Digital Commons Network^™

Reinforcement Learning-Based Optimal Control Of Uncertain Nonlinear Systems, Miguel Garcia, Wenjie Dong

Electrical and Computer Engineering Faculty Publications

This paper considers the optimal control of a second-order nonlinear system with unknown dynamics. A new reinforcement learning based approach is proposed with the aid of direct adaptive control. By the new approach actor-critic reinforcement learning algorithms are proposed with three neural network approximation. Simulation results are presented to show the effectiveness of the proposed algorithms.

United States Department Of Defense Response To The Office Of Science And Technology Policy Memo, 2022: Public Access Plan (December 2024)

Copyright, Fair Use, Scholarly Communication, etc.

DOD response to OSTP memo, 2022: Public Access Plan (December 2024)

Exploring The Capabilities Of Classifier-Free Guidance In Recommendation Tasks, Noah Buchanan

Graduate Theses and Dissertations

This thesis addresses the problem of recommending items to users based on their ratings of items through a diffusion recommender system. Regular recommender systems are already capable of efficient recommendation through conventional methods such as collaborative or content-based filtering. Diffusion is a new type of generative AI that aims to improve our previous AI's shortcomings in the generative domain, like Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). We use diffusion to create a recommender system that mirrors the sequence users take when browsing and rating items. The current methods of recommendation with diffusion do not use the new innovation …

Ohmic Contacts For Fabrication Of Sic Cmos Devices, Anthony Di Mauro

Graduate Theses and Dissertations

Today’s world of electronics is dominated by semiconductor devices which utilize silicon as their substrate material. Though, silicon is not ideal for semiconductor devices in high-voltage or high-temperature applications. Additionally, the efficiency of silicon devices becomes drastically reduced in nonideal operating conditions. Therefore, finding alternatives to silicon?based devices has been a topic for decades now. A few great candidates to replace silicon devices for said applications include Silicon Carbide (SiC), Gallium Nitride (GaN), and Aluminum Arsenide (AlAs). SiC has grown its reputation as the best candidate, when compared to other potential alternatives, due to its wide bandgap, high operating frequency, …

A Volumetric Model Of Ree And Other Critical Element-Bearing Underclay Deposits In The Eckley Mine Area, Luzerne County, Pennsylvania, Harrison Spiller

Graduate Theses and Dissertations

The Eastern Middle Anthracite Field in southern Luzerne County, Pennsylvania was investigated for potential quantities of critical minerals, including rare earth-bearing minerals (REE) present in underclay deposits associated with coal measures of an existing anthracite coal mine. This work is built on Department of Energy/National Energy Technology Laboratory (DOE/ NETL) 2016 work on samples from the Eckley Mine near Hazelton, Pa. which discovered elevated contents of some critical minerals in core from a single wellbore. This thesis reports on new and additional information collected from that area through geological field work, detailed conventional core descriptions, stratigraphic cross sections, and spectral …

Comparing And Evaluating Models Of Tile-Assembly Using Intrinsic Simulation, Daniel Hader

Graduate Theses and Dissertations

Tile-assembly studies abstract models of computation inspired by advancements in the emerging field of DNA-nanotechnology, where synthetic strands of DNA are used as building blocks for microscopic structures. These DNA strands can be made to combine into structural units with selectively sticky sides that abstractly resemble Wang tiles. However, unlike Wang tiles, an assembly process is modeled where tiles combine one-by-one to form larger assemblies according to matching rules based on their sticky sides. While in practice, these tile-assembly models have seen use in designing DNA nano-structures, the mathematical study of their theory has revealed an exciting interplay between geometric …

Synthesis Of Chemical Fuels And Feedstocks From Co2 For Extraterrestrial Applications, Samuel Keith Conlin

Graduate Theses and Dissertations

The reduction of CO₂ into products for either the storage of renewable electricity or to act as a source of renewable feedstock for industry, is not economically feasible given the current costs of renewable energy. Significant amounts of work have gone into attempting to optimize both electrochemical and nonthermal plasma-based CO₂ reduction systems in an attempt to reduce side reactions and improve energy efficiency in order to meet cost feasibility targets. These techniques can also be adapted for In-Situ Resource Utilization (ISRU) contexts, which are far less sensitive to the cost of renewable energy yet have more strenuous …

