Prediction Of Anomalous Events With Data Augmentation And Hybrid Deep Learning Approach, Ahmed Shoyeb Raihan

Graduate Theses, Dissertations, and Problem Reports

In this study, we propose a novel anomaly detection framework designed specifically for Multivariate Time Series (MTS) data, addressing the prevalent challenges in analyzing such complex datasets. The detection of anomalies within MTS data is notably difficult due to the complex interplay of numerous variables, temporal dependencies, and the common issue of class imbalance, where one category significantly outnumbers another. Traditional deep learning (DL) approaches often fall short in simultaneously tackling these issues. Our framework is designed to address these challenges through a two-phased approach. Phase I employs Conditional Tabular Generative Adversarial Networks (CTGAN) to create strategic synthetic data, setting …

Implementing Unmanned Aerial Vehicles To Collect Human Gait Data At Distance And Altitude For Identification And Re-Identification, Donn E. Bartram

Graduate Theses, Dissertations, and Problem Reports

Gait patterns are a class of biometric information pertaining to the way a person moves and poses. Gait information is unique to each person and can be used to identify and reidentify people. Historically, this task has been achieved through the use of multiple ground-based imaging sensors. However, as Unmanned Aerial Vehicles (UAVs) advance, they present the opportunity to evolve the process of persons identification and re-identification. Collecting human gait data using UAVs at distances ranging from 20m to 500m and altitudes ranging from 0m to 120m is a challenging task. The current biometric data collection methods, primarily designed for …

Machine Learning For Environmental Sustainability, Syeda Nyma Ferdous

Graduate Theses, Dissertations, and Problem Reports

This research proposes a comprehensive approach to address pressing challenges in environmental sustainability, agricultural residue management, using machine learning based approaches. Machine learning (ML) techniques have emerged as powerful tools for addressing environmental sustainability challenges by facilitating the analysis and prediction of ecological phenomena, and optimization of resource management strategies. The study explores the synergies between environmental sustainability and machine learning to develop a framework that leverages artificial intelligence techniques covering a wide range of tasks including crop residue management, soil CO2 flux prediction, and forest carbon system prediction for sustainable development. The study analyze various ML models, such as, …

High-Pressure Ignition And Flame Propagation – An Experimental And Numerical Study, James Shaffer

Graduate Theses, Dissertations, and Problem Reports

The next generation of advanced combustion devices is being developed to operate under ultra-high-pressure conditions, to improve combustion efficiency and reduce pollutant emissions. However, at such extreme conditions, flame tends to become unstable, and measurement of fundamental properties becomes challenging. The laminar burning speed ( ) is among those properties, as it is required for the validation of kinetic models and the modeling of turbulent combustion. One potential method to resolve this issue and achieve measurement at very high pressures (i.e., 20-50 atm), is focusing on ignition affected region. The flame kernel in this region is more resistant to perturbations …

Analyzing Viability Of Blue Indium Gallium Nitride Leds For Use In Space Missions Using A Low Earth Orbit Cubesa, Bertrand Edward Wieliczko

Graduate Theses, Dissertations, and Problem Reports

The payload capacity of spacecraft is constrained by the weight of the craft itself, including fuel and electronic systems. The protective measures used to shield onboard electronics from the harsh space environment, characterized by high-energy particles and significant temperature fluctuations, can further diminish the available payload capacity. This thesis explores the potential of naturally radiation-hard alternatives to commonly used electronic materials, such as Silicon, to reduce the need for shielding and other protective measures, thereby decreasing the weight and cost of space missions.

III-V semiconductor materials, such as Gallium Nitride (GaN), are known for their inherent resilience to temperature swings …

Transparent And Conductive Gallium Oxide Electrode For Simultaneous Recording And Optogenetic Stimulation, Christopher Patrick Carey

Graduate Theses, Dissertations, and Problem Reports

Neural electrode technology has been around for centuries since the times of Galvani. In early electrophysiology experiments metal wires were used to induce contractions in dissected animals. The metal wire electrode has since been a standard tool to both stimulate and record neural activity. In the past two decades, a new strategy for neural stimulation has been formulated based on the emergent field of optogenetics. Optogenetics refers to the use of light-sensitive proteins genetically imbedded in the membrane of a neuron to elicit neural activity. This technique offers more selectivity in the stimulation of neurons. Typical optogenetic neural electrodes, or …

Evaluation Of 50’ Frp Truss Bridges With Timber Decks, Maxwell Browning Carey

Graduate Theses, Dissertations, and Problem Reports

Fiber-reinforced polymer (FRP) composites have become mainstream structural materials and are being utilized in many different structural applications because of their outstanding thermos-mechanical properties and other characteristics. These characteristics include exceptional corrosion resistance, energy absorption, durability, high strength-to-weight, stiffness-to-weight ratios, and others. Also, FRP composites are cost effective especially when accounting for the service life of such a material.

