Engineering Commons^™

Exploring The Use Of Enhanced Swad Towards Building Learned Models That Generalize Better To Unseen Sources, Brandon M. Weinhofer

USF Tampa Graduate Theses and Dissertations

Deep learning models, typically, take significant time to train. Classifier ensembles are areliable way to increase classifier accuracy and perhaps generalizability to unseen sources of data. These classifiers can be combined with a simple voting scheme. The problem is that having multiple models can very heavily increase training time. Snapshot ensembles have been shown to provide a boost in performance by creating an ensemble of classifiers with different weights during the training of a single deep learned model. This can somewhat solve the problem of the increased training time as you do not have to train separate models. As Machine …

Effects Of Unobservable Bus States On Detection And Localization Of False Data Injection Attacks In Smart Grids, Moheb Abdelmalak

USF Tampa Graduate Theses and Dissertations

In an era increasingly marked by sophisticated cyber-attacks, this thesis investigates the critical issue of bus unobservability in smart grids and its impact on the effectiveness of cyber-attack detection and localization models. Given that unobservability is a prevalent challenge in smart grids due to various factors, researchers have developed numerous algorithms for optimal Phasor Measurement Unit (PMU) placement under scenarios of limited observability. However, these models primarily focus on enhancing network observability, often without considering whether this placement optimally facilitates attack detection. This research is driven by the hypothesis that a deeper understanding of the effects of unobservable buses can …

Identifying Highly Responsive Locations For Spinal Motion Tracking Sensors, Tyler Hutchinson

Undergraduate Honors Theses

Tracking spinal motion in the lower back serves as a useful tool for aiding diagnostics. This study seeks to determine if a fabric garment with integrated strain sensors may provide sufficient information to identify key spinal motion characteristics typically manifested in skin strain. Sensors adhered directly to an individual’s skin would be the most effective means of capturing such characteristics. However, adhering sensors to skin of the lower back is difficult for frequent or everyday application. This research aims to integrate a sensor system into a more comfortable and readily user-applied device. Here we examine the implementation of such a …

Temporospatial Deep Learning Strategies For Prediction Of Disease Progression In Radiology, John D. Mayfield

USF Tampa Graduate Theses and Dissertations

While the fields of machine learning and medicine are deeply rooted in axiomatic scientific principles, there is an element of art that makes the practice imperfect, yet innately human. As the two fields have seen the greatest overlap in their collective history, there remains a chasm between them in terms of practical translation for the patients who desire and deserve personalized medicine. As presented in this dissertation, I and my collaborators have contributed to the groundwork for future exploration of predicting disease progression by identifying signals within sequential medical imaging to provide a temporospatial relationship upon which we can make …

Standardization Of Risk Classifications For Unmanned Space Vehicle Missions, Collin A. Gwaltney

Theses and Dissertations

This paper seeks to model risk classification levels (A-D) for 122 Space Vehicle programs. Models include multinomial logistic regression as well as random forest, a machine learning technique based on decision trees. We use independent variables (IVs) which are theoretically correlated to risk class for the regression and one random forest model. We then include all IVs and allow the random forest technique to use those which provide the most information on risk class before paring down the number of IVs to only 7. We show that the accuracy of predictions increases from 62% to 87% by using random forest …

Insights Into Cellular Evolution: Temporal Deep Learning Models And Analysis For Cell Image Classification, Xinran Zhao

Master's Theses

Understanding the temporal evolution of cells poses a significant challenge in developmental biology. This study embarks on a comparative analysis of various machine-learning techniques to classify cell colony images across different timestamps, thereby aiming to capture dynamic transitions of cellular states. By performing Transfer Learning with state-of-the-art classification networks, we achieve high accuracy in categorizing single-timestamp images. Furthermore, this research introduces the integration of temporal models, notably LSTM (Long Short Term Memory Network), R-Transformer (Recurrent Neural Network enhanced Transformer) and ViViT (Video Vision Transformer), to undertake this classification task to verify the effectiveness of incorporating temporal features into the classification …

Using Natural Language Processing To Identify Mental Health Indicators In Aviation Voluntary Safety Reports, Michael Sawyer, Katherine Berry, Amelia Kinsella, R Jordan Hinson, Edward Bynum

National Training Aircraft Symposium (NTAS)

