Digital Commons Network^™

Robust Hardware Trojan Detection Leveraging Dual‑Domain Features And Stacked Ensemble Learning, Sefatun-Noor Puspa

All Theses

In Cyber-physical systems rely on sensors, communication, and computing, all powered by integrated circuits (ICs). These ICs are vulnerable to malicious hardware attacks, with hardware Trojans being one of the stealthiest threats. Trojans are malicious implants in the circuitry, which are often inserted during design or fabrication stages. This stealthy addition remains dormant until triggered and might cause functional disruptions or sensitive information leakage once triggered. Traditional IC validation methods, such as functional testing and logic analysis, usually fail to capture these subtle anomalies because hardware Trojans are intentionally designed to mimic normal circuit behavior. They often remain dormant under …

Enhanced Situational Awareness Of Solar Pv Plants For Near Real-Time Planning And Operation In Modern Power Systems, Michael A. Walters

All Theses

Solar photovoltaic (PV) plant development and utilization is increasing worldwide but remains intrinsically challenged by its large dependence on highly variable weather conditions and operating states. This paper presents a framework to leverage three new situational awareness indices (SAIs), namely: weather condition index (WCI) to gauge operational performance based on environmental states, operational complexity index (OCI) to indicate the severity of power generation reductions, and photovoltaic generation index (PVGI) to provide a final determination of the impact on power generation and to bolster situational awareness in planning and operational contexts for solar PV plants. This is accomplished by exploiting the …

Robustness Of Vision Language Models For Pedestrian Detection Tasks, Ostonya K. Thomas

All Theses

Autonomous vehicle (AV) systems typically employ modular systems in which discrete components handle separate tasks such as perception, computation, and path planning. While flexible, this approach allows errors to propagate and compound across the pipeline, and many AI systems offer little transparency into their internal decision-making. Such limitations are particularly concerning in safety-critical domains where failures can carry lethal consequences. Vision Language Models (VLMs) have emerged as a promising alternative because they support end-to-end implementations that bypass compounding error risks and provide natural language explanations of their outputs. Despite these advantages, prior research has demonstrated that both computer vision systems …

Multimodal Aerial Image-Based Ground Object Detection And Classification Using Yolo, Erik Nielsen

All Theses

Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating …

Exploration Of Real-Time Power Electronic Simulation On Amd Npu, Shouyu Du

All Theses

The rapid electrification of the automotive and data center sectors has created a critical demand for high-fidelity, real-time simulation of complex power electronic systems. While Hardware- in-the-Loop (HIL) simulation on Field-Programmable Gate Arrays (FPGAs) is the current industry standard, it presents significant challenges regarding development complexity and memory limita- tions. This dissertation investigates the feasibility of utilizing Neural Processing Units (NPUs)— specifically the AMD AI Engine (AIE) XDNA2 architecture—as a novel platform for real-time, deterministic circuit simulation. This study establishes a comprehensive automated modeling framework based on graph theory and Massarini’s method to derive linear state-space representations for arbitrary circuit …

Implementation Of A Local Llm Serving System For Agentic Ai, Zhiheng Ni

All Theses

This thesis presents a system that allows large AI models to run directly on personal devices instead of relying on cloud servers. Recent advances in artificial intelligence, especially large language models (LLMs), have made it possible to build powerful applications such as chatbots, coding assistants, and intelligent agents. However, most of these systems run in the cloud, which raises concerns about privacy, latency, and cost.

To address these issues, this work develops a local AI serving system that runs efficiently on a specialized hardware component called a Neural Processing Unit (NPU). The system provides a unified interface that supports multiple …

Deep Learning For Predicting Impact Energy And Compression After Impact Strength Of Composite Materials Using C-Scan Images, K. T. Tan, Jason P. Mack, Faizan Mirza, Zhong-Hui Duan

University Research

Traditional assessment of post-impact performance in carbon fiber reinforced polymer (CFRP) composites often relies on simplified scalar metrics that fail to capture the complex spatial interactions driving failure. This study addresses this limitation by developing an automated, end-to-end deep learning framework that shifts from manual feature extraction to the direct interpretation of raw damage morphology from ultrasonic C-scans. Using a ResNet18-based convolutional neural network (CNN) trained on 1,428 augmented images, the model achieved coefficients of determination (R2) of 0.7948 ± 0.0847 for compression after impact (CAI) strength and 0.9436 ± 0.0098 for impact energy. Beyond prediction, this dual-purpose methodology serves …

