Digital Commons Network^™

Assessment Of Countermovement Jump In Athlete Status And Monitoring, Michael David Delong

Graduate Theses, Dissertations, and Problem Reports (ETD)

Utilizing a CMJ to test athlete physical abilities and training program efficacy is popular, as it is simple, noninvasive, and has significant relations with sport qualities. However, assessments often use discrete outcome measures. This research explored strategy-based measures accounting for eccentric power and time and may explain athlete status more effectively. The research objectives are to analyze the use of the mean power rate of the CMJ to compare athletes' playing ability and its usefulness in monitoring during off-season training. Additionally, power-time curve analysis added location and timing of effects due to fatigue or fitness adaptation. Proper testing and monitoring …

Use Of Thyroid Imaging Reporting And Data Systems (Tirads) Ultrasound In Differential Diagnosis Of Thyroid Nodules, Aya Mohamed Hamed Abdelaal, Ghada M Ahmed Gaballah, Donia Mohamed Sobh

Mansoura Medical Journal

Background: Thyroid nodules refer to masses of abnormally proliferating cells with abnormal tissue stiffness in thyroid. This study aimed to assess diagnostic accuracy of Thyroid Imaging Reporting and Data System in differentiating benign from malignant thyroid nodules.

Methods: This cross-sectional study included forty adult patients with sixty-two thyroid nodules. A 7.5-10 MHz linear array transducer was used to perform imaging protocol. Three-dimensional measurements were done on nodules. All thyroid nodules were  examined using doppler ultrasound. All thyroid nodules were described in terms of composition, echogenicity, margins, shape and echogenic foci.  According to ACR TI-RADS,  the points were given …

Serum Magnesium Level And Carotid Artery Calcification And Stiffness In Dialysis Patients: Single Center Cross-Sectional Study, Kareem Ahmed Elbosaty, Alaa Abd Elaziz Sabry, Gehad Ahmad Saleh, Nehal Atef Elshabrawy

Mansoura Medical Journal

Introduction Vascular calcification is common among end-stage renal disease (ESRD) patients on regular dialysis, either hemodialysis or peritoneal dialysis. Magnesium is suggested to play a role in inhibiting that process. Recently, Mg started to be considered one of the factors that protect against vascular calcification and consequently decrease CVD mortality rate in CKD patients. Many recent studies support that role although the mechanism of that protective effect is not clear. But it is supposed to be a combination of both passive and active mechanisms. The passive one occurs through interference with calcium phosphate deposition and hydroxyapatite inhibition by phosphate binding. …

Modeling Hepa Filter Media Performance And Evaluation Of Filtration Leak Test Success, Daniel M. Abraham, Steven J. Eckels, Shahin N. Amiri

Civil & Environmental Engineering Faculty Publications

This research presents a cost-effective microscale modeling analysis of high-efficiency particulate air (HEPA) filter media. We analyzed leak-free and leaking media with known leak sizes. A three-dimensional fibrous model with non-homogeneous fiber diameters (0.2–2 µm) and a packing density of 7.5% was developed to replicate a HEPA filter sheet (H14) microstructure. The objective was to simulate and analyze the pressure drop and collection efficiency of nanofibrous media for aerosol particles with a diameter of d_p ≤ 0.5 µm. The results were compared to prior experimental and theoretical models, exhibiting a high level of agreement with pressure drop and efficiency …

Revisiting The Life Cycle Of Margalefidinium Polykrikoides Group Iii, Eduardo Pérez-Vega, Kenneth N. Mertens, Pjotr Meyvisch, Margaret R. Mulholland

OES Faculty Publications

Dinoflagellates produce cysts as a strategy to withstand environmental stressors, with nutrient depletion generally considered a key trigger for cyst production. Resting cysts are thick-walled, typically composed of one to several layers, and characterized by a prolonged dormancy period. In contrast, pellicle cysts possess a thin, single wall and exhibit no dormancy or a markedly shorter dormancy than resting cysts of the same species. Margalefidinium polykrikoides produces pellicle and resting cysts, whereas its congener, M. fulvescens, has been shown to produce pumpkin-like structures. Using phase-contrast microscopy, time-lapse microscopy, FlowCam, and attenuated total reflection Fourier transform infrared microspectroscopy (ATR μ-FTIR), …