In this study, testing and analysis were performed at both the component as well as a structural system levels. Herein, two FRP truss bridges of different widths with 50 ft. spans underwent extensive testing and analysis in accordance with AASHTO specifications. …

Reformed-Based Approaches To The Teaching And Learning Of Science, Sahar Vali

Graduate Theses, Dissertations, and Problem Reports

This qualitative practice-based study explores the efficacy of reformed-based science teaching approaches in fostering meaningful student engagement within elementary science classrooms, framed within the science-as-practice paradigm. Utilizing three theoretical frameworks, the Next Generation Science Standards (NGSS) and Ambitious Science Teaching (AST), and the Teacher Noticing, this research investigates how these frameworks influence student engagement in scientific disciplinary practices. The study draws on data from an NSF-funded project on teacher noticing in fifth-grade classrooms in West Virginia. Through a practice-based research approach, the relationship between teachers’ pedagogical practices and student engagement in science and engineering practices as outlined by NGSS and …

Data-Driven Approaches For Achieving Carbon Neutrality: Predictive Models For Reducing Co2 Emissions And Enhancing Industrial Sustainability, Farzana Islam

Graduate Theses, Dissertations, and Problem Reports

In response to the escalating challenges posed by climate change and industrial inefficiency, this thesis presents a comprehensive investigation aimed at advancing the predictive modeling of global CO2 emissions and enhancing operational efficiency in steel manufacturing through Electric Arc Furnace (EAF) temperature optimization. Leveraging a rich dataset sourced from the World Development Indicators database alongside a meticulously curated dataset specific to EAF operations, our study applies an innovative blend of econometric and machine learning techniques, including Pooled Ordinary Least Squares (Pooled OLS), Random Effects (RE), Fixed Effects (FE), and Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) models. The …

Strategies For Process Systems Mapping And Control Based On Operability Analysis, Victor Manuel Cunha Alves

Graduate Theses, Dissertations, and Problem Reports

This dissertation aims to develop strategies for process systems engineering (PSE) mapping using models, emerging tools and algorithms motivated by process operability analysis research. Such strategies will be employed to ensure simultaneous design and control of large-scale industrial systems. The emerging tools and techniques in this research include supervised machine learning-based (ML-based) operability mapping, automatic differentiation (AD) for implicit mapping, and the development of a systematic mapping approach for control structure selection using operability analysis. Thus far, the developed operability algorithms either recur to nonlinear programming (NLP) solutions which are computationally expensive or to linearizing the underlying modeling task at …

Application Of High-Resolution Fiber Optic Data To Enhance Completion Design, Christian J. Pacheco

Graduate Theses, Dissertations, and Problem Reports

MS Dissertation Defense

By

Christian Pacheco

Title: Application of High-Resolution Fiber Optic Data to Enhance Completion Design Major: Petroleum and Natural Gas Engineering Date: Thursday, April 18, 2024 Time: 4:00 PM Place: 141 Engineering Science Building

Abstract

Well stimulation is a technique that has been used in the industry for decades, and with the ability to drill wells horizontally the practice has become more valuable and effective than ever before. Its use is consistently being optimized and completions design plays a crucial role in the recovery of hydrocarbons. Several different downhole tools and measurements have been used to optimize these …

Joint Learning Of Unknown Safety Constraints And Control Policies In Reinforcement Learning, Lunet Abiye Yifru

Graduate Theses, Dissertations, and Problem Reports

Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades. Yet, deploying RL policies in real-world scenarios presents the crucial challenge of ensuring safety. Traditional safe RL approaches have predominantly focused on incorporating predefined safety constraints into the policy learning process. However, this reliance on predefined safety constraints poses limitations in dynamic and unpredictable real-world settings where such constraints may not be available or sufficiently adaptable. Bridging this gap, we propose a novel approach that concurrently learns a safe RL control policy and identifies the unknown safety constraint parameters of a given environment. …

Enhancing 5g Fixed Wireless Access In Rural Settings Via Machine Learning-Driven Resource Optimization, Maryam Amini