Ai Institute Summer Camp Webinar Summary, Dora Nguyen

Paul English Applied Artificial Intelligence (AI) Institute Publications

This report summarizes the AI Institute Summer Camp informational webinar hosted by the Paul English Applied Artificial Intelligence Institute (PEAAII) at the University of Massachusetts Boston. The webinar introduced the structure, curriculum, learning objectives, and student outcomes associated with the 2026 AI Institute Summer Camp. In addition to summarizing the webinar content, this report analyzes participant questions, engagement trends, and areas of audience interest. Findings indicate strong interest in coding accessibility, mentorship opportunities, student outcomes, research experiences, and program flexibility. The report also identifies opportunities for improving future webinar delivery, including expanded eligibility guidance, pre-camp learning resources, enhanced presentation of …

Moodify: A Mood-Based Music Recommendation System, Meghana Kagitha

Theses and Dissertations

Music has long been recognised as a powerful tool for emotional regulation, yet existing music streaming platforms often fail to align song recommendations with a user's current emotional state. Moodify is a mood-based music recommendation system designed to bridge this gap by delivering personalised playlists that reflect how a user feels in real time.

This project presents the design, development, and evaluation of Moodify, a mobile application that leverages the Circumplex Model of Emotion to capture user mood through an intuitive two-dimensional valence-arousal interface. Rather than relying on text input or manual search, users plot their emotional state directly onto …

Adaptive Artificial Potential Field Guidance And Control For Autonomous Docking With Uncooperative And Unknown Spacecraft, Steven Holmberg

Theses and Dissertations

The increasing demand for on-orbit servicing (OOS), active debris removal (ADR), and space domain awareness (SDA) missions has increased the need for autonomous spacecraft rendezvous and proximity operations (RPO) with uncooperative and unknown targets. Traditional guidance and control methods are typically designed for cooperative systems with known geometry and state information. This work builds on previous research to develop and evaluate an artificial potential field (APF)-based control framework capable of autonomous operation with minimal prior target knowledge and applicability to both relatively static and tumbling spacecraft.

The proposed APF formulation incorporates established safety constructs from cooperative docking systems, including an …

Ionospheric Plasma Electron Density Measurement And Theory Using Impedance Probe Techniques, Justin Wellington

All Graduate Theses and Dissertations, Fall 2023 to Present

The ionosphere plays a critical role in how radio frequency (RF) signals, like those used in Global Position System (GPS) satellite communications, travel through space. Disturbances in the ionosphere, such as equatorial plasma bubbles (EPB), scatter these signals and cause communication dropouts or navigational errors. To study these conditions, spacecraft use instruments that measure the surrounding plasma directly. One of these instruments is an impedance probe, which applies a small electrical signal to a sensor and determines electron density from the measured impedance.

This thesis improves the modeling and interpretation of impedance probe measurements. A numerical method is developed that …

Examining Motivations And Perceptions In Secondary Technology And Engineering Education: A Gendered Analysis Using The Fit-Choice Scale, Abigail Villanueva

All Graduate Theses and Dissertations, Fall 2023 to Present

This study examined why individuals choose to become secondary technology and engineering education (TEE) teachers and whether motivations differ between men and women. TEE programs help prepare students for careers in science, technology, engineering, and math (STEM), yet schools face teacher shortages and low female representation in the field. Understanding what draws people to this profession can support better recruitment and retention efforts. Sixty-six current TEE teachers completed a survey about the factors that influenced their decision to teach. Overall, the strongest motivations were a personal interest in teaching, enjoyment of working with young people, and the desire to make …

Developing Fragility Curves For Steel Special Moment-Resisting Frames In Utah, Olivia P. Murphy

All Graduate Theses and Dissertations, Fall 2023 to Present

Major seismic events along the Wasatch Fault represent a serious threat to Utah's residents and built environment. Engineers currently rely on a statistical approach that calculates earthquake ground shaking based on probabilities of various events occurring over extended time periods. This method informs how strong new buildings must be constructed. However, many structural engineering professionals in Utah worry that this probability-based approach may significantly underestimate the actual ground shaking compared to an alternative method that examines the largest possible earthquake a fault can generate. The substantial differences between the two analytical approaches raise fundamental concerns about whether existing construction standards …