Microplastics Suppress Copepod Grazing Of The Harmful Algal Bloom-Forming Dinoflagellate, Alexandrium Catenella, Megan Ladds, Christopher Gobler

OES Faculty Publications

While harmful algal blooms (HABs) are prominent occurrences in coastal zones where microplastic concentrations are maximal, the manner in which microplastics may influence food webs and HABs is poorly understood. This study explored how polystyrene microplastics affected copepod grazing of the saxitoxin-synthesizing harmful dinoflagellate, Alexandrium catenella, as well as a non-toxic dinoflagellate, Gymnodinium aureolum. Experiments were performed using multiple densities of microplastics (250 – 10,000 mL^–¹) of differing sizes (4 and 10 µm), as well as multiple densities of microalgae in microplates. The addition of 10 µm microplastics at densities of 1000 – 10,000 beads mL^{– …}

A Unified Automated And Explainable Ai Framework For Drug Discovery, Clinical Diagnostics, And Public Health Data Prediction, Lord Coffie

College of Graduate Studies: Theses & Dissertations

This thesis investigates the development of automated, explainable artificial intelligence systems to improve automated scientific discovery, clinical diagnostic support, and public health decision-making. Three independent yet thematically aligned studies were conducted across cheminformatics, radiology, and population health. Study A introduces an automated and explainable machine learning pipeline for Quantitative Structure–Activity Relationship (QSAR) modeling using RDKit-derived molecular descriptors. The pipeline performs systematic preprocessing, consensus-based feature selection (mutual information, random forest importance, RFECV), and benchmarks six supervised models—Random Forest, XGBoost, Support Vector Machine, Balanced Random Forest, EasyEnsembleClassifier, and a blended meta-ensemble, achieving AUC = 0.90 and accuracy = 0.83, while ensuring interpretability …

Early Icu Physiological Subtyping From Time-Series Data: A Comparative Study Of Feature Complexity, Predictive Performance, And Model Interpretability, Rojeena Khadka

College of Graduate Studies: Theses & Dissertations

Intensive Care Unit (ICU) patients do not follow a single uniform physiological pattern. Patients admitted with the same diagnosis show different clinical trajectories over time making standardized classification and treatment approaches insufficient. The increasing availability of large-scale electronic health records in MIMIC-IV makes it possible to investigate such heterogeneity through data-driven approach that captures how physiology evolves during the early phase of ICU admission. This thesis compares two analytical pipelines designed to identify physiological subtypes from the first 48 hours of ICU time series data. This study then assesses how well these subtypes predict in-hospital mortality. The first approach, referred …

Modeling Accreditation Standards And Evaluation Methods To Inform Strategic Planning In Public Health Education, Debra Rich

College of Graduate Studies: Theses & Dissertations

Public health has long benefited from the relationship between postsecondary education, accreditation, and government employment. Assessment and accreditation are important tools in postsecondary education to ensure fiscal responsibility, professional competencies, and quality assurance. The competency standards implemented in post-secondary education are not under the direct control of the federal government; however, policy amendments aimed at specific accreditation criteria could result in changes to public health curriculum and create eligibility barriers for students who rely on federal financial support. The Central Washington University Public Health program has provided educational support in professional public health for decades, and there is an increased …

Validity Assessment Of Resting Heart Rate Variability From The Garmin Health Snapshot, Kayla M. Porter, Andrew Flatt

Honors College Theses

Purpose: To assess the agreement between the Garmin Forerunner 265 (a commercially available sports watch) and a single-channel electrocardiographic (ECG) chest strap for determining resting heart rate variability (HRV). Secondary aims were to assess the impact of skin tone and body position on measurement accuracy.

