Digital Commons Network^™

Developing Deep Learning Methods For Cognitive Impairment Detection Based On Non-Invasive Data, Muath Alsuhaibani

Electronic Theses and Dissertations

Cognitive impairment detection is on the rise to help reduce the burden of healthcare costs on institutions and individuals. Mild Cognitive Impairment (MCI) is an early stage of cognitive decline progressing to Alzheimer’s disease (AD) or AD-related Dementia (ADRD). Detecting the early stages of AD/ADRD is crucial for early interventions among older adults to mitigate cognitive decline over time. However, the current diagnostic methods are often costly and/or invasive, such as MRI and PET scans. Thus, the search for non-invasive and cost-effective screening tools for the early detection of cognitive impairment using speech, language, visual, and motor data is growing. …

Assessing Cascaded Op-Amp And Pre-Current Amplifier Configurations In Transimpedance Amplifier Interfacing Circuits For Nano-Scale Current-Based Sensor Applications, Mohamed Mamdouh, Sameh O. Abdellatif

Electrical Engineering

This study provides a comprehensive analysis of two proposed configurations for current-to-voltage converters tailored for nano-scale current-based sensor applications, focusing on key performance metrics such as linearity, dynamic range, DC noise immunity, and power losses. The evaluation employed frequency-dependent analyses, including transient response, step response, input impedance, and frequency-dependent noise spectra, to compare a cascaded double output configuration with a pre-current amplifier design. The results indicate a trade-off between dynamic range and linearity, with the pre-current amplifier demonstrating a higher dynamic range but lower linearity compared to the cascaded configuration. Additionally, the current amplifier configuration exhibited advantages in power consumption …

Investigating Resilience Of Cyberattack Detection Using Lyapunov-Based Economic Model Predictive Control To Data Poisoning, Helen Durand, Akkarakaran Francis Leonard

Chemical Engineering and Materials Science Faculty Research Publications

Cyberattacks may be performed on process control systems due to their integration of networking and computing with physical systems. Prior work in our group has developed detection strategies for nonlinear systems under sensor, actuator, and combined sensor and actuator attacks which can ensure, under characterizable conditions, that attacks can be detected before they cause safety issues. However, this work did not take into account the potential that an attacker could attempt to provide data to a process that causes an attack to remain undetected but that also is consistent with different process dynamics than those which the process has. This …

Response Of Dynamic Processes With Control Implemented On A Noisy Quantum Computer, Shilpa Narashimhan, Dominic Messina, Henrique Oyama, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

A major challenge to determining the applicability (and potential outperformance over classical computers) of a quantum computer (QC) within chemical manufacturing processes is quantum noise. Computations by a QC are error-prone due to the influence of quantum noise inherent to the hardware. Errors in control inputs may destabilize a chemical process and lead to unsafe conditions for manufacturing personnel and the environment. The response of a process with control implemented on a QC to errors due to noise must be investigated thoroughly. In this work, the impacts of control input errors due to quantum noise on a process are modeled …

Heuristic Strategies For Process Stabilization Using Proportional Control Implemented By A Noisy Quantum Simulator, Keshav Kasturi Rangan, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

Processing and storage demands of industrial processes are causing fields such as optimization, scheduling, and control to assess the effectiveness of quantum devices in their applications. A key objective of control systems is to ensure process safety. This paper focuses on the potential of quantum devices to compute control inputs that maintain system safety despite sources of nondeterminism inherent to currently available quantum devices (quantum noise). In our previous work, we employed a quantum simulator to assess whether a quantum implementation of a proportional (P) control law could stabilize a single-input/single-output system under quantum noise approximated from a real quantum …

Tools To Design Algorithms For Implementing Control Over Quantum Computers, Shilpa Narashimhan, Jihan Abou Halloun, Kip Nieman, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

Quantum computers (QCs) may find future applications within control systems that operate manufacturing processes. For application within control engineering, quantum algorithm development must be led by control engineers. However, control engineers may face challenges in designing quantum algorithms for control engineering problems. In this work, we provide several path-finding studies that leverage engineering tools such as optimization, encryption, and computational "short-cuts" toward making algorithm design for QC easier for control engineers.