Design And Optimization Of Matrix Core Transformer For High Power Bidirectional Isolated Dc/Dc Converter, Zhe Zhao

Graduate Theses and Dissertations

Thanks to the advancement of semiconductor technology, the silicon carbide (SiC) devices with high voltage and power capability are developed and widely used in several industry applications, e.g., gird-connected photovoltaic (PV) system, data center power supply, and electrical vehicle (EV) charging station. After the concept of solid-state transformer (SST) was proposed as an important solution to the medium voltage (MV) power conversion systems, this bidirectional isolated DC/DC converter has attracted much attention in academia and industry. One of the main advantages of SST is to improve both the power density and efficiency of the power conversion system by replacing the …

Real-Time Simulation And Workforce Development For Industrial Control Systems With Troy: Testbed For Resilient Operational Systems, Gideon Henry Sutterfield

Graduate Theses and Dissertations

Digital automation for critical infrastructure (CI) is largely supported by industrial control systems (ICS) and operational technology (OT). The increase in digital automation as time progresses correlates with a rise in targeted cyberattacks at these vulnerable yet precious assets. TROY: Testbed for Resilient Operational sYstems, a highly scalable hybrid IT & OT utilizing virtual machines and a Typhoon-HIL real-time simulation, contributes to cybersecurity for CI by serving as a research and workforce development platform. By using Typhoon-HIL to simulate ICS, the platform can be used to replicate a realistic network environment for a myriad of research functions. The system uses …

Towards Comprehensive And Interpretable Video Understanding, Khoa Vo

Graduate Theses and Dissertations

Video understanding is a critical domain in computer vision, focusing on analysis of sequential visual data to extract meaningful spatiotemporal information for tasks such as action recognition, video captioning, video retrieval, and temporal action localization, etc. Despite significant advancements with spatio-temporal convolutional neural networks and attention-based video models, current methods face limitations, including inadequate representation of main actors, lack of fine-grained modeling of relevant objects, and limited interpretability.
This thesis addresses these challenges by proposing novel approaches that enhance video understanding through modeling interactions among entities (actors and objects) and between entities and the environment, while improving interpretability in the …

Multimodal Spectroscopy To Study Tumor Microenvironmental Changes In Vivo, April Mordi

Graduate Theses and Dissertations

Every year there are millions of new cancer diagnoses and deaths worldwide. While great strides have been made in technologies and drugs for cancer treatment, there is still a need to understand tumor response to therapy as many patients still endure treatment failure after completing their treatment regimen. Current clinical imaging techniques for detecting response to therapy are utilized weeks to months after the course of treatment, and present limitations to measuring response during treatment. Optical spectroscopy techniques can help meet this need to determine the response of tumors to treatment as it allows for near real-time in vivo characterization …

An Automated Design Flow From Synchronous Rtl To Optimized Layout Using Commercial Eda Tools For Multi-Threshold Null Convention Logic Circuits, Cole Harrington Sherrill

Graduate Theses and Dissertations

This work presents the first automated design flow from synchronous RTL to highly optimized layout for Multi-Threshold NULL Convention Logic (MTNCL) circuits. The developed synthesis flow overcomes many of the drawbacks of existing attempts and leverages the advanced optimization features provided by modern synthesis tools. The remaining timing race conditions native to the MTNCL architecture have been identified and thoroughly explored. Two sets of novel timing constraints were devised: the first responds to these race conditions, yielding highly reliable MTNCL circuits; the second directly targets the critical paths within MTNCL circuits, allowing the designer to optimize the target circuit for …

Deep Learning Framework For Inverse Problems In Computational Imaging: A Lensless Imaging And Super-Resolution Magnetic Resonance Imaging Case, Arpan Poudel