Development Of A Novel Method For Simultaneously Testing Multiple Specimens To Evaluate Tension-Tension Fatigue Life, Mehedi Hasan Mahfuz

All Graduate Theses and Dissertations, Fall 2023 to Present

The aim of this study is to develop a novel method for rapidly evaluating the tension–tension fatigue life of metals. Fatigue failure, which occurs when materials gradually weaken and fracture under repeated loading, is a critical concern in designing safe and reliable structures such as airplanes, cars, and bridges. Traditional fatigue testing methods are slow, costly, and typically limited to one specimen at a time. To address this, a high-throughput testing method was developed that allows multiple small-scale specimens to be tested simultaneously while following international testing standards. Using stainless steel sub-sized specimens scaled at 1:5 relative to the ASTM …

Reconfigurable Antennas Using Varactors On A Planar Parasitic Layer And Pin Diodes On A Dome Parasitic Layer, Andrew J. Hendricks

All Graduate Theses and Dissertations, Fall 2023 to Present

This research explores two types of reconfigurable, steerable antennas. These antennas change their beam direction based on electric input signals. The antennas have a layer that overlays the main antenna circuit board. The layer has small copper rectangles (pixels) that may be connected using either varactor diodes (which behave as voltage-controlled capacitors) or PIN diodes (electronic switches). The first antenna can steer in the xz-plane in any direction within about 23° from boresight (straight up from the antenna) and in the yz-plane to about 29° from boresight. The antenna uses varactor diodes on a planar layer. The second …

Exploring Cognitive Load Theory In The Post-Secondary Engineering Classroom, Gabriel Q. Van Dyke

All Graduate Theses and Dissertations, Fall 2023 to Present

Engineering programs often emphasize subject-matter expertise over pedagogical training, which can leave students struggling with course demands and contribute to retention challenges. This study applied Cognitive Load Theory (CLT) to examine how undergraduate engineering students experience the cognitive demands of their coursework compared to non-engineering classes. Using a sequential explanatory mixed methods design, cognitive load surveys were followed by interviews to address two research questions: (1) What are the differences in intrinsic and extraneous cognitive load levels between engineering courses and non-engineering courses taken concurrently by undergraduate engineering students? (2) How do engineering students perceive the unique challenges or benefits …

Aerodynamic Parameter Estimation For A Scaled F-16: A Simulation-Based Sensitivity Analysis, Kathle C. Tischner

All Graduate Theses and Dissertations, Fall 2023 to Present

The physical motion of an aircraft is determined by the resulting forces and moments acting on the aircraft. These forces and moments can be defined as a mathematical equation where the control deflections, rotation rates, and orientation of the aircraft are multiplied by individual constants and summed together to define the entire force or moment. This method results in a highly accurate model that defines the motion of the aircraft at low angles of attack and sideslip. Initial calculations of the aerodynamic model are created based on analytical estimations based on the physical properties of the aircraft. Additional refinement of …

The Effect Of Hydroflow Devices On Calcium Carbonate Buildup., Holton Shults

Master of Engineering Theses

Water containing high levels of dissolved minerals, mainly calcium and magnesium, is known as hard water, which is commonly found across the world due to calcium’s abundance in the earth’s crust. Hard water can lead to calcium carbonate buildup (also referred to as limescale) that reduces flow, clogs pipes, and lowers heat exchanger efficiency, all of which can drive up costs. This work evaluated two commercially available chemical-free treatment devices from HydroFLOW USA LLC, called the Pearl Plus and s38 devices. These electromagnetic devices are designed to alter calcium carbonate crystal structure, potentially reducing the amount of calcium …

An Experimental Study On Turbine-Based Energy Harvesters For Thermal Underwater Gliders, Stephen Edward Coster

Theses and Dissertations

Buoyancy-driven underwater gliders have been optimized for long-duration missions primarily for continual monitoring of the ocean’s water column. However, longer missions and higher-powered sensors have increased the energy requirements of gliders. While current solutions aim to increase battery capacity, the development of energy-harvesting systems (EHMs) could greatly improve mission capabilities in both ability and duration. This thesis discusses the experimental testing of an underwater glider with an EHM as detailed in the theoretical study, “Development of a Turbine-Based Ocean Thermal Energy Harvesting Mechanism Applied to the Underwater Glider” by Hongbo Hou, PhD. The rear-mounted turbine captures energy using the kinetic …