Voluntary Safety Reporting Programs (VSRPs) are a critical tool in the aviation industry for monitoring safety issues observed by the frontline workforce. While VSRPs primarily focus on operational safety, report narratives often describe factors such as fatigue, workload, culture, staffing, and health, directly or indirectly impacting mental health. These reports can provide individual and organizational insights into aviation personnel's physical and psychological well-being. This poster introduces the AVIation Analytic Neural network for Safety events (AVIAN-S) model as a potential tool to extract and monitor these insights. AVIAN-S is a novel machine-learning model that leverages natural language processing (NLP) to analyze …

A Systematic Review Of Fourth Industrial Revolution Technologies In Smart Irrigation: Constraints, Opportunities, And Future Prospects For Sub-Saharan Africa, Joshua Wanyama, Erion Bwambale, Shafik Kiraga, Abia Katimbo, Prossie Nakawuka, Isa Kabenge, Isaac Oluk

Department of Agricultural and Biological Systems Engineering: Faculty Publications

The adoption of Fourth Industrial Revolution (4IR) technologies has revolutionized agricultural practices worldwide. However, their application in the context of sub-Saharan Africa remains a critical challenge. This study presents a systematic review that investigates the potential of 4IR technologies in smart irrigation. Sub- Saharan Africa faces multiple agricultural challenges, exacerbated by climate change, water scarcity, and inefficient irrigation practices. The need for sustainable, water-efficient, and data-driven irrigation systems is urgent to ensure food security and economic development in the region. This study addresses a crucial knowledge gap by assessing the constraints, opportunities, and prospects of implementing 4IR technologies for smart …

Mri Image Regression Cnn For Bone Marrow Lesion Volume Prediction, Kevin Yanagisawa

Theses and Dissertations

Bone marrow lesions (BMLs), occurs from fluid build up in the soft tissues inside your bone. This can be seen on magnetic resonance imaging (MRI) scans and is characterized by excess water signals in the bone marrow space. This disease is commonly caused by osteoarthritis (OA), a degenerative join disease where tissues within the joint breakdown over time [1]. These BMLs are an emerging target for OA, as they are commonly related to pain and worsening of the diseased area until surgical intervention is required [2]–[4]. In order to assess the BMLs, MRIs were utilized as input into a regression …

A.I. May Be Able To Measure The Capacity Of Used Electric Vehicle Batteries, Paul Bradford

Research on Capitol Hill

EV batteries reach the end of their useful lifetime in vehicles around 70-80% of initial capacity. However, many of these batteries can still hold large amounts of energy and can be particularly useful for stationary applications.

Optimal Additive Fabrication Of Patient-Specific Bone Tissue Scaffolds Through Material Formulation, Computational Flow Simulation, And Material Deposition Monitoring, Ethan O’Malley

Theses, Dissertations and Capstones

The advancement of additive manufacturing technologies has opened new avenues for fabricating biocompatible and structurally functional bone tissue scaffolds, essential in treating osseous fractures, defects, and diseases. This research aims to develop mechanically strong, dimensionally precise, and patient-specific porous bone tissue scaffolds that provide both structural integrity and biological functionality. Through three interconnected studies, several key challenges in the fabrication of these structures using the PME additive manufacturing process are addressed. First, the influence of polysaccharide and hydroxyapatite concentrations on the compressive modulus of PME-printed porous scaffolds is investigated. By creating structures with varying hydroxyapatite and polysaccharide compositions, the study …

Using Unsupervised Machine Learning To Reduce The Energy Requirements Of Active Flow Control, Jared N. Kerestes

Browse all Theses and Dissertations

It is generally accepted that there exist two types of laminar separation bubbles (LSBs): short and long. The process by which a short LSB transitions to a long LSB is known as bursting. In this research, large eddy simulations (LES) are used to study the evolution of an LSB that develops along the suction surface of the L3FHW-LS at low Reynolds numbers. The L3FHW-LS is a new high-lift, high-work low-pressure turbine (LPT) blade designed at the Air Force Research Laboratory. The LSB is shown to burst over a critical range of Reynolds numbers. Bursting is discussed at length and its …

Numerical Design, Fabrication, And Characterization Of Porous Tissue Scaffolds For Bone Regeneration, Brandon Coburn