Improving High Frequency Absorptive Filters For Quantum Computing, Christopher B. Sutton

Graduate Masters Theses

Coaxial transmission lines in superconducting quantum circuits are subject to infrared radiation (IR) leakage as signals travel from room temperature (≈ 300 K) to low temperature (≈ 10 mK). Current experimental configurations typically include an epoxy based filter on all cables connecting classical devices (pulse generators, VNA, etc.) to the quantum circuit. The epoxy is characterized by its dielectric properties per unit length and acts as an absorber, attenuating IR noise. Historically, such IR filters have been fabricated by the experimentalists who require them, more recently they have become commercially available. This work investigates the performance of filters which were …

Performance Analysis Of Multivariable Control Structures Applied To A Neutral Point Clamped Converter In Pv Systems, Renato Santana Ribeiro Junior, Eubis Pereira Machado, Damásio Fernandes Júnior, Tárcio André Dos Santos Barros, Flavio Bezerra Costa

Michigan Tech Publications

This paper addresses the challenges encountered by grid-connected photovoltaic (PV) systems, including the stochastic behavior of the system, harmonic distortion, and variations in grid impedance. To this end, an in-depth technical and pedagogical analysis of three linear multivariable current control strategies is performed: proportional-integral (PI), proportional-resonant (PR), and deadbeat (DB). The study contributes to theoretical formulations, detailed system modeling, and controller tuning procedures, promoting a comprehensive understanding of their structures and performance. The strategies are investigated and compared in both the rotating ((Formula presented.)) and stationary ((Formula presented.)) reference frames, offering a broad perspective on system behavior under various operating …

Exploring Longitudinal Stability Of Spatiotemporal Sequential Patterns By Means Of Autoencoder Schemes For Eeg Based Personal Identification, Muhammed E. Oztemel

LSU Doctoral Dissertations

Robust personal identification remains a critical and challenging task in the digital era. Electroencephalography (EEG) offers a unique biometric modality that captures individual brain dynamics through complex neural signals. This dissertation proposes autoencoder (AE) based feature extraction and subject identification through these features. EEG recordings are first transformed into topographic maps to represent spatial brain activity. Consecutive topomaps are then concatenated to capture temporal transitions across frames. Convolutional autoencoders (CAEs) are used to learn spatial and temporal patterns, while domain-adaptive AEs are designed to model evoked potential based responses. Additionally, self-attention mechanism is incorporated to enhance feature representation. To analyze …

Performance Analysis Of Pem Fuel Cells Via Puma Optimizer With The Aid Of Practical Verifications, Hossamm Ashraf, Sameh O. Abdellatif, Mahmoud M. Elkholy \, Attia A. El-Fergany

Electrical Engineering

This manuscript presents a novel application of the recently developed Puma Optimizer (PO) for identifying the unknown parameters in Mann’s model, which is widely used for characterizing the behavior of Polymer Electrolyte Membrane Fuel Cells (PEMFCs). The proposed PO-based methodology is rigorously evaluated using three test cases. One test case involves experimental I–V measurements under various operating conditions from a commercial PEMFC stack, the Horizon H-100 (100 W), which was assembled and tested in the laboratory. The other two cases are established benchmark PEMFC systems, the Ballard Mark V 5 kW and BCS 500 W units. Comprehensive statistical analyses over …

Multi-Layered Framework For Llm Hallucination Mitigation In High-Stakes Applications: A Tutorial, Sachin Hiriyanna, Wenbing Zhao

Electrical and Computer Engineering Faculty Publications

Large language models (LLMs) now match or exceed human performance on many open-ended language tasks, yet they continue to produce fluent but incorrect statements, which is a failure mode widely referred to as hallucination. In low-stakes settings this may be tolerable; in regulated or safety-critical domains such as financial services, compliance review, and client decision support, it is not. Motivated by these realities, we develop an integrated mitigation framework that layers complementary controls rather than relying on any single technique. The framework combines structured prompt design, retrieval-augmented generation (RAG) with verifiable evidence sources, and targeted fine-tuning aligned with domain truth …

Techno-Enviro-Economic Approach For Electrification Of Rural And Shrimp Farming Regional Development Of An Isolated Island In Indonesia By Utilizing Hybrid Renewable Energy Systems, Fiqih Akbar Wijaya, Mohammad Akita Indianto

Journal of Materials Exploration and Findings

One of the challenges in developing and archipelagic countries such as Indonesia is maintaining energy demand in rural and isolated areas due to difficulties in electrical distribution. For instance, in areas like Bawean Island, no additional electricity capacity has been introduced in the past year, leading to an unmet potential customer demand. One of the possible options is by utilizing Hybrid Renewable Energy Systems (HRES) that are integrated with existing fossil fuel-based energy systems to support the growing energy demand in the remote island. A case study in Bawean Island is conducted with the projected energy demand covers the energy …

Autonomous Uav Swarm Formation Utilizing Gradient-Driven Contour Mapping For Radiation Source Localization, Edgar Amalyan