Graduate Theses and Dissertations

Inverse problems in computer vision involve reconstructing an original scene or image from incomplete, noisy, or indirect measurements. These problems are critical in tasks such as image denoising, deblurring, super-resolution, and lensless imaging, where the goal is to recover high-quality images from degraded or partial measurements. This thesis introduces novel approaches to address two specific real-world inverse problems: (1) image super-resolution in medical imaging and (2) lensless image reconstruction . In the first part of this work, we tackle the problem of image super-resolution in Magnetic Resonance Imaging (MRI). High-resolution MRI scans are often limited by hardware constraints, patient movement, …

Addressing Cybersecurity Data & Workforce Scarcity With Troy: Testbed For Resilient Operational Systems, Henry Oliver Schmidt

Graduate Theses and Dissertations

Machine learning has seen an explosive rise in the past decade. Companies, organizations, and governments are racing to pursue the advancements and insight provided by machine learning powered tools. However, to get effective and meaningful insights from machine learning models a significant amount of detailed data is required to train them. This poses a problem in fields where data is not openly available, such as cybersecurity. Entities are often unwilling to give out network or system data to the public for machine learning and cybersecurity research since that data can contain sensitive or proprietary information. The risk simply outweighs the …

Enhancing Smart Grid Security And Resilience Using Programmable Networks, Zheng Hu

Graduate Theses and Dissertations

The security and resilience of smart grids are essential to ensuring reliable and efficient energy distribution, especially as these cyber-physical systems grow more interconnected and complex. Supervisory Control and Data Acquisition (SCADA) systems play a critical role in smart grid operations by enabling essential infrastructure control and real-time monitoring. However, SCADA systems are highly vulnerable to modern cyber threats, which target weaknesses in industrial protocols and real-time data requirements.

This dissertation investigates the potential of programmable network technologies, with a focus on P4 (Programming Protocol-independent Packet Processors) switch, to deliver adaptable, in-network security solutions tailored to the needs of smart …

Employee Development And Employee Resilience In The Post-Covid-19 Workplace: A Quantitative Study Of High School Educators, Amy Keiser Maffei

Graduate Theses and Dissertations

The problem addressed by this research is the need for protective factors to support teacher resilience. Organizations that fail to develop employee resilience risk failing to enjoy the positive outcomes associated with it. Research-based methods to improve resilience may benefit organizations, including school districts. The purpose of this study was to examine the relationship between employee development provided by a school district and the resilience of its high school teachers in the post-Covid-19, in-person workplace. Conservation of Resources theory served as the framework to guide the research. Study participants completed a questionnaire with Likert-style response options, with items to assess …

Modeling, Synthesis, And Experimental Characterization Of Rhenium Disulfide For Optoelectronic Devices, Solomon Opeyami Ojo

Graduate Theses and Dissertations

Two-dimensional (2D) transition metal dichalcogenides (TMDs) have garnered considerable interest for their potential in optoelectronics and photonics owing to their remarkable combination of electronic, optical, and mechanical properties. These characteristics distinguish them from other 2D materials, including graphene, making them particularly valuable for next-generation technologies. This dissertation focuses on ReS_₂, a 2D TMD with a unique anisotropic 1T distorted crystal structure. The research aims to elucidate its fundamental properties through a combination of theoretical modeling, material synthesis, and experimental characterization techniques, with the goal of optimizing ReS_₂ for device applications. A theoretical investigation utilizing Density Functional Theory …

Intersectionality And Career Persistence Of African American Women In Cybersecurity Careers: A Narrative Inquiry, Monica Marquita Jones Prewitt

Graduate Theses and Dissertations

The purpose of this narrative inquiry is to examine the experiences of African American women working in cybersecurity, a male-dominated field. An intersectional lens will be used in the study to provide insight into their positionality as women of color in a male-dominated career field. The study will examine the stories of the women who persisted in the field and the existing influences or interventions that supported their retention. This pre-registered study will provide the framework for this study to be completed at the University of Arkansas. The researcher will use a descriptive phenomenological approach and semi-structured interviews to understand …