Graduate Theses, Dissertations, and Problem Reports

Providing broadband access to rural communities continues to be an important societal problem whose solution would help to break down the digital divide. While 5G wireless networks may be used for rural broadband, a key challenge is the placement of base stations, which is exacerbated by the use of high frequencies in the millimeter-wave band. Such technology requires an unobstructed line of sight, demanding meticulous planning of the number, height, and location of base stations for optimal coverage. Conventional methods, such as ray-tracing to simulate signal propagation across varied terrain, are computational costly and not feasible for vast coverage areas. …

Bridging Evolutionary And Bayesian Optimization For Enhanced Safety Verification In Control Systems, Joshua M. Yancosek

Graduate Theses, Dissertations, and Problem Reports

The rigorous safety verification of control systems in critical applications is essential, given their in creasing complexity and integration into everyday life. Simulation-based falsification approaches play a pivotal role in the safety verification of control systems, particularly within critical applications. These methods systematically explore the operational space of systems to identify configurations that result in violations of safety specifications. However, the effectiveness of traditional simulation based falsification is frequently limited by the high dimensionality of the search space and the sub stantial computational resources required for exhaustive exploration. This thesis presents Bayesian Evolutionary Approach for COuNterexample, or BEACON, a novel …

Modeling, Control, And Fault Detection Of Energy Systems Under Limited High-Confidence Data Scenarios, Selorme K. Agbleze

Graduate Theses, Dissertations, and Problem Reports

Abstract

Modeling, Control, and Fault Detection of Energy Systems under Limited High-Confidence Data Scenarios

Selorme K. Agbleze

Utilizing process measurements for fault detection is an established approach for processes with adequate datasets. For systems with limited high-confidence data representing fault cases and some amount of low-confidence data, few quantitative hybrid techniques exist for performing fault detection. In real systems, it is time-consuming, expensive, and sometimes not productive to generate enough high-confidence data with fault characteristics of a specific process. The problem of limited high-confidence data scenarios may also arise due to process novelty, the need for new operating conditions, or …

Active Uncertainty Representation Learning: Toward More Label Efficiency In Deep Learning, Salman Mohamadi

Graduate Theses, Dissertations, and Problem Reports

The primary goal of this dissertation is to investigate and improve the efficiency of deep learning algorithms, especially within computer vision problem domains, from the perspective of label-efficiency. This investigation showed that deep learning algorithms are mostly notorious for the lack of uncertainty representation. Accordingly, we aimed to develop an array of deep learning frameworks rich with uncertainty representation. These frameworks are mainly within two current pillars of machine learning, deep active learning and self-supervised learning. These frameworks include deep active ensemble sampling for efficient sample selection within deep active learning, a two-stage ensemble-based general self-training approach for existing visual …

Passive Wireless Corrosion And Temperature Detection In High-Temperature Environments, Noah Lane Strader

Graduate Theses, Dissertations, and Problem Reports

This work focuses on the theory and development of LC sensors for high temperature and corrosion measurement for stainless steel and copper surfaces with power industry and general corrosion detection applications. The LC resonators were fabricated via screen printing an Ag inductor on an alumina substrate. The LC design was modeled using the ANSYS HFSS modeling package. The LC passive wireless sensors operate with resonant frequencies centered at 85-110 MHz. The wireless response of the LC sensor was interrogated and received by a radio frequency signal generator and spectrum analyzer at temperatures from 50-800 °C for copper ground planes and …

Evaluation Of Probable Maximum Precipitation (Pmp) For West Virginia To Predict Current And Future Pmp & Utilizing Acid Mine Drainage (Amd) Sludge In Reclamation, Grace Katherine Kerr

Graduate Theses, Dissertations, and Problem Reports

This thesis includes two main topics: 1) evaluation of probable maximum precipitation (PMP) for West Virginia to predict current and future PMP, and 2) utilizing acid mine drainage (AMD) sludge as a reclamation plan.