Theses, Dissertations and Capstones

With the recent advancements within biomedical engineering of bone tissue scaffolds, there is still a need to develop mechanically robust and biocompatible with low immunogenicity for bone regeneration. Additionally, the evaluation of the fluid dynamics of the porous Triply Periodic Minimal Surfaces (TPMS) bone scaffold also shows the need for investigation due to the complex fluid interaction of hemodynamics that occurs with the scaffold internal and external domains. To aid in the development of treating bone fractures, defects, and diseases. Furthermore, with the induction of a wide variety of TPMS architecture that yields different topologies, the Convolutional Neural Network (CNN) …

Constructing An Interpretable Deep Learning Framework Utilizing Variational Autoencoder Latent Space For Part-Prototype Learning, Shiska Raut

Computer Science and Engineering Theses - Archive

What visual attributes do cats have in common, and what features set them apart from dogs? How are we able to tell the difference between the two? While we do not fully understand the mechanism humans use for object detection, one popular theory suggests that it boils down to identifying distinct visual features specific to each object. For example, all cats have vertical slit-shaped pupils when their eyes are constricted, which is something we do not see in dogs. These slit-shaped pupils are a feature ‘prototypical’ to cats. Object classification is a computer vision task that involves identifying and categorizing …

Kissing Bond Assessment In Adhesive Bonded Carbon Fiber Reinforced Composites Using Dielectric Spectroscopy, Minhazur Rahman

Mechanical and Aerospace Engineering Dissertations - Archive

The widespread use of fiber-reinforced composites in industries such as space, aviation, automobiles, and construction necessitates the formation of robust composite joints between critical structural components. Although adhesive-bonded joints are superior with improved load distribution and reduced weight, they are often overlooked in favor of bolted joints and mechanical fasteners due to the lack of reliable Non-Destructive Evaluation (NDE) techniques for adhesive-bonded composites. The anisotropic nature of the substrate and the intricate interfacial interactions between the adherend and adhesive material present significant challenges for conventional NDE methods. Moreover, weak adhesive bonds can result from uncontrolled manufacturing parameters, such as accidental …

Enhancing Scanning Tunneling Microscopy With Automation And Machine Learning, Darian Smalley

Graduate Thesis and Dissertation 2023-2024

The scanning tunneling microscope (STM) is one of the most advanced surface science tools capable of atomic resolution imaging and atomic manipulation. Unfortunately, STM has many time-consuming bottlenecks, like probe conditioning, tip instability, and noise artificing, which causes the technique to have low experimental throughput. This dissertation describes my efforts to address these challenges through automation and machine learning. It consists of two main sections each describing four projects for a total of eight studies.

The first section details two studies on nanoscale sample fabrication and two studies on STM tip preparation. The first two studies describe the fabrication of …

Real-Time Detection Of Sea Turtles Using Uav And Neural Networks On Edge Devices, Jose A. Gonzalez Nunez, Jose G. Gonzalez Nunez, Mustafa I. Akbas, Patrick Currier, Nickolas D. Macchiarella

Journal of Aviation/Aerospace Education & Research

Sea turtle populations continue to diminish around the globe for various reasons. Therefore, the need for innovative solutions to monitor sea turtles has been increasing. This research paper focuses on an innovative application of artificial intelligence (AI) and machine learning (ML) together with unmanned aerial vehicles (UAV) to improve sea turtle conservation efforts. We outline the design, implementation, and evaluation of a system that deploys UAVs equipped with high-resolution cameras, coupled with a purpose-built neural network to recognize, classify, and monitor sea turtles. This project thus serves as a platform for understanding the wider applicability and limitations of this technology …

Exploring Machine Learning Techniques For Embedded Hardware, Neel R. Vora

Computer Science and Engineering Theses - Archive

This thesis delves into the intricate symbiosis between machine learning (ML) methodologies and embedded hardware systems, with a primary focus on augmenting efficiency and real-time processing capabilities across diverse application domains. It confronts the formidable challenge of deploying sophisticated ML algorithms on resource-constrained embedded hardware, aiming not only to optimize performance but also to minimize energy consumption. Innovative strategies are explored to tailor ML models for streamlined execution on embedded platforms, with validation conducted across various real-world application domains. Notable contributions include the development of a deep-learning framework leveraging a variational autoencoder (VAE) for compressing physiological signals from wearables while …

Stock Price Trend Prediction Using Emotion Analysis Of Financial Headlines With Distilled Llm Model, Rithesh H. Bhat

