Digital Commons Network^™

Training Uav Teams With Multi-Agent Reinforcement Learning Towards Fully 3d Autonomous Wildfire Response, Bryce Hopkins

All Theses

As climate-exacerbated wildfires increasingly threaten landscapes and communities, there is an urgent and pressing need for sophisticated fire management technologies. Coordinated teams of Unmanned Aerial Vehicles (UAVs) present a promising solution for detection, assessment, and even incipient-stage suppression – especially when integrated into a multi-layered approach with other recent wildfire management technologies such as geostationary/polar-orbiting satellites and CCTV detection networks. However, there remains significant challenges in developing the necessary sensing, navigation, coordination, and communication subsystems that enable intelligent UAV teams. Further, federal regulations governing UAV deployment and autonomy pose constraints on real-world aerial testing, creating a disconnect between theoretical research …

Time-Domain Line Protection In Presence Of Renewables, Prabin Adhikari

All Dissertations

Inverter based resources (IBRs) are crucial in integrating renewable energy sources into the power grid. However, their unique fault characteristics, significantly different from synchronous generators (SGs), present several challenges for existing line protection schemes at both transmission and distribution levels. These schemes, reliant on distance and directional relays designed in phasor domain, are not well-suited for IBRs. Most published literature addressing this problem concentrates on altering the control design of inverters. However, this approach faces practical limitations. Inverter controls, often proprietary, are not readily accessible to utilities, rendering the control-based solutions impractical for widespread implementation.

To address this challenge, this …

Impacts Of High-Frequency Operation On Magnetics And Performance On Isolated Power Electronic Converter Design, David Arturo Porras Fernandez

Graduate Theses and Dissertations

The pursuit of high-power density and high switching frequency is a central theme in the advancement of power electronic converters. While these parameters offer significant benefits in terms of compactness and performance, they also introduce challenges related to efficiency and thermal management. This doctoral dissertation aims to provides a design framework to analyze the implications of high-frequency operation (> 100 kHz) on magnetics design and performance in power electronic converters, particularly when integrating silicon carbide (SiC) power modules. It examines the advantages and disadvantages of high-frequency operation and delves into its effects on the performance of the converter, focusing on …

Modeling, Optimization, And Characterization For Choke Horn Antennas, Ibrahim Nasser I Alquaydheb

Graduate Theses and Dissertations

This dissertation presents a comprehensive study focusing on the modeling, optimization, and characterization of choke horn antennas (CHAs). An analytical model designed to capture the parameters of CHA and derive the total radiated fields from the choke and waveguide elements is primarily focused on in this work. Compared to the use of simulation software, such as ANSYS HFSS (High Frequency Structure Simulator) or CST Studio, which employs numerical methods to simulate and calculate antenna performance, numerous advantages are offered by the analytical model. Analytical models provide deeper insight into electromagnetic interactions and the principles governing antenna behavior, leading to a …

A Real-Time Iot-Based Data Acquisition And Monitoring System For Photovoltaic Applications, Adam Barbosa, Hamza Mubarak, Fazel Mohammadi, Mohammad J. Sanjari, Mehrdad Saif

Electrical & Computer Engineering and Computer Science Faculty Publications

The transition to low-carbon energy systems, driven by climate change and fossil fuel scarcity, highlights technologies, such as Photovoltaic (PV) technology, for sustainable energy generation. This paper focuses on enhancing the efficiency of PV monitoring systems by leveraging Internet of Things (IoT) technology for accurate and real-time monitoring of essential parameters, such as voltage, current, and output power. Significant gaps in cost-effective and reliable IoT integration for PV monitoring are addressed, with an emphasis on predictive modeling. In this regard, a low-cost real-time IoT-based data acquisition and monitoring system for PV systems, as a proof of concept for future endeavors …

Hardware-Oriented Protection And Acceleration For Machine Learning Application, Antian Wang

All Dissertations

The security of Machine Learning (ML) grows along with the development of high-performance models and expanding application scenarios. Numerous users are benefiting from the convenience brought by transformative ML applications. In the meantime, various attackers are trying to find vulnerabilities within ML deployment service models, thereby undermining the performance of ML and jeopardizing stakeholders’ interests. The dissertation focuses on the two aspects of secure ML applications: acceleration and protection. Homomorphic Encryption (HE) emerges as a widely recognized security primitive suitable for the cloud computing service model, where the computation can be performed over ciphertext without decryption. However, evaluations in the …

Data-Driven Enhanced Energy Management System Applications For Energy Control Centers, Dulip Madurasinghe