Methods: Young adults (n = 30, 57% women) aged 18–39 years without known cardiovascular conditions and without tattooing or scarring on the dorsal left wrist were recruited. HRV was recorded simultaneously using ECG and the Forerunner 265’s optical sensor during Garmin’s 2-minute “Health Snapshot.” Measurements were obtained in three standardized positions: supine, seated, and standing. …

Geovig And Purevig: Geometry-Aware Architectures For Efficient Computer Vision, Omar Ismail

Theses and Dissertations (Comprehensive)

Deploying deep learning models for medical image analysis on mobile devices requires a balance between inference latency, memory footprint, and delineating anatomical boundaries with high accuracy. While Convolutional Neural Networks (CNNs) and mobile Vision Transformers (ViTs) offer efficiency, they often struggle to model the irregular, non-local geometric structures inherent in biological tissues without incurring prohibitive computational costs. In this thesis, we introduce GeoViG (Geometric Vision Graph), an architecture that bridges the gap between efficient grid-based processing and explicit Geometric Deep Learning. GeoViG introduces a novel transition from high-resolution pixel grids to low-resolution dynamic graphs via a SpreadEdgePool operator, a geometry-aware …

Error-Driven Density Control For Compact Gaussian Splatting Under Sparse Supervision, Abdelrhman Elrawy

Theses and Dissertations (Comprehensive)

This thesis studies efficiency and stability challenges in Gaussian-splatting-based reconstruction under sparse supervision. In few-shot novel view synthesis, standard 3D Gaussian Splatting (3DGS) can overfit the limited training views and grow an unnecessarily large number of primitives due to limitations in its Adaptive Density Control (ADC) mechanism. This thesis introduces an error-driven reformulation of ADC that triggers densification using opacity gradients as a lightweight proxy for rendering error, and shows that such aggressive densification must be paired with delayed and conservative pruning to prevent destructive create--destroy cycles. When combined with depth-based geometric regularization, the resulting framework produces substantially more compact …

Differential Impact Of Admission Type And Clinical Complexity On Diabetes Hospitalization Costs Among African American And Hispanic Patients In Southeastern Virginia, Ismail El Moudden, Asra Amidi, Reem Sharaf-Alddin, Michael C. Bittner, Qi Zhang

Department of Obstetrics & Gynecology Faculty Publications

Background

Diabetes mellitus (DM) imposes substantial healthcare costs with documented disparities among African Americans and Hispanic patients. To inform care delivery and resource allocation, this study identified hospitalization cost predictors among African American and Hispanic patients with diabetes in Southeastern Virginia.

Methods

We analyzed 6,011 hospital discharges from the Virginia Health Information database (2016-2020) for adults aged 18-85 with diabetes. Discharges were classified by Medicare Severity Diagnosis-Related Groups: DM with complications/comorbidities (DCC, n = 3,328), DM with major complications/comorbidities (DMCC, n = 1,518), and DM without major complications/comorbidities (DWO, n = 1,165). Because cost distributions were right-skewed (skewness 3.5-8.24), we …

Consensus And Controversies Of International Guidelines For The Diagnosis, Surveillance, And Management Of Fetal Growth Restriction: An Updated Comparison, Daniele Diane Mascio, Suneet P. Chauhan, Tullio Ghi, Asma Khalil, Juliana G. Martins, Sara Sorrenti, Tamara Stampalija, Fabrizio Zullo, Francesc Figueras

Department of Obstetrics & Gynecology Faculty Publications

OBJECTIVE: To compare areas of consensus and disagreements across contemporary international and national guidelines on the diagnosis, surveillance, and management of fetal growth restriction (FGR).

DATA SOURCES: Electronic searches of MEDLINE from database inception up to March 2026 using MeSH terms and keywords related to FGR and guidelines. STUDY ELIGIBILITY CRITERIA: Critical, structured comparison of national or international guidelines on FGR published since 2010. Final inclusion required unanimous agreement from all authors.