UNLV Theses, Dissertations, Professional Papers, and Capstones

This thesis presents a drone swarm for radiation mapping to aid source localization. The Department of Energy advocates employing UAVs for this task, but existing approaches remain inefficient and impractical in real-world scenarios. Three custom drones are built and flight-tested. A control algorithm to follow a contour, a constant-intensity path, is designed using a gradient fit. By knowing the source’s direction, the drone swarm can fly in the optimal trajectory at every step, leaving nothing to assumption. A program is created that implements formation flight and autonomous navigation. It is tested via a software-in-the-loop simulation utilizing radiation sources and detectors …

The Dropbot: Design And Development Of A Custom Drone For Precision Water Drop Penetration Time (Wdpt) Testing, Mugundan Prakash

UNLV Theses, Dissertations, Professional Papers, and Capstones

Assessing the hydrophobic characteristics of soil is vital for understanding soil wettability or soil-water interactions, particularly in post-wildfire environments where water repellency can significantly impact ecosystem recovery, water infiltration, and erosion control. One key metric in soil wettability studies is the Water Drop Penetration Time (WDPT) test, which evaluates the hydrophobicity of soil and guides land treatment strategies. This thesis presents the design and development of DropBot, a custom-built drone platform engineered for the precise delivery and analysis of water droplets in WDPT tests.The DropBot, a custom drone, integrates a lightweight, 3D-printed frame with a self-leveling platform, enabling consistent droplet …

Safe Real-Time Obstacle Detection And Navigation Using Cbf–Clf And Cbf–Pid Control, Nicolas M. Hernandez

McKelvey School of Engineering Graduate Student Theses & Dissertations

Traditional robotic navigation pipelines typically follow a three stage architecture: obstacle detection, path planning, and low-level control for trajectory tracking. While effective in static environments, these methods often introduce latency and lack formal guarantees of safety in dynamic or unplanned for scenarios. Our work addresses these limitations by developing a real-time controller grounded in Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs), unified through a Quadratic Program (QP). We first investigate a hybrid CBF-PID-QP controller on a 1/10 scale car, where the CBF serves as a real-time safety filter, modifying the PID output to prevent constraint violations. While this …

Land8fire: A Complete Study On Wildfire Segmentation Through Comprehensive Review, Human-Annotated Multispectral Dataset, And Extensive Benchmarking, Anh Tran, Minh Tran, Esteban Marti, Jackson Cothren, Chase Rainwater, Sandra Eksioglu, Ngan Le

Electrical Engineering and Computer Science Faculty Publications and Presentations

Early and accurate wildfire detection is critical for minimizing environmental damage and ensuring a timely response. However, existing satellite-based wildfire datasets suffer from limitations such as coarse ground truth, poor spectral coverage, and class imbalance, which hinder progress in developing robust segmentation models. In this paper, we introduce Land8Fire, a new large-scale wildfire segmentation dataset composed of over 20,000 multispectral image patches derived from Landsat 8 and manually annotated for high-quality fire masks. Building on the ActiveFire dataset, Land8Fire improves ground truth reliability and offers predefined splits for consistent benchmarking. We evaluate a range of state-of-the-art convolutional and transformer-based models, …

Accelerating Gnn Inference On Multi-Core Systems, Binglin Ji

McKelvey School of Engineering Graduate Student Theses & Dissertations

Graph Neural Networks (GNNs) are becoming increasingly popular, with their applications expanding across diverse domains. As the scale of graph data continues to grow, including larger numbers of nodes, edges, and higher embedding dimensions, standardized libraries such as DGL and PyG have been developed to facilitate GNN computation. However, with the rapid increase in the number of processor cores and the evolution of multi-core architectures, these libraries often show poor scalability and fail to execute GNN inference efficiently on the latest multi-core systems, particularly those with upwards of a hundred cores. To address this limitation, we present FGI, a Fast …

Method For Target Detection In A High Noise Environment Through Frequency Analysis Using An Event-Based Vision Sensor, Will Johnston, Shannon Young, David Howe, Rachel Oliver, Zachary Theis, Brian Mcreynolds, Michael L. Dexter

Faculty Publications

Event-based vision sensors (EVSs), often referred to as neuromorphic cameras, operate by responding to changes in brightness on a pixel-by-pixel basis. In contrast, traditional framing cameras employ some fixed sampling interval where integrated intensity is read off the entire focal plane at once. Similar to traditional cameras, EVSs can suffer loss of sensitivity through scenes with high intensity and dynamic clutter, reducing the ability to see points of interest through traditional event processing means. This paper describes a method to reduce the negative impacts of these types of EVS clutter and enable more robust target detection through the use of …