Probable maximum precipitation (PMP) is essential for dam design as well as for the inspection, operation, maintenance, and repairs of these facilities. West Virginia Department of Environmental Protection Dam Safety utilizes the 6-hr, 10-mi² (26-km²) PMP established by Hydrometeorological Report (HMR) 51 based on the analysis of extreme rainfall. These PMP are outdated because there have been unaccounted for extreme rainfall events that …

Site Specific Probable Maximum Precipitation Implications For High Hazard Dams In West Virginia, Levi Jacob Cyphers

Graduate Theses, Dissertations, and Problem Reports

Estimates of probable maximum precipitation (PMP) are necessary for designing the maximum reservoir storage necessary to prevent dam overtopping. Recent investigations in Ohio, Virginia, and Pennsylvania imply that reducing PMP rainfall estimates in West Virginia may be appropriate; however, additional studies in this data deficient region with changing climate is necessary before any reductions are contemplated. The objective of this study was to re-evaluate PMP for the Howard Creek Dam watershed in West Virginia. The 6-hr, 10 mi² PMP was evaluated for current (2019) and projected (2100) climates and compared to the design PMP. Then, the impact of the …

Special Collections As Muse: The Use Of Rare Books And Archives To Inspire Creative Works, Tracy Grimm, Adriana Harmeyer

Faculty & Staff Scholarship

The unique and varied collections held by archives and special collections within many academic libraries offer fertile ground for the creative endeavors of students, faculty, and professional artists. This chapter explores direct and indirect methods librarians and archivists may engage creators with primary source materials. Academic libraries do not necessarily need to build art-focused collections in order to support the research of creators. More than subject content, successful engagement with creators is developed by means of collaborative relationships with arts faculty, artists, and galleries to reach student creators and introduce concepts of primary source research as a source of inspiration. …

Evaluations Of Frp Composite Coupons Under Impact And Puncture, Lekhnath Bhandari

Graduate Theses, Dissertations, and Problem Reports

Evaluations of FRP Composite Coupons Under Impact and Puncture

Lekhnath Bhandari

Railroad tank cars are the main mode of transportation for carrying flammable liquids and other hazardous materials, in any mode of ground transportation system. These tank cars, if punctured during derailments may explode releasing large amounts of hazardous materials and posing serious threats to human life and leading to economic losses. To minimize such catastrophes, in 2015, United States Department of Transportation (USDOT) proposed to improve the thermal and puncture performances of these tank cars and introduced two new design specifications: DOT-117 and DOT-117R. Tank cars with 9/16 inches …

Weigh-In-Motion Data-Driven Pavement Performance Prediction Models, Mohhammad Afsar Sujon

Graduate Theses, Dissertations, and Problem Reports

The effective functioning of pavements as a critical component of the transportation system necessitates the implementation of ongoing maintenance programs to safeguard this significant and valuable infrastructure and guarantee its optimal performance. The maintenance, rehabilitation, and reconstruction (MRR) program of the pavement structure is dependent on a multidimensional decision-making process, which considers the existing pavement structural condition and the anticipated future performance. Pavement Performance Prediction Models (PPPMs) have become indispensable tools for the efficient implementation of the MRR program and the minimization of associated costs by providing precise predictions of distress and roughness based on inventory and monitoring data concerning …

Feasibility Of Applying Motion Magnification In Subsurface Defect Detection For Concrete And Fiber-Reinforced Polymer Specimens, Nagavardhani Malineni

Graduate Theses, Dissertations, and Problem Reports

Irrespective of size and complexity, every civil infrastructure needs certain scrutiny regarding its structural health to ensure its serviceability during its lifetime. In olden times such scrutiny was done with the aid of destructive testing methods using sensors that required cumbersome and expensive installations and led to the destruction of at least part of the tested specimen. However, in recent times, many non-destructive methods, such as acoustic emission testing, electromagnetic testing, and laser testing methods have emerged, leaving the specified tested specimen undisturbed. With the advancement in sensor technology like motion magnification and with the help of access to high-speed …

Microwave-Assisted Ammonia Synthesis Over Cs-Ru/Ceo2 Catalyst, Alazar Kesete Araia

Graduate Theses, Dissertations, and Problem Reports

Ammonia synthesis is one of the greatest innovations of the 20^th century with extensive applications from fertilizers to intermediates for nitrogen-containing chemicals and pharmaceuticals. Annually, more than 242 million tons of ammonia is produced globally, supporting approximately 27% of the world’s population. One of the fast-growing applications for ammonia is as H₂ energy carrier due to its high energy storage capacity, considered to be a decarbonized energy source. The low volumetric energy density and incompressibility makes Hydrogen a non-preferable energy carrier; an alternative carrier becomes a requirement. Ammonia possesses unique property as an energy-dense carrier to store and …

An Artificial Neural Network Approach To Predicting Formation Stress In Multi-Stage Fractured Marcellus Shale Horizontal Wells Based On Drilling Operations Data, Moudhi Alawadh