STUDY APPRAISAL AND SYNTHESIS METHODS: Pre-specified extraction across domains: definition; prediction/prevention; surveillance tools and frequency; delivery timing and mode; and labor induction methods. Dual data …

Modeling Healthcare Data With Logistic Quantile And Uniform-Based Mixture Polynomial Distributions, Mohan D. Pant, Aditya Chakraborty, Jovanna A. Tracz

Epidemiology, Biostatistics, & Environmental Health Faculty Publications

Continuous healthcare data often deviate from normality, which can substantially increase the risk of making invalid inferences, given that many inferential statistical procedures rely on normality assumption. To obviate this issue, we propose a new family of non-normal distributions based on a linear combination of the quantile functions of standard logistic and uniform (0, 1) distributions. This new family of non-normal distributions is studied within three different methods: L-moments, conventional moments, and percentiles. Its performance is compared among the three methods in the context of parameter estimation and data modeling. The results of Monte Carlo simulation and bootstrapping techniques indicate …

Beyond Numbers: Bridging Statistical Significance And Clinical Relevance In Healthcare Research, Maharaj Singh, Waheeda Khan, Mehreen Fatima

College of Nursing Faculty Research and Publications

Objective: This study aims to bridge the gap between statistical significance and clinical relevance using rigorous statistical methodologies applied to simulated healthcare data, thereby enhancing the translational value of research outcomes for patient‑centered care. Methods: A synthetic dataset representing 10,000 patients was generated, and descriptive statistics were applied to compare two treatment groups. Binary outcomes were predicted using both a logistic regression model and a neural network. Two‑tailed tests with a significant level of 0.05 were employed, utilizing SAS version 9.4 and IBM SPSS Statistics, Version 29.0 (IBM Corp., Armonk, New York, United States of America). Results: The simulated dataset …

Nirmatrelvir-Ritonavir Targeting Viral Persistence In Post-Covid-19 Condition (Long Covid) In The Usa (Recover-Vital): A Randomized, Double-Blind, Placebo Controlled, Phase 2 Trial, Lindsey R. Baden, Nirav S. Shah, Sean T. H. Liu, Jonathan Cohen, James May, Andre Kumar, Grace A. Mccomsey, Peter Chen, Michelle Floris-Moore, Nora G. Singer, Inti Fernandez, Alex J. Slandzicki, Zanthia Wiley, Alexandra Kadl, David A. Kaminsky, Harvey Hsu, Tiffany A. Walker, Aluko A. Hope, Luis Ostrosky-Zeichner, Jason D. Goldman, Michael J. Peluso, Thomas F. Patterson, Sairam Parthasarathy, Janet M. Mullington, Paul Bolin Jr., Sarah E. Jolley, Jerry A. Krishnan, Mario Castro, Sally L. Hodder, Priscilla Pemu, Helen Y. Chu, Michael G. Risbano, Maya R. Jerath, Eleftherios Mylonakis, Ryan T. Hurt, Radica Alicic, Nabila S. Azad, Marc A. Sala, Michelle S. Harkins, Jeffrey Parsonnet, Neil Stafford, Philip Robinson, Sabiha Hussain, Xian Qiao, Sophie Two Hawk, Michael Lillestol, Nathan Erdmann, Kelly A. Gebo, Praveen Sudhindra, Joseph Sassine, Gailen D. Marshall, Tulika Chatterjee, Caryn G. Morse, Eyal Kedar, William W. Stringer, Jennifer A. Frontera, Michael Jordon, Caitlin Blaskewicz, Jorge L. Santana, Rachel A. Foot, Cherry Wongtrakool, Matthew William Mccarthy, Alem Mehari, Arch Amon, Alison K. Cohen, Nita Jain, Christine Maughan, Doug Lindsay, Rachel Olson, Samuel Broderick, Pearl Rowe, Sean M. O'Brien, David R. Walt, Bruce D. Levy, Leonard A. Jason, Phillip A. Low, Cyndya A. Shibao, Barry Make, Lucinda Bateman, Susan Redline, David Knopman, Adrian F. Hernandez, Tracy L. Nolen, Craig Reist, Lisa Berdan, Richard Whitley, Kanecia O. Zimmerman, For The Recover-Vital Clinical Trial Group

Department of Medicine Faculty Publications

Background

Post-acute sequelae of SARS-CoV-2 infection, more commonly known as long COVID, has emerged as a major health problem. The pathogenesis of long COVID is unknown, but among the leading hypotheses is viral persistence. We aimed to investigate whether the use of the SARS-CoV-2 antiviral nirmatrelvir-ritonavir improved long COVID symptoms.