All Dissertations

This dissertation explores the pressing needs of modern bulk power system operation and control and delves into enhancements to EMS applications with minimal infrastructure development. The dissertation investigates three main EMS application enhancements. The transmission network topology processing (TNTP) is a foundational application of the EMS. A physics-based hierarchical transmission network topology processing (H-TNTP), including substation configuration identification, to improve efficiency and reliability is proposed. Secondly, a multi-level distributed linear state estimation (D-LSE) approach solely based on PMUs is proposed utilizing H-TNTP as the network modeling tool. The D-LSE can conduct linear state estimation (LSE) at either substation, area or …

Mmwave Tx-Rx Self-Interference Suppression Through A High Impedance Surface Stacked Ebg, Adewale K. Oladeinde, Ehsan Aryafar, Branimir Pejcinovic

Electrical and Computer Engineering Faculty Publications and Presentations

This paper proposes a full-duplex (FD) antenna design with passive self-interference (SI) suppression for the 28 GHz mmWave band. The reduction in SI is achieved through the design of a novel configuration of stacked Electromagnetic Band Gap structures (EBGs), which create a high impedance path to travelling electromagnetic waves between the transmit and receive antenna elements. The EBG is composed of stacked patches on layers 1 and 2 of a four-layer stack-up configuration. We present the design, optimization, and prototyping of unit antenna elements, stacked EBGs, and integration of stacked EBGs with antenna elements. We also evaluate the design through …

Ensemble Machine Learning At The Edge Using The Codec Classifier Structure And Weak Learners Guided By Mutual Information, Aj Beckwith

All Graduate Theses and Dissertations, Fall 2023 to Present

The Codec Classifier is a low-computation, low-memory tree ensemble method that dramatically improves feasibility of image classification on resource-constrained edge devices. It achieves advantages over other tree ensemble methods due the separation of encoder and decoder tasks in the classifier. The encoder partitions feature space, and the decoder labels the regions in the partition. This functional separation of tasks enables the encoder design (partitioning) to be guided by maximizing the mutual information (MI) between class labels and the features (i.e. the encoded representation of the data) without regard to the error performance of the classifier. Experiments show maximizing MI leads …

Thermal Management Of Roadway-Embedded Power Electronics For Electric Vehicle Dynamic Wireless Charging Systems, Conner R. Sabin

All Graduate Theses and Dissertations, Fall 2023 to Present

Electric vehicles (EVs) are gaining popularity worldwide. However, concerns raised by the public about purchasing EVs include the limited availability of charging infrastructure, high costs, and the inconvenience of current charging methods. Dynamic wireless charging systems enable electric vehicles to charge while driving, thereby extending the range of EVs and reducing the necessity for large, expensive batteries. Moreover, these systems can initiate charging automatically without user interaction, enhancing charging convenience.

The ground assembly of existing dynamic wireless charging systems consists of an electromagnetic assembly, power electronics for the transmitter pad, and power electronics for grid connection. Installation of these systems …

Gps-Denied Navigation Using Location Estimation And Texel Image Correction, Nikolas I. Jensen

All Graduate Theses and Dissertations, Fall 2023 to Present

In recent years, the use of small drones, also categorized as small Unmanned Aerial Vehicles (sUAV), has surged. They are used for tasks like surveying land, collecting data from a distance, and performing maneuvers for military operations. These drones are popular because they are affordable, small, easy to use, and can navigate well in complex areas. These factors make them a cheap and quick option for tasks like surveying and surveillance when compared to traditional methods.

This thesis introduces a system that uses algorithms to figure out where the drone is. Typically, this relies on sensors and GPS, but GPS …

Federated Learning In Wireless Networks, Xiang Ma

All Graduate Theses and Dissertations, Fall 2023 to Present

Artificial intelligence (AI) is transitioning from a long development period into reality. Notable instances like AlphaGo, Tesla’s self-driving cars, and the recent innovation of ChatGPT stand as widely recognized exemplars of AI applications. These examples collectively enhance the quality of human life. An increasing number of AI applications are expected to integrate seamlessly into our daily lives, further enriching our experiences.

Although AI has demonstrated remarkable performance, it is accompanied by numerous challenges. At the forefront of AI’s advancement lies machine learning (ML), a cutting-edge technique that acquires knowledge by emulating the human brain’s cognitive processes. Like humans, ML requires …

Anomaly Detection On Wind Turbine Blades Using Aerial Imaging, Image Processing, And Deep Learning, Bridger Kohl Altice

All Graduate Theses and Dissertations, Fall 2023 to Present

In reaction to rising global temperatures and carbon dioxide emissions, many countries are looking to use energy sources other than fossil fuels. One such source of energy is wind energy, which can be harvested by wind turbines. By rotating at high speeds, the blades of these large turbines are able to convert wind energy to kinetic energy, which is then converted to electricity usable by the power grid. Traditional methods for inspecting these turbines for damages are expensive, unsafe, and susceptible to human error. These turbines are so tall and so large that inspectors run the risk of falling from …

Filter Incidence Narrowband Infrared Spectrometer For Space-Based Methane Measurement And Plume Detection, Bruno Mattos

All Graduate Theses and Dissertations, Fall 2023 to Present

Monitoring methane emissions from space is essential for reducing global warming. This dissertation introduces the Filter Incidence Narrowband Infrared Spectrometer (FINIS), a compact, lightweight instrument designed for nanosatellites to accurately measure methane emissions. FINIS uses two innovative imaging spectrometers to capture the Earth's reflected light, focusing on the strongest methane absorption feature at 1666 nm. By using tiled interference filters, each imager collects detailed spectral data, allowing precise methane detection. FINIS has been significantly improved from its prototype to its space-ready version, set to launch on the ACMES CubeSat in late 2025. The new design includes a binocular optical system …

Periodic Information Leakage Fault Detection On A Risc-V Microprocessor, Idris Somoye

Electrical and Computer Engineering ETDs

The execution behavior of a Microprocessor (μP) in the presence of a fault is difficult to predict because of the complex interactions across pipeline stages and between functional units within the architecture. Fault effects are known to not introduce any type of anomaly in the input-output behavior for 10s of thousands to millions of clock cycles. These characteristics increase the difficulty of evaluating μP architectures for resilience to information leakage events, i.e., scenarios where a fault causes sensitive data such as an encryption key to be inadvertently diverted to a primary output channel. This dissertation explores two promising strategies for …

Secondary Electron Yield Of Metals, Alloys, And Metal Oxides From First Principles Based Monte Carlo Simulations, Raul E. Gutierrez

Electrical and Computer Engineering ETDs

Density Functional Theory (DFT) based Monte Carlo (MC) simulations of the Sec-
ondary Electron Yield (SEY) of metals, alloys, and metal oxides are performed to
find material properties that could help reduce or influence the multipactor effect.
In order to accurately model the SEY of materials, knowledge of the frequency- and
momentum-dependent Energy Loss Function (qDepELF) is required. The qDepELF
is difficult to determine from experiment; however, it can be calculated from first
principles. The DFT-MC approach for simulating the secondary electron genera-
tion, propagation, and emission processes is described herein. Material properties,
which are calculated using DFT and used …

Integrated Multi-Omics Analysis Of Cerebrospinal Fluid In Postoperative Delirium, Bridget A. Tripp, Simon T. Dillon, Min Yuan, John M. Asara, Sarinnapha M. Vasunilashorn, Tamara G. Fong, Sharon K. Inouye, Long H. Ngo, Edward R. Marcantonio, Zhongcong Xie, Towia A. Libermann, Hasan H. Otu

Department of Electrical and Computer Engineering: Faculty Publications

Preoperative risk biomarkers for delirium may aid in identifying high-risk patients and developing intervention therapies, which would minimize the health and economic burden of postoperative delirium. Previous studies have typically used single omics approaches to identify such biomarkers. Preoperative cerebrospinal fluid (CSF) from the Healthier Postoperative Recovery study of adults ≥ 63 years old undergoing elective major orthopedic surgery was used in a matched pair delirium case–no delirium control design. We performed metabolomics and lipidomics, which were combined with our previously reported proteomics results on the same samples. Differential expression, clustering, classification, and systems biology analyses were applied to individual …

A New Approach: Ordinal Predictive Maintenance With Ensemble Binary Decomposition (Opmeb), Ozlem Ece Yurek, Derya Birant

Turkish Journal of Electrical Engineering and Computer Sciences

Predictive maintenance (PdM), a fundamental element of modern industrial systems, employs machine learning to monitor equipment conditions, estimate failure probabilities, and optimize maintenance schedules. Its core objective is to enhance equipment reliability, extend lifespan, and minimize costs through data-driven insights by enabling efficient maintenance scheduling, reducing downtime, and optimizing resource allocation. In this paper, we propose a novel ordinal predictive maintenance with ensemble binary decomposition (OPMEB) method for the PdM domain, considering the hierarchical nature of class labels reflecting the machine's health status, including categories like healthy, low risk, moderate risk, and high risk. The proposed OPMEB method was validated …

Enrichment Of Turkish Question Answering Systems Using Knowledge Graphs, Okan Çi̇ftçi̇, Fati̇h Soygazi̇, Selma Teki̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Recent capabilities of large language models (LLMs) have transformed many tasks in Natural Language Processing (NLP), including question answering. The state-of-the-art systems do an excellent job of responding in a relevant, persuasive way but cannot guarantee factuality. Knowledge graphs, representing facts as triplets, can be valuable for avoiding errors and inconsistencies with real-world facts. This work introduces a knowledge graph-based approach to Turkish question answering. The proposed approach aims to develop a methodology capable of drawing inferences from a knowledge graph to answer complex multihop questions. We construct the Beyazperde Movie Knowledge Graph (BPMovieKG) and the Turkish Movie Question Answering …

Detection And Classification Of Unauthorized Use Of Irrigation Motors In Agricultural Irrigation, Önder Ci̇velek, Sedat Görmüş, Hali̇l İbrahi̇m Okumuş, Orhan Gazi̇ Kederoglu

Turkish Journal of Electrical Engineering and Computer Sciences

The decarbonisation of electricity generation requires the real-time monitoring and control of grid components in order to efficiently and timely dispatch demand. This highly automated system, known as the Smart Grid, relies on smart or sensor-equipped distribution network components to optimise energy flow and minimise losses. However, energy theft, a major obstacle to efficient resource utilisation, poses a significant challenge to achieving this goal. This study proposes and evaluates a real-time telemetry and control system designed to mitigate energy theft in agricultural irrigation applications. The system increases energy efficiency by tracking the energy use in agricultural irrigation. The key challenge …

A New Dynamic Classifier Selection Method For Text Classification, İsmai̇l Terzi̇, Alper Kürşat Uysal

Turkish Journal of Electrical Engineering and Computer Sciences

The primary objective of employing multiple classifier systems (MCS) in pattern recognition is to enhance classification accuracy. Dynamic classifier selection (DCS) and dynamic ensemble selection (DES) are two purposeful forms of multiple classifier systems. While DES involves the selection of a classifier set followed by decision combination, DCS opts for the choice of a single competent classifier, eliminating the necessity for classifier combination. As a consequence, DCS methods exhibit superior efficiency in terms of processing time and memory usage compared to DES methods. Moreover, a substantial performance gap exists between the performance of Oracle and both DES and DCS methods. …

A Real-Time Embedded System Designed For Nilm Studies With A Novel Competitive Decision Process Algorithm, Sai̇d Mahmut Çinar, Rasi̇m Doğan, Emre Akarslan

Turkish Journal of Electrical Engineering and Computer Sciences

This paper explores the determination of any load or load combination in a power system at any moment. This process requires measurements at the main electric utility service entry of a house, known as nonintrusive measurement. To accurately identify loads, total harmonic distortion, RMS, third harmonic currents, and power consumption are considered their fingerprints. Based on these fingerprints, an algorithm called the competitive decision process is developed and integrated into an embedded system. This algorithm has a two-level decision mechanism. In the first stage, the winner loads with the highest similarity scores from each feature are determined, and the loads …

Multi-Label Voice Disorder Classification Using Raw Waveforms, Gökay Di̇şken

Turkish Journal of Electrical Engineering and Computer Sciences

Automated voice disorder systems that distinguish pathological voices from healthy ones have been developed with the aid of machine learning methods. Both clinicians and patients can benefit from these systems as they provide many advantages, compared to the invasive techniques. These systems can produce binary (healthy/pathological) or multi-class (healthy/selected pathologies) decisions. However, multiple disorders might exist in an individual’s voice. Multi-label classification should be considered in such cases. By this time, only a single report is available on this topic, where hand-crafted features were used, and a data augmentation technique was utilized to overcome class imbalances. In this study, a …

Network Intrusion Detection Based On Machine Learning Strategies: Performance Comparisons On Imbalanced Wired, Wireless, And Software-Defined Networking (Sdn) Network Traffics, Hi̇lal Hacilar, Zafer Aydin, Vehbi̇ Çağri Güngör

Turkish Journal of Electrical Engineering and Computer Sciences

The rapid growth of computer networks emphasizes the urgency of addressing security issues. Organizations rely on network intrusion detection systems (NIDSs) to protect sensitive data from unauthorized access and theft. These systems analyze network traffic to detect suspicious activities, such as attempted breaches or cyberattacks. However, existing studies lack a thorough assessment of class imbalances and classification performance for different types of network intrusions: wired, wireless, and software-defined networking (SDN). This research aims to fill this gap by examining these networks’ imbalances, feature selection, and binary classification to enhance intrusion detection system efficiency. Various techniques such as SMOTE, ROS, ADASYN, …

Exploration Of Semiconductor Gain Medium, Resonator, Pump, And Frequency Stabilization For Laser Guide Star Applications, Mingyang Zhang

Optical Science and Engineering ETDs

Laser Guide Star (LGS) systems are essential for adaptive optics in ground-based astronomical observation. This dissertation demonstrates the feasibility of semiconductor-based LGS systems using the membrane external-cavity surface-emitting laser (MECSEL) platform, employing multiple quantum wells. Various laser cavity configurations were analyzed through simulations and experiments. The in-well pumping method was explored to reduce the quantum defect and address thermal limitations. Multi-pass pumping schemes were designed with Zemax modeling and demonstrated experimentally. To simplify multi-pass pumping, the hybrid-MECSEL (H-MECSEL) design was introduced. COMSOL modeling studied thermal management and thermal lensing effect.

The H-MECSEL achieved approximately 30 W of output power at …

Embedding Direction Of Arrival And Antenna Beamforming Algorithms On Automated Software Defined Radio Platforms, Adrian J. Lewis

Electrical and Computer Engineering ETDs

Antenna arrays are an essential technology in the modern era in both communications and radar applications. The algorithms used for antenna arrays are beginning to be embedded in smart device applications to enable greater communication abilities. This thesis explores the idea of embedding direction of arrival and beamforming algorithms using a software defined radio platform. Specifically, the Multiple Signal Classification (MuSiC) algorithm and Minimum Variance Distortionless Response (MVDR) algorithm are combined. The combination of similar algorithms has the potential to be used in many internet of things applications to enable more dynamic communication ability.

Bio-Inspired Robotic Framework For Spatiotemporal Analyses In Environmental Monitoring Applications, Maliha Kabir

Electrical Engineering Theses

Frequent fluctuations in the environment's temperature and climate significantly impact our crop fields. Floods and droughts occur in different places in different seasons, which is very unusual and affects the crops' health and productivity. During these calamities, they are also not able to monitor their crop fields. However, if it is possible by providing farmers with information about their fields' conditions like temperature, pressure, and soil moisture, we can help them assess environmental conditions for specific areas. This data can also aid farmers in determining the appropriate amounts of fertilizers and pesticides to apply to their crops and which crops …

On The Surface Topography Of Local Overheating And Plasma Formation Due To Initial Condition Perturbations Sourcing The Electrothermal Instability On High-Current-Density Conductors, Maren Whiting Hatch

Electrical and Computer Engineering ETDs

The electrothermal instability (ETI) is a Joule heating-driven instability that instigates runaway heating on conductors driven to high current density, altering the 3D evolution of the expansion and phase state. Most metals include complex distributions of imperfections (voids, resistive inclusions) which seed ETI. To simplify comparison with modeling and theory, experiments examined growth of ETI from various alloys of stainless steel as well as relatively void/inclusion free, 99.999% pure, diamond-turned, 1 mm-diameter aluminum rods. Aluminum surfaces included a variety of deliberately machined and well-characterized perturbations, including 10-micron-scale quasi-hemispherical voids, or “engineered” defects (ED), and sinusoidal patterns of varying wavelength and …

Pulsed Secondary Electron Yield Measurements Of Metallic And Dielectric Materials Of Interest For High Power Vacuum Electron Devices, Bilal Ahmed Malik

Electrical and Computer Engineering ETDs

Secondary electron emission (SEE) from conductors is thought to play an important role in the initiation of Multipactor breakdown in vacuum electron devices. The SEE of dielectric materials plays a crucial role in numerous scientific and technological applications, including particle accelerators, spacecraft charging, and plasma diagnostics. Additionally, the SEE of an insulator may depend on its electrical stress history. In both cases, SEE strongly depends on any conditioning of the material surface. We present measurements on both conducting and insulating materials of interest in these applications. Measurements are being made in an existing test stand, recently modified to enable measurements …

Authenticated Diagnosing Of Covid-19 Using Deep Learning-Based Ct Image Encryption Approach, Mohamed Attia Abdelgwad, Amira Hassan Abed, Mahmoud Bahloul

Future Computing and Informatics Journal

Researchers are motivated to use artificial intelligence in biometrics, medical imaging encryption, as well as cybersecurity due to its rapid progress. An encryption method for CT scans—which are used to diagnose COVID-19 disease—is proposed in this study. The suggested encryption method creates a connection among an individual's face picture and CT image to increase confidentiality. The simple CT picture is first enhanced with a host image. An encryption key is multiplied by the final result. This key is produced by applying a Convolutional Neural Network (CNN) to recognize characteristics from people's face photographs. Additionally, a straightforward CNN with three convolutional …