A Deep Learning Approach For Semantic Segmentation And Its Application On Ctc., Samir Farag Harb

Electronic Theses and Dissertations

This dissertation explores the modeling and analysis of medical images, focusing on the intricate task of colon segmentation and subsequent 3D reconstruction, which are critical steps in Computed Tomography Colonography (CTC) systems. The primary objective of this research is to develop precise segmentation approaches to enhance the accuracy of colon identification and reconstruction from abdominal CT scans. Three distinct segmentation approaches are proposed and evaluated: a Markov Random Field (MRF)-based approach, a convolutional neural network (CNN)-based deep learning (DL) approach, and a sequential episodic training with dual contrastive learning Approach (G-SET-DCL) that has a flavor of few-shot learning (FSL). To …

A Generalizable And Privacy-Preserving Framework For Anomaly Detection In Heterogeneous Iot Environments, Mahshid Rezakhani

All Theses

With the rapid growth of Internet of Things (IoT) devices across various sectors, detecting anomalies in such systems has become increasingly challenging. IoT environments produce diverse and evolving data streams, often lacking labeled examples, which limits the effectiveness of traditional machine learning models. These models typically require frequent retraining and struggle to adapt to new deployment conditions. This thesis proposes a flexible, privacy-aware framework for anomaly detection in multivariate time series data generated by heterogeneous IoT systems. The approach integrates a long short-term memory variational autoencoder (LSTM-VAE) with contrastive learning and adversarial adaptation, enabling the model to generalize across domains, …

Optimal Distributed Energy Resource Control And Scheduling In A Microgrid Framework, Timothy M. Dodge

All Graduate Theses and Dissertations, Fall 2023 to Present

As we use more renewable energy, such as solar power, and add new devices, such as electric vehicle chargers and battery storage, to our buildings, the management of electricity becomes more complex. These local energy sources and devices can form small "microgrids" that need careful coordination to work efficiently with the main power grid. The system figures out the best times to use, store or charge different devices (such as batteries and EVs) to avoid costly, high electricity demand spikes and help stabilize the main power grid, especially when asked by the utility company. A major part of this work …

Study Of Ai Applications In Biomedical Data Acquisition, Communication, And Analysis: Cest Mri Acceleration And Ecg Transmissions, Adarsha Bhattarai

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

This dissertation investigates the application of artificial intelligence in biomedical data acquisition, communication, and analysis to advance neurological research and to enable the early detection of cardiovascular conditions. Despite significant advances in imaging and physiological modalities, challenges persist. Imaging modalities, such as the chemical exchange saturation transfer magnetic resonance imaging (CEST MRI) technique are challenged by a prolonged data acquisition time and high operational costs. In addition, physiological modalities such as electrocardiogram (ECG) sensors face constraints in providing uninterrupted signal monitoring which is crucial for the timely detection of premature cardiac abnormalities. The primary goal of this work is to …

Low Energy Ion Irradiation Effects In Electronic Devices And Materials, David C. Mccall

All Dissertations

The physics and engineering of ion-solid interactions are governed by the ion beam characteristics (flux, charge, energy) and target(s) in question. Here I present work on two projects related to the extraction of a high flux of low charge state Argon ions from a commercial plasma source and the irradiation of an engineered target, a transistor, with high charge state Argon ions.

An end-Hall ion source that produces a a high current plasma of ions and electrons in a rough vacuum environment is characterized. Using a Langmuir probe and multiple pressure measurements, the ion and electron content of the source …

Secure Control And Trust Evaluation Framework For Autonomous Transportation Systems, Grace Muriithi

All Dissertations

This dissertation advances the cybersecurity of hybrid tracked vehicles (HTVs) and ship power systems (SPSs) by developing innovative cyber-attack models and corresponding defence frameworks. First, we formulate stealthy false-data-injection attacks (FDIAs) on HTV energy-management systems as a partially observable Markov decision process (POMDP) solved via deep reinforcement learning. A novel sniffing-based reward function guides the attacker to covertly degrade battery capacity and energy efficiency, which we evaluate using custom stealth–impact metrics and a sliding-window anomaly detector (Isolation Forest with Dynamic Time Warping). Additionally, we model sophisticated control-layer attacks in HTVs, including reinforcement-learning-optimised replay attacks and denial-of-service (DoS) attacks targeting generator-speed …

Development Of A High-Performance, Cost-Effective Architecture For Real-Time Fourier Transform Analysis On An Efinix Trion Fpga, Luke Cashwell