Methods

We conducted a double-blind, placebo-controlled, randomised trial involving adults who had developed persistent symptoms (≥12 weeks) associated with three major symptom phenotypes (cognitive, autonomic, or exercise) after acute SARS-CoV-2 infection at 69 US sites. Participants were eligible if they were 18 years or older and had a previous suspected, …

Uncertainty-Guided Test-Time Optimization For Personalizing Segmentation Models In Longitudinal Medical Imaging, Jaehee Chun, Austin Castelo, Mckell Woodland, Caleb O'Connor, Mais Al Taie, Mohamed Eltaher, Aashish Gupta, Bilel Daoud, Shanli Ding, Jeddy Bennett, Anirban Maitra, Matthew A Firpo, Kimberly Kirkwood, Eugene J Koay, Kristy K Brock

Faculty, Staff and Student Publications

Background: Accurate and consistent image segmentation across longitudinal scans is essential in many clinical applications, including surveillance, treatment monitoring, and adaptive interventions. While personalized model adaptation using patient-specific prior scans has shown promise, current approaches typically rely on fixed training durations and lack mechanisms to determine optimal stopping points on a per-patient basis, particularly in the absence of validation labels.

Purpose: We propose an uncertainty-guided test-time optimization (TTO) framework that dynamically adjusts the personalization duration for each patient using a validation-free stopping criterion based on predictive uncertainty.

Methods: Our framework personalizes a generalized segmentation model using patient-specific prior imaging and …

Baseline Body Mass Index Category And Incident Treated Hypertension In Australian Men: A Linked Prospective Cohort Study Using Pbs/Mbs Data, Ebenezer Afrifa-Yamoah

Research outputs 2022 to 2026

Background: Excess adiposity is a major modifiable risk factor for hypertension; however, the incremental prognostic value of body mass index (BMI) beyond standard predictors remains unclear. We examined the associations between baseline BMI category and incident treated hypertension, and assessed whether BMI improved risk prediction.

Methods: Data were obtained from the Ten to Men longitudinal study (2013–2024) linked to Pharmaceutical Benefits Scheme (PBS) and Medicare Benefits Schedule (MBS) records. The cohort comprised 12,742 men aged ≥ 18 years without treated hypertension at baseline, followed for 133,038 person-years. Adjusted Cox proportional hazards models were fitted. Discrimination, calibration, decision curve analysis, E-values, …

Healthcare Provider Perspectives On A Clinical Decision Tool To Support Individualized Exercise Prescriptions And Discussions For Breast Cancer Survivors, Jinani Jayasekera, Oliver W. A. Wilson, Kaitlyn M. Wojcik, Eleanor M. Kerr, Rachelle Brick, David Berrigan, Jennifer Yeong-Shin Sheng, Takeo Fujii, Kathleen Thomas, Henri K. Parson, Padma Sheila Rajagopal, Richard L. Street Jr.

Department of Medicine Faculty Publications

Purpose: We evaluated healthcare providers' current knowledge, practices, and perspectives on a novel clinical decision tool (beta-version) to facilitate individualized exercise prescriptions and discussions in clinical settings.

Methods: We recruited healthcare providers who had treated or provided care to breast cancer survivors aged >= 35-years in the past 12 months. The participants were presented with a tool to provide individualized exercise recommendations considering women's individual, clinical, and contextual characteristics. Validated and reliable pre-existing instruments were used to survey providers' current knowledge, practices regarding exercise discussions, and perspectives on the beta-version (paper-draft) of the novel tool.

Results: The sample consisted of …

A Quantitative Analysis Of Barriers To College Students’ Seasonal Vaccination Intentions And Behaviors, Kelly S. Clemens, John Matkovic

Faculty Publications – Health Sciences

Objective
Vaccination is crucial to college student health, but quantitative analyses of barriers in this population are limited. The present study expands the work of Su and Chen to determine the relative influence of structural, psychological, and social vaccination barriers.