Computer Science and Engineering Theses - Archive

Capturing the volatility of stock prices helps individual traders, stock analysts, and institutions alike increase their returns in the stock market. Financial news headlines have been shown to have a significant effect on stock price mobility. Lately, many financial portals have restricted web scraping of stock prices and other related financial data of companies from their websites. In this study we demonstrate that emotion analysis of financial news headlines alone can be sufficient in predicting stock price movement, even in the absence of any financial data. We propose an approach that eliminates the need for web scraping of financial data. …

Neural Net Estimation Of Discriminants Posterior Probability Vector, Harshvardhan Harshvardhan

Electrical Engineering Theses - Archive

Interpreting multi-layer perceptron (MLP) classifier outputs as posterior probabilities is a well-established practice in machine learning and is supported in the literature. However, several authors point out that MLP outputs are very poor estimates of the posterior probabilities. This is demonstrated for classifiers with and without nonlinear output activation. Achieving this reliability depends on key factors such as model complexity, sufficient training data availability, and optimization techniques' effectiveness. In practice, these requirements are not met, resulting in suboptimal probability estimates. Our approach introduces an innovative method based on the softmax output. The method aim to refine MLP discriminants into more …

Equipment Performance Cost Optimization Using Machine Learning (A Surface Condenser Case Study), Firdaus Basheer, Mohamed Saleem Haja Nazmudeen, Fadzliwati Mohiddin, Elango Natrajan

ASEAN Journal on Science and Technology for Development

Equipment performance assessment or prediction has usually been done using the conventional approach. Organization is often too busy to focus on improvement opportunities for equipment performance. Opportunities identifications are heavily reliant on expert opinion and the methods used often vary from one person to another depending on the knowledge they possess. The benefits of simplistic and realistic equipment performance prediction would significantly improve maintenance costs and hence could help to reduce the total operating cost of the asset. In this research work, a surface condenser was used as a case study. The solution proposed in this research work is to …

Improving Decision-Making Processes In Construction And Infrastructure Bidding: Qualitative And Quantitative Approaches Including Graph Theory, Game Theory, And Machine Learning, Muaz Osman Elzubeir Ahmed

Doctoral Dissertations

"Construction and infrastructure bidding is a highly competitive process that entails various uncertainties faced by contractors. Contractors weigh various factors to determine the expected benefits of a construction project and decide their bid value. However, the situation is more complex in multi-stage bidding (MSG), where general contractors must account for the bids of their subcontractors and face a greater threat of the winner’s curse (i.e., situation where the winning contractor underestimates the actual cost of the project). As such, bidding-related complexities, risks, and uncertainties, if uncontrolled, can lead to the rise of claims and disputes between stakeholders. Existing research falls …

Applications Of Predictive And Generative Ai Algorithms: Regression Modeling, Customized Large Language Models, And Text-To-Image Generative Diffusion Models, Suhaima Jamal

College of Graduate Studies: Theses & Dissertations

The integration of Machine Learning (ML) and Artificial Intelligence (AI) algorithms has radically changed predictive modeling and classification tasks, enhancing a multitude of domains with unprecedented analytical capabilities. Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative potential, allowing visual content creation directly from textual descriptions. These advancements are pivotal in design, art, entertainment, and visual communication, as well as enhancing creativity and productivity. This work explores three significant studies in …

Optimization Of Inter-Satellite Routing Using Lstm-Based Path Prediction Model, Yash Bhamare

Master's Projects

Satellite networks are one of the most important components that fulfill the world’s need for connectivity. To ensure that communication is efficient and reliable, robust routing algorithms are a must. Because, although it is true that certain routing characteristics may not be permanently and continuously flawless, a routing technique must effectively adapt to modifications in such network characteristics. The new routing method uses a Long Short-Term Memory (LSTM) model to manage dynamic metrics for Low Earth Orbit satellite networks. This LSTM model is aimed at predicting the optimal routing direction on the premise that a satellite is soon to be, …

Development Of Digital Twin For Fdm Printer With Preventive Cyber-Attack And Control Algorithms, Md Hazrat Ali, Asad Malik, Nursultan Jyeniskhan, Muhammad Arif Mahmood, Essam Shehab, Frank Liou

