that build it. Consolidation settlement design requires both indices, and both are obtained from the incremental-loading oedometer test, which occupies a specimen for one to two weeks; the index tests that accompany it are complete within hours. Empirical correlations have filled that interval since the 1950s, but their coefficients are calibrated on specific soil populations and transfer poorly between regions. The first study analyzes 376 consolidation tests compiled for the Florida Department of …