A New Approach To Generate Combinatorial Patterns In Logical Analysis Of Data And Its Application To Predict College Retention, Salihah Ahmed E. Jaafari

Theses and Dissertations

Student retention and degree completion remain central challenges for higher-education institutions, with significant implications for student success, institutional effectiveness, and public accountability. While advances in predictive analytics have enabled earlier identification of students at risk of withdrawal, many commonly used machine learning approaches suffer from limited interpretability, constraining their practical usefulness for advising, intervention, and policy decision making. This dissertation addresses the problem of predicting student persistence by developing and evaluating optimization based, interpretable classification models within the Logical Analysis of Data (LAD) framework. Building on existing LAD formulations, this research introduces two novel pattern generation models, the Best Term …

Manned Exploration Of Satellites Of The Outer Planets: An Analysis Of Current Technologies And A Discussion Of Advancements Required, Joshua Carson Meador

Theses and Dissertations

The Solar System’s outer planets have many satellites, some of which are known to be the most likely places to find extraterrestrial life in our celestial backyard. Multiple scientific missions have been sent to glean information from these satellites, yet the possibility of a manned expedition has long been exclusive to science fiction stories. This paper intends to collect and analyze the current state of space travel technology to explore the feasibility of such a mission with modern technology and to discuss which future advancements should be the focal point for making such missions a reality. To begin, data on …

Aircraft Fault Detection Via Weight And Bias Analysis Of A Custom First Neural Network Layer, George Harrison Chen

Theses and Dissertations

Fault detection in aircraft is traditionally handled through redundant hardware and comparison algorithms to detect failures. Alternatives like model-based residual generation and data-driven approaches such as supervised fault classification and unsupervised anomaly detection have been explored, but they suffer from practical limitations; model-based methods require accurate system models, and data-driven methods have large constraints on the data limiting scalability and adaptability. This work presents a purely data-driven neural network architecture featuring a custom first layer designed for real-time fault detection where the weights and biases of this layer are used to detect faults. The network requires zero supervision and complements …

Hdra-Fusion: Hybrid Detection With Routed Architecture For Manipulation-Aware Ai Face Forgery Detection, Omar Ebeid

Theses and Dissertations

With the rapid advancements in artificial intelligence-based image generation and manipulation tools, it is extremely difficult to detect if an image is genuine or artificially crafted. Despite extensive research in this area, existing image detection systems suffer from three major problems: suboptimal cross-dataset generalization due to shortcut learning of dataset-specific patterns, unreliable probability estimates due to domain shift, particularly in cross-manipulation evaluation settings, and an inability to detect images manipulated by multiple types of manipulations within a single detection framework. To address these limitations, we propose HDRA-Fusion (Hybrid Detection with Routed Architecture), a framework built on the conclusion that different …

Design And Simulation Of Anti-Resonant Hollow-Core Fiber For Sensing Applications, Pravallika Kante

Theses and Dissertations

This thesis presents the design and simulation of an 8-tube single-ring anti-resonant hollow-core fiber for sensing applications, with particular emphasis on methane gas detection at the fundamental absorption wavelength of 3.3 µm. Conventional solid-core silica optical fibers exhibit strong multi-phonon material absorption beyond 2.5 µm, rendering them fundamentally unsuitable for efficient light guidance and direct gas sensing at mid-infrared wavelengths. Anti-resonant hollow-core fibers overcome this limitation by guiding light predominantly through an air-filled hollow core via the anti-resonant reflecting optical waveguide mechanism, in which the thin silica glass walls of the cladding tubes act as Fabry-Pérot etalons that confine the …

Measurements And Scaling Of Ion Propulsion Impulse During Driven Magnetic Reconnection, Fatima Ebrahimi, Nicholas A. O'Gorman, Kush Maheshwari, Jongsoo Yoo, Alexandre Sainterme, Hantao Ji

Faculty Publications

Impulse scaling during magnetic reconnection, the magnetic energy conversion to kinetic energy, via direct Mach probe measurements in Magnetic Reconnection Experiment is examined. Ion exhaust velocity and impulse scalings with reconnecting magnetic field during the push phase of driven reconnection are presented. The outflows and impulse measurements are compared with global MHD simulations. Both measurements and simulations reveal a favorable scaling, greater than linear, of impulse with reconnecting field. These scaling results establish that magnetic reconnection could be utilized for plasma propulsion.