Graduate Theses, Dissertations, and Problem Reports

The distribution of the anisotropic minimum horizontal stress, both in horizontal and vertical directions, is necessary for effective hydraulic fracture treatment design in Marcellus Shale horizontal wells. Typically, the minimum horizontal stress can be estimated sonic logs. However, sonic log data is not commonly available for the horizontal Marcellus shale wells due to the complexity and cost. The objective of this research is to predict the anisotropic minimum horizontal stress by utilizing drilling parameters including depth, weight-on-bit (WOB), revolution per minute (RPM), standpipe pressure, torque, pump flow rate, and the rate of penetration (ROP). More specifically, artificial neural network (ANN) …

Strengthening Of Damaged Structural Members With External Frp, Krishna Tulasi Gadde

Graduate Theses, Dissertations, and Problem Reports

Fiber reinforced polymer (FRP) composites are excellent alternatives to traditional materials for civil infrastructure. Several researchers have worked on the application of FRP composites for construction, repair, and rehabilitation of structures. This research aims at evaluating the use of carbon, glass, basalt, and hybrid FRPs with epoxy and polyurethane resin systems for rehabilitation of damaged structural components. Following evaluations were carried out in this research: (i) tension testing of FRP coupons, (ii) compression testing of concrete cylinders with and without damaged sections/FRP reinforcements, (iii) flexural testing of external-FRP reinforced RC beams with and without damages, (iv) pull-off tests on FRP …

A Computer Vision-Based Method For Tack Coat Coverage Inspection Using Drone-Collected Images, Aida Da Silva

Graduate Theses, Dissertations, and Problem Reports

Tack coat is a thin asphalt applied between the existing surface and asphalt overlay during road rehabilitation. The uniformity of tack coat coverage plays a vital role in providing adhesive bonding between the two layers in the pavement structures. To ensure tack coat uniformity, the current practice primarily relies on manual inspection during construction by field experts. This process is time-consuming and tedious, and the results can be subjective and error-prone. Drones have emerged as a non-destructive sensing technology in the construction industry for many inspection practices. Unlike other non-destructive inspection technologies, drones offer benefits ranging from accelerating data collection …

Application Of Metagenomic And Molecular Microbiology Techniques To Elucidate Sources Of Fecal Pollution And Anthropogenic Antibiotic Resistance Genes To Surface Water: A Step Towards A “One Health” Approach To Watershed Management, Mehedi Hasan Tarek

Graduate Theses, Dissertations, and Problem Reports

The use of fecal indicator bacteria, such as Escherichia coli, is a widely established regulatory and monitoring practice to detect surface water contamination associated with fecal pollution. However, the detection or quantification of fecal indicator bacteria alone does not accurately inform the sources of fecal pollution. The development of molecular and metagenomic methods that target the DNA of microorganisms has resulted in a host of new tools for monitoring fecal pollution and its sources, as well as for understanding emerging microbial threats, such as antimicrobial resistance. Antimicrobial resistance is a critical “One Health” challenge presenting a high risk to …

Optimizing Sample Collection And Data Interpretation For Effective Wastewater-Based Epidemiology In Combined Sewer Systems, Christopher Allen Anderson

Graduate Theses, Dissertations, and Problem Reports

COVID-19 has spurred growth in the science surrounding wastewater-based epidemiology (WBE) pertaining to the detection of severe acute respiratory virus 2 (SARS-CoV-2) in waste streams as an early warning signal for public health. However, the highly variable wastewater environment has made it difficult to standardize an approach for sampling and analysis, especially in locations using combined sewer infrastructure. This study addresses knowledge gaps of WBE via three specific aims: (1) to compare diurnal fluctuations of SARS-CoV-2 and the human fecal indicator, pepper mild mottle virus (PMMoV) in wastewater treatment plant (WWTP) influent samples collected during dry versus wet weather conditions; …

Energy Digital Twins In Smart Manufacturing Systems, Anna Billey

Graduate Theses, Dissertations, and Problem Reports

In this thesis, an Energy Digital Twin for smart manufacturing systems was developed and evaluated. In particular, the study focused on bidirectional parameter communication between the physical and the virtual part with the aim of optimizing the energy used in the manufacturing process. Rising costs and the environmental impacts related to energy consumption have grown in importance worldwide. There are elevated concerns in sectors like manufacturing, leading to an urgent quest to reduce energy consumption. A recent advancement in Industry 4.0 technology, the Digital Twin, represents a promising smart technology and tool that researchers are investigating to help reduce energy …