Participants
Participants were 650 students from a large, midwestern university during the 2024 vaccination season.

Methods
Participants were recruited from a college campus and randomized to respond to items assessing their barriers to, intentions to receive, and uptake of the COVID-19 or influenza vaccination.

Results
Structural, psychological, and social barriers were differentially important to vaccinations and to intentions vs. uptake …

Gaze Transition Entropy And Automation Trust In Multitasking Workspace, Yusuke Yamani, Austin Jackson, Tetsuya Sato, Feyishola Ashimi, Michael S. Politowicz, Eric T. Chancey, Makoto Itoh

Psychology Faculty Publications

Safe flight operation requires visual scanning across multiple displays in a cockpit, which collectively represent the state of the aircraft and supporting automation. Trust is a crucial factor that drives human-automation interaction, and recent work has suggested a relationship between an operator's visual attention and automation trust. One index that captures predictability of eye movements between different areas of interest is gaze transition entropy. The current work reanalyzed data from Sato et al., which examined eye movement patterns and trust in automation associated with the system monitoring task of the Multi-Attribute Task Battery. Results showed credible positive correlations between the …

A Real-Time Examination And Comparison Of Differentiation Among Suicidal Thinking And Affect Items In An Adolescent Sample, Elizabeth A. Edershile, Kinjal K. Patel, Annabelle M. Mournet, Richard T. Liu, Catherine R. Glenn, Evan M. Kleiman

Psychology Faculty Publications

Suicide risk assessments require individuals to differentiate among types of suicidal thoughts (e.g., passive vs. active); yet most research relies on aggregate metrics that obscure this differentiation. Indeed, more severe forms of suicidal thinking are thought to involve the simultaneous experience of multiple forms of thoughts at high intensities. The present study draws on concepts from the affect differentiation literature to (a) examine different ways to operationalize differentiation in suicidal thinking and (b) compare differentiation in suicidal thinking with differentiation in affect. Adolescents (N = 200) recently hospitalized for suicidal thoughts and behaviors completed a 28-day ecological momentary assessment …

Gain-Delay Decoupling In Human Stimulus Frequency Otoacoustic Emissions Reveals Constraints On Cochlear Nonlinear Amplification, Yoshita Sharma, Arturo Moleti, Renata Sisto, Teresa Botti, Hansapani Rodrigo, Sri Mishra

School of Mathematical & Statistical Sciences Faculty Publications

Purpose: The nonlinear cochlear amplifier, driven by outer hair cells, underlies the remarkable sensitivity and frequency selectivity of the mammalian auditory system. Stimulus frequency otoacoustic emissions (SFOAEs) provide a noninvasive window into these active cochlear processes, yet the relationship between emission gain and delay across stimulus levels remains incompletely understood. This study examined the level dependence of SFOAEs in normal-hearing human listeners to characterize cochlear nonlinear response properties. We tested how emission gain and delay vary with stimulus level and estimated the frequency of the apical–basal transition associated with the breakdown of the approximate local scaling symmetry.

Methods: SFOAEs were …

Artificial Intelligence And Machine Learning In Smart Vaginal Formulation Development, Deborah A. Ogundemuren, Vivek Agrahari, Andrew P. Wong, Carolina Herrera, Margaret O. Ilomuanya, Gustavo F. Doncel

CONRAD Publications

Vaginal drug delivery in women's health remains underutilized and insufficiently studied, largely due to the complexity and dynamic nature of the vaginal microenvironment. Variations in vaginal pH, hormonal levels, and microbiota composition introduce significant biological variability, complicating formulation design and contributing to inconsistent therapeutic outcomes and poor patient adherence. Conventional vaginal formulations often fail to account for these individual differences, highlighting the need for more adaptive and predictive approaches. Emerging advances in artificial intelligence (AI) and machine learning (ML) offer promising strategies to address these challenges by enabling multi-parameter, data-driven formulation development that explicitly considers biological variability. Despite their transformative …