Honors Theses

This project presents the development of a high-performance, cost-effective, and powerefficient pipelined architecture designed to execute 10,000 Fast Fourier Transforms (FFTs) per second on an Efinix Trion T120 FPGA. Each FFT processes 4096 signed 13-bit elements, facilitating real-time data analysis for a Time-Domain Impedance Probe (TDIP) operating at a maximum data rate of 490 Mbit/s. The algorithm utilizes the built-in multipliers and dual-port memory cells of the FPGA to optimize data storage, transfer, and processing. It achieves this high performance while only using approximately 4% of the Look-Up Tables (LUTs), 7% of the integrated RAM cells, and 15% of the …

Data-Driven Koopman Theory For Transient Stability And Safety Analysis Of Power Systems With Renewable Penetration, Bhagyashree Umathe

All Dissertations

This dissertation presents a novel approach to analyzing and controlling nonlinear systems using the Koopman operator framework and data-driven methods. Nonlinear power systems, characterized by complex behaviors and sensitivity to initial conditions, pose significant challenges for stability and safety assessment, especially during transient events.

The first part of this work focuses on reachability analysis using the spectral properties of the Koopman operator. By leveraging eigenfunctions extracted from sampled trajectory data, the approach computes forward and backward reachable sets efficiently, even in high-dimensional nonlinear systems, without requiring dense state-space sampling. This method is validated through numerical examples, demonstrating its ability to …

Low-Level Memory Attacks On Edge Assisted Robotic Applications, William Arnold

Master of Engineering Theses

This thesis investigates how low-level memory faults can undermine edge-assisted robotic systems that rely on memory optimization. As robots are utilized in real world applications, the ability to operate safely and successfully in mission critical deployment becomes important. To help achieve these goals, developers are increasingly starting to place computation nodes at network edges to meet latency and reliability requirements. Edge nodes, however, are resource-constrained and resources conservation techniques such as Kernel Same-page Merging (KSM) are enabled to deduplicate identical pages across processes or virtual machines. This thesis shows that this optimization technique quietly widens the attack surface and can …

Ev Charging Management In A Real-Time Optimization Framework Considering Operational Constraints, Hilmi Cihan Güldorum, Ayşe Kübra Erenoğlu, İbrahim Şengör, Barry P. Hayes, Ozan Erdinç

Department of Computer Science Publications

The electrification of transportation plays a central role in the decarbonization of energy systems. Although electric vehicles (EVs) are expected to reduce energy related emissions, the increasing demand imposed by large scale EV adoption presents serious challenges for distribution systems (DSs), which were not originally designed to accommodate such loads. This study proposes a mixed integer quadratically constrained programming (MIQCP) framework to optimize the operation of an EV parking lot (EVPL) under DS constraints. The model compares three widely adopted objective functions: minimization of active power loss, charging cost, and uncontrolled charging impact, which is represented by minimizing the total …

Advancing Real-World Implementation Of The Well Optimized Linear Finder (Wolf) High-Speed Atmospheric Turbulence Compensation Method, Timothy Evan Coon

Theses and Dissertations

This dissertation advances the real-world implementation of the Well Optimized Linear Finder (WOLF) method for high-speed Atmospheric Turbulence Compensation (ATC). Atmospheric turbulence introduces phase aberrations into optical wavefronts and degrades image quality in terrestrial imaging systems. Traditional phase diversity methods are computationally intensive and poorly suited to real-time operation. The WOLF method addresses these limitations through a novel, point-wise formulation of the optical transfer function (OTF) as a structured autocorrelation of the generalized pupil function (GPF). This formulation enables the estimation of phase aberrations at individual spatial coordinates with distributed computational complexity.

The research begins by developing a MATLAB-based simulation …

Autoregressive Temporal Modeling For Advanced Tracking-By-Diffusion, Pha Nguyen, Rishi Madhok, Bhiksha Raj, Khoa Luu

Electrical Engineering and Computer Science Faculty Publications and Presentations

Object tracking is a widely studied computer vision task with video and instance analysis applications. While paradigms such as tracking-by-regression,-detection,-attention have advanced the field, generative modeling offers new potential. Although some studies explore the generative process in instance-based understanding tasks, they rely on prediction refinement in the coordinate space rather than the visual domain. Instead, this paper presents Tracking-by-Diffusion, a novel paradigm for object tracking in video, leveraging visual generative models via the perspective of autoregressive models. This paradigm demonstrates broad applicability across point, box, and mask modalities while uniquely enabling textual guidance. We present DIFTracker, a framework that utilizes …