Increasing The Prediction Accuracy Of Plant Oil Production Processes Through Adjusting The Parameters Of Machine Learning Models, Umidjon Ruziev, M.K. Shodiev, A.T. Rajabov

Chemical Technology, Control and Management

Vegetable oil production is characterized by high variability in output indicators due to nonlinear interactions between raw material parameters, equipment modes, and heat and mass transfer conditions. Existing approaches to applying machine learning in this field, as a rule, do not account for the impact of hyperparameter adjustments on forecasting quality across specific technological stages. The article presents a systematic methodology for adjusting model parameters (Ridge regression, SVR, GBM, LSTM) applied to three key tasks: predicting residual oil content in oil cake, color index during bleaching, and free fatty acid content during deodorization. In a set of 1000 observations, including …

Reliability Analysis Of Separator Control Systems, D.P. Muxitdinov, O.U. Sattarov, M.Sh. Nematov

Chemical Technology, Control and Management

This article aims to enhance the reliability, efficiency, and diagnostic capabilities of gas-liquid separators operating in hazardous technological processes. In the study, the separator is considered as a critical functional unit of an industrial system and is analyzed through structural and functional decomposition. The main operating parameters of the separator, including pressure drop (ΔP), separation efficiency and operational state are described on the basis of a mathematical model. In addition, a state model is developed for normal operation, foaming, liquid droplet carryover with the gas flow, and failure conditions. Emphasis is placed on diagnostic and monitoring issues, …

Data-Driven Neuro-Fuzzy Modeling And Rule Optimization For Intelligent Prediction Of Bioreactor Dynamics, Kamala Najaf Mammadzada

Chemical Technology, Control and Management

Modeling wastewater bioreactors is a challenging problem in environmental engineering because the processes are constantly changing and the microorganisms do not behave in a linear or predictable way. This makes it difficult to predict and control the system behavior. This research investigates three artificial intelligence approaches for modeling wastewater bioreactors: the Mamdani Fuzzy Inference System (FIS), the Adaptive Neuro-Fuzzy Inference System (ANFIS), and clustering-based fuzzy models. These models help us predict what is happening in the bioreactors. For instance they help us predict how the amount of substances in the water is changing over time like dS₀/dt dSs/dt …

Consistency-Based Computing Of Fuzzy Eigenvalues And Fuzzy Eigenvectors: Method And Application, Kamala. R. Aliyeva Prof., Nihad Mehdiyev, Shamil Mehdi

Chemical Technology, Control and Management

The computation of eigenvalues and eigenvectors under uncertainty is a fundamental problem in fuzzy linear algebra and decision analysis. When matrix elements are represented by fuzzy numbers, classical spectral methods cannot be directly applied due to nonlinearity, ambiguity in ordering, and the propagation of uncertainty. Moreover, in many practical applications, particularly those involving pairwise comparison matrices, the reliability of eigenvalue-based results strongly depends on the consistency of the underlying data. This paper proposes a consistency-based framework for computing fuzzy eigenvalues and fuzzy eigenvectors that explicitly integrates consistency analysis into the spectral derivation process. The proposed method preserves the fuzzy structure …

Regular Synthesis Algorithms Of Control Devices In Nonlinear Control Systems, Husan Zakirovich Igamberdiyev, Iskandar Yusupovich Abdurakhmanov, Uktam Farkhodovich Mamirov

Chemical Technology, Control and Management

This paper examines the development of regularized algorithms for synthesizing control devices in control systems for polynomial objects, described by multidimensional Volterra functional series. The synthesis problem is solved using a two-stage procedure. In the first stage, the optimization problem is initially solved for an open-loop system. The second stage involves determining the parameters of the control device, i.e., its impulse response functions, by using the relationship between the characteristics of the open-loop and closed-loop systems. Regular algorithms are presented for finding the impulse response functions of the control device based on methods for regularizing the solution of operator equations …