Una Nueva Herramienta Para Estimar El Volumen Muscular Independientemente De La Edad, El Sexo Y El Nivel De Actividad Física, José J. Rivera-Sánchez, Laura P. Burgos-Morelos, Daniel Castillo-Castillo, Gerardo Méndez-Suárez, Juan C. Lopez-Alvarenga, Damián Carrillo-Ruíz

School of Medicine Publications

Antecedentes: Actualmente, la evaluación del volumen muscular requiere técnicas invasivas o de imagen, lo que aumenta los costos y retrasa la evaluación, y las mediciones antropométricas con frecuencia son inexactas.

Objetivo: Desarrollar una fórmula matemática para estimar el volumen del cuádriceps.

Material y métodos: Se evaluaron 127 sujetos: 40 adultos sedentarios de 20 a 35 años, 47 atletas adultos de 20 a 45 años y 40 adultos sedentarios de 70 a 94 años. Se dividieron en grupos de desarrollo y de validación. Se realizaron mediciones de variables antropométricas y fuerza de agarre, y se desarrolló la fórmula de predicción del …

Safety Aware Continual Reinforcement Learning-Based Output Tracking Control Of Nonlinear Continuous-Time Systems, Irfan Ganie, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

An output feedback (OF)-based control scheme utilizing both a scalable multilayer neural network (MNN) observer and actor–critic MNN via integral reinforcement learning (IRL)/adaptive dynamics programming (ADP) approach for a class of nonlinear systems with output constraints is introduced. The proposed observer, critic, and actor MNN weight updates are derived using a singular value decomposition (SVD) of MNN activation function gradient along with output error, Bellman and control input errors, respectively. Next, the approach incorporates continual learning (CL), utilizing a penalty function in the weight update laws for both actor–critic MNNs to consolidate knowledge from previous tasks and enhance learning in …

Safe Optimal Control Framework For Cooperative Manipulation Of Objects In Human–Robot Teams, Irfan Ganie, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This article introduces a distributed deep neural network (NN)-based adaptive control framework for cooperative object manipulation in human–robot teams with unknown agent dynamics by using three distinct multilayer NN observers (MNNOs). The first observer, termed the reference point estimator, enables each robotic agent to estimate the object's reference center using consensus-based learning, even without direct access to global reference trajectories. The second observer, referred to as the human force-to-trajectory estimator, uses human-applied forces to infer the intended position, velocity, and acceleration of the object, enabling real-time estimation of human intent. Together, these two observers allow distributed estimation of human-intended motion. …

Self-Calibrating Uav Navigation: Reinforcement Learning Approaches For Horizontal Trajectory Estimation, Shirin Nasr-Esfahani, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

Accurate unmanned aerial vehicle (UAV) trajectory estimation is essential for autonomous navigation, particularly in GPS-denied environments. Visualodometry and simultaneous localization and mapping (SLAM) approaches require precise camera intrinsic parameters, which are typically obtained through predefined or offline calibration. Instead, in this work, we propose a reinforcement learning (RL)-based self-calibration framework that estimates camera intrinsic parameters directly from monocular video sequences, without requiring prior knowledge of the camera, environment, or calibration targets. This intrinsic parameter estimation is then leveraged to achieve robust UAV trajectory estimation using only video data. We formulate the problem as a sequential decision-making task, where an RL …

Online Lifelong Optimal Adaptive Control Of Partially Uncertain Strict Feedback Discrete-Time Systems With Application To Quadrotor Uavs, Maxwell Geiger, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This article considers the infinite time horizon optimal adaptive tracking control of partially uncertain strict feedback discrete-time (DT) systems with application to quadrotor uncrewed aerial vehicles (UAVs). First, the strict feedback DT system is transformed into an equivalent affine nonlinear DT system in terms of the tracking error dynamics. The optimal adaptive tracking control problem is solved using an augmented system approach, where a horizon of future bounded reference trajectory points is used in the augmented state, when compared to using a single point. It is assumed that the internal dynamics of the strict feedback system are unknown, but the …