Two-Photon Imaging For Characterizing Tumor Microenvironmental Changes In Non-Small Cell Lung Cancer Associated With Metastatic Recurrence, Paola Monterroso Diaz

Graduate Theses and Dissertations

Lung cancer remains the leading cause of cancer deaths, comprising nearly 25% of all cancer deaths (Sung et al., 2021a). The five-year survival rate of patients with non-small cell lung carcinoma (NSCLC) remains significantly low given that over half present with locally advanced or metastatic disease at time of diagnosis, and experience tumor recurrence following therapeutic intervention (Tamura et al., 2015; Uramoto & Tanaka, 2014). Current evaluation techniques to assess treatment response are lacking, given they are implemented several weeks after treatment completion and are solely based on anatomical changes in tumor size, forgoing other criteria such as functional or …

Causal Discovery In Time Series Data Using Deep Learning Techniques, Saima Zahin Farhana Absar

Graduate Theses and Dissertations

Causal structure learning from observational data has been an active field of research over the past decades. In the literature, different algorithms and models have been proposed, such as constrained-based methods and score-based methods including the emerging deep learning-based methods. However, most of the approaches apply to static and non-dynamic data only. In many applications, the data is temporal. For example, monitoring systems, weather surveillance systems, and stock data, to name but a few. Incorporating temporal information is an important extension of the causal discovery field. With the growth of observational data these days, the discovery of causal relationships from …

Investigation Of Conductive Die-Top Thermal Capacitors During Short Circuit Operation Of Silicon Carbide Devices, Youssef Abotaleb

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Silicon carbide (SiC) power devices have garnered significant attention in recent years due to their superior thermal and electrical properties compared to traditional silicon devices. However, SiC power devices suffer from severe reliability issues arising from their mechanical properties. This is because the Young's modulus of SiC is about three times larger than that of silicon, which correspondingly raises the mechanical stresses acting on the bonding structure, often leading to device failure under power shock events.

Traditional packaging materials and designs tend to constrain SiC performance, as hot-spot temperature resulting from a power shock is one of the key factors …

Identifying Challenges Faced By Small And Medium Enterprises (Smes) In The Middle East And North Africa (Mena) Region Through Total Quality Management, Mohamad Atef

Theses and Dissertations

Recently, Small and Medium Enterprises (SMEs) have become recognized as an important driver of global economic growth and innovation. This phenomenon is particularly evident in the MENA region, where small and medium-sized enterprises (SMEs) make a significant contribution to the businesses. SMEs offer significant benefits in terms of job creation, revenue generation, and fostering economic diversity. Although SMEs have a vital contribution in the economy of the MENA region, SMEs face many challenges that hinder their development and long-term viability. Focusing on these challenges is very important for fostering a vibrant and resilient economic environment. The objective of this thesis …

Triadic Temporal-Semantic Alignment For Weakly-Supervised Video Moment Retrieval, Jin Liu, Jialong Xie, Fengyu Zhou, Shengfeng He

Research Collection School Of Computing and Information Systems

Video Moment Retrieval (VMR) aims to identify specific event moments within untrimmed videos based on natural language queries. Existing VMR methods have been criticized for relying heavily on moment annotation bias rather than true multi-modal alignment reasoning. Weakly supervised VMR approaches inherently overcome this issue by training without precise temporal location information. However, they struggle with fine-grained semantic alignment and often yield multiple speculative predictions with prolonged video spans. In this paper, we take a step forward in the context of weakly supervised VMR by proposing a triadic temporalsemantic alignment model. Our proposed approach augments weak supervision by comprehensively addressing …

An Aggregate Matching And Pick-Up Model For Mobility-On-Demand Services, Xinwei Li, Jintao Ke, Hai Yang, Hai Wang, Yaqian Zhou

Research Collection School Of Computing and Information Systems

This paper presents an Aggregate Matching and Pick-up (AMP) model to delineate the matching and pick-up processes in mobility-on-demand (MoD) service markets by explicitly considering the matching mechanisms in terms of matching intervals and matching radii. With passenger demand rate, vehicle fleet size and matching strategies as inputs, the AMP model can well approximate drivers’ idle time and passengers’ waiting time for matching and pick-up by considering batch matching in a stationary state. Properties of the AMP model are then analyzed, including the relationship between passengers’ waiting time and drivers’ idle time, and their changes with market thickness, which is …