Mechanical and Aerospace Engineering Faculty Research & Creative Works

This paper presents a developed model of a Digital Twin (DT) for a fused deposition modeling (FDM) printer, real-time defect detection, and proposed frameworks for preventing cyber-attacks in real-time. It also highlights a model predictive control (MPC) algorithm for controlling the material feed based on a real-time feedback system. The system is designed and developed based on DT, and MPC with integrated machine learning (ML) algorithms to establish real-time process control and enhance the safety and reliability of the physical plant. ML algorithm is used for anomaly detection based on the convolutional neural network (CNN) model. The developed system can …

Word Prediction Using Dynamic Skip Connections Along With Arabert And Lstm In Arabic Language, Ahad Almalki, Faris Kateb, Rayan Mosli

ASEAN Journal on Science and Technology for Development

Natural Language Generation (NLG) plays a crucial role in modern digital tools, including chatbots, virtual support, content suggestions, and tailored marketing, making bots more responsive and reducing the need for human staff. While there's much research on NLG for languages like English, languages like Arabic, Urdu, and Chinese still face challenges. This study examines Arabic NLG's unique aspects, dialects, and word variations. With around 420 million Arabic speakers globally, it's crucial to advance NLG for this language. We compared three models: Long Short-Term Memory (LSTM), a mix of Bidirectional Encoder Representations from Transformers (BERT) and LSTM, and a version that …

Enhancing Reservoir Modeling And Simulation Through Artificial Intelligence And Machine Learning: A Smart Proxy Modeling Approach, Andrew Timothy Jenkins

Graduate Theses, Dissertations, and Problem Reports (ETD)

The application of numerical reservoir simulation (NRS) has been a common approach within the oil and gas industry for decades, providing a means to model and forecast dynamic subsurface interactions, as a basis for reservoir management and development decisions. These techniques have expanded to application within carbon capture utilization and storage (CCUS) projects as domestic and global policy shift towards reducing carbon emissions while maintaining the energy needs of our modern society. NRS techniques have become a core process for permitting approval in Class VI (large-scale geological sequestration) wells due to the fundamental similarity of these types of subsurface processes. …

Triggered Online System Re-Identification Applied To Model Predictive Control Using Gaussian Processes, Daniel Augusto Kestering

Graduate Theses, Dissertations, and Problem Reports (ETD)

Safety, product quality, enhanced performance, and increased profit all depend on the control of chemical and energy processes. However, operational issues can lead to control challenges, especially when processes are subject to disturbances during their operation. Process control methods work best when processes operate close to their designed operat- ing conditions, but lack of performance or other issues may occur when the process is far from such conditions. To overcome these challenges, in this dissertation, online model re- identification is proposed for Model Predictive Control (MPC). This involves reassessing the predictive model of an advanced controller, namely MPC, when re-identification …

Machine Learning Based Intrusion Detection Framework For Can Bus Vulnerabilities In Modern Vehicles, Obinna C. Agbo

Graduate Theses, Dissertations, and Problem Reports (ETD)

The Controller Area Network (CAN) bus is a crucial communication backbone in modern vehicles, connecting various Electronic Control Units (ECUs). However, inherent design weaknesses such as the lack of encryption and authentication make CAN networks vulnerable to cyber-attacks, including spoofing, Denial of Service (DoS), and fuzzing attacks. This thesis thoroughly evaluates these vulnerabilities and the limitations of existing security frameworks like Message Authentication Codes (MACs) and encryption, advocating for the adoption of Intrusion Detection Systems (IDS) as a more practical solution for CAN bus security. The proposed IDS leverages advanced machine learning techniques to accurately detect intrusions, even under complex …

Learned Modeling And Control Of Continuum Robots For Surgical Applications, Cameron Jack Wolfe

Dartmouth College Master’s Theses

To reduce morbidity and mortality during surgery, surgeons have increasingly turned to Minimally Invasive Surgery (MIS), which involves passing instruments through small incisions or natural orifices to minimize patient trauma. Although MIS has significantly improved patient outcomes, it hinders a surgeon's dexterity and impairs visual and tactile feedback. These deficiencies have prompted the adoption of Robot-Assisted Surgery (RAS), in which surgeons control robots instead of using handheld instruments. While RAS has improved patient outcomes, robots struggle to navigate constricted spaces due to their rigidity, spurring the development of Continuum Robots (CRs). These flexible infinite degree-of-freedom robots move by bending, allowing …