Unsupervised Modality Adaptation With Text-To-Image Diffusion Models For Semantic Segmentation, Ruihao Xia, Yu Liang, Peng-Tao Jiang, Hao Zhang, Bo Li, Yang Tang, Pan Zhou

Research Collection School Of Computing and Information Systems

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation hinders their performance and restricts their application in real-world multimodal scenarios. To address this issue, we propose Modality Adaptation with text-toimage Diffusion Models (MADM) for semantic segmentation task which utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model’s cross-modality capabilities. Specifically, MADM comprises two key complementary components to tackle major challenges. First, due to the large modality gap, using one modal data to generate …

3d Snapshot: Invertible Embedding Of 3d Neural Representations In A Single Image, Yuqin Lu, Bailin Deng, Zhixuan Zhong, Tianle Zhang, Yuhui Quan, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

3D neural rendering enables photo-realistic reconstruction of a specific scene by encoding discontinuous inputs into a neural representation. Despite the remarkable rendering results, the storage of network parameters is not transmission-friendly and not extendable to metaverse applications. In this paper, we propose an invertible neural rendering approach that enables generating an interactive 3D model from a single image (i.e., 3D Snapshot). Our idea is to distill a pre-trained neural rendering model (e.g., NeRF) into a visualizable image form that can then be easily inverted back to a neural network. To this end, we first present a neural image distillation method …

Self-Supervised Fine-Tuning For Neural Expert Finding, Budhitama Subagdja, Dan Sanchari, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Expert finding systems allow ones to find individuals who have expertise in specific fields or domains. Traditional expert finding are mostly based on topic modeling or keyword search methods that are limited in their capability to encode contextual knowledge from natural language. To address the limitation, this paper presents Neural Expert Finder (NEF), a novel method that takes a transfer learning approach based on transformer encoder networks to leverage the rich seman-tic and syntactic patterns of language encoded in pre-trained language models (PLMs). We propose a self-supervised learning approach utilizing contrastive training using both positive and automatically generated negative samples …

Long-Tailed Out-Of-Distribution Detection Via Normalized Outlier Distribution Adaptation, Wenjun Miao, Guansong Pang, Jin Zheng, Xiao Bai

Research Collection School Of Computing and Information Systems

Onekeychallenge in Out-of-Distribution (OOD) detection is the absence of groundtruth OOD samples during training. One principled approach to address this issue is to use samples from external datasets as outliers (i.e., pseudo OOD samples) to train OOD detectors. However, we find empirically that the outlier samples often present a distribution shift compared to the true OOD samples, especially in LongTailed Recognition (LTR) scenarios, where ID classes are heavily imbalanced, i.e., the true OOD samples exhibit very different probability distribution to the head and tailed ID classes from the outliers. In this work, we propose a novel approach, namely normalized outlier …

A Report Summarizing Hsc Faculty Participants: Ithaka S+R Coordinated Study Making Ai Generative For Higher Education, Laura J. Hall, Robyn Gleasner

Publications

This report presents findings from the University of New Mexico Health Sciences Center’s (HSC) participation in the ITHAKA S+R study Making AI Generative for Higher Education. Seven faculty members from HSC disciplines including internal medicine, pathology, psychiatry, nursing, radiology, and population health were interviewed to explore their perspectives on generative AI (GenAI) in teaching and learning, research and scholarship, and institutional support. A unique theme of “practice” emerged, reflecting how GenAI is influencing clinical care, bench-to-bedside translation, and the preparation of students for future professional practice. The report highlights faculty experiences, ethical concerns, and support needs, offering insight into how …

Divlog: Log Parsing With Prompt Enhanced In-Context Learning, Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, Pinjia He

Research Collection School Of Computing and Information Systems

Log parsing, which involves log template extraction from semistructured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing …