Engineering Commons^™

Deep Learning And Generative Ai Approaches For Automated Diagnosis And Personalized Treatment: Bridging Machine Learning, Medicine, And Biomechanics In Predicting Tissue Mechanics And Biomaterial Properties., Yasin Shokrollahi

Theses and Dissertations

Machine learning, particularly deep neural networks, has demonstrated significant potential in predicting high-dimensional tasks across various domains. This work encompasses a detailed review of Generative AI in healthcare and three studies integrating machine learning with finite element analysis for predicting biomechanical behaviors and properties. Initially, we provide a comprehensive overview of Generative AI applications in healthcare, focusing on Transformers and Denoising Diffusion models and suggesting potential research avenues to address existing challenges.

Subsequently, we addressed soccer-related ocular injuries by combining finite element analysis and machine learning to predict retinal mechanics following a soccer ball hit rapidly. The prediction errors are …

Project Thetis: A Low-Cost, Low-Profile Inertial Data Logger, Braidan Duffy

Theses and Dissertations

This thesis details the design, testing, calibration, and verification of a nine degree of freedom inertial measurement data logger for use with floating bodies. The instrument was conceived to address limitations of equipment used in classes within the Ocean Engineering department at Florida Institute of Technology. By meeting with several stakeholders and end users, a series of stakeholder requirements, capabilities, and component-level requirements were de- veloped that informed the design constraints. There were several hardware iterations of the board, culminating in Revision F5 which was extensively tested and proven. The design was inspected after testing concluded to determine which capabilities …

Robust Uncertainty Estimation Framework In Deep Reinforcement Learning For Active Slam, Bryan Joseph Pedraza

Theses and Dissertations

Autonomous mobile robots are essential in various domains such as industry, manufacturing and healthcare. Navigating autonomously and avoiding obstacles are crucial tasks that involve localizing the robot to explore and map unknown environments without prior knowledge. Simultaneous localization and mapping (SLAM) present significant challenges. In this study, we introduce a new approach to address robust navigation and mapping of robot actions using Bayesian Actor-Critic (A2C) reinforcement learning. The A2C framework combines policy-based and value-based learning by dividing the model into two components: (1) the policy model (Actor) determines the actions based on the state, and (2) the value model (Critic) …

Sustainable Cities: Life-Cycle Cost Analysis Of Integrating Piezoelectric Harvesters Into Roadways, Heba Mohamed Gaber

Theses and Dissertations

Energy is essential in our modern era. Because of the increasing electricity consumption, sustainable and Renewable energy became a necessary global approach to fill the gap of the ongoing energy shortage in addition to the climate change crisis due to using conventional ways for energy production. Renewable energy is a global approach that has achieved great accomplishments during the last decades and is gradually increasing. Energy harvesting is considered one of the main resources for renewable energy. Energy harvesting from the roadways is an ingenious horizon for sustainable, clean, and renewable energy generation. Harvesting energy from the roadways by using …

Robust And Uncertainty-Aware Image Classification Using Bayesian Vision Transformer Model, Fazlur Rahman Bin Karim

Theses and Dissertations

Transformer Neural Networks have emerged as the predominant architecture for addressing a wide range of Natural Language Processing (NLP) applications such as machine translation, speech recognition, sentiment analysis, text anomaly detection, etc. This noteworthy achievement of Transformer Neural Networks in the NLP field has sparked a growing interest in integrating and utilizing Transformer models in computer vision tasks. The Vision Transformer (ViT) model efficiently captures long-range dependencies by employing a self-attention mechanism to transform different image data into meaningful, significant representations. Recently, the Vision Transformer (ViT) has exhibited incredible performance in solving image classification problems by utilizing ViT models, thereby …

Electromagnetic Field Analysis, Materials Characterization, And Advanced Modeling Of Modern Guitar Pickups, Luis Alonso Villarreal

Theses and Dissertations

This Thesis establishes the foundations of modern guitar pickup theory, enhancing current pickup design by an increase in voltage output, reduction of DC resistance, and a reduction of production costs. This research investigates factors that have received insufficient attention, such as the performance of different magnetic materials, magnet geometry, bobbin geometry, metal effects, etc. An equation to calculate the output of guitar pickups is developed. Additionally, this work constructs a modern pickup using the techniques developed in this thesis incorporating theory and advanced modeling techniques to simulate changes in performance and interactions with different magnetic materials and geometries. The new …

Laser Assisted Direct Writing Of Liquid Metal For Microprinting Applications, Olga Vargas Cruz

Theses and Dissertations

This paper presents a research study for potential printing of a Liquid Metal (LM) Eutectic Gallium Indium alloy (EGaIn) through the applications of the innovative additive manufacturing technology LIFT (Laser Induced Forward Transfer). LIFT is a precise printing technology that allows to create small, detailed printing. The liquid metal in study, EGaIn, has demonstrated great potential for microelectronics applications due to its minimum toxicity and high conductivity. Throughout this research different printing parameters are studied to comprehend the behavior of EGaIn printing with LIFT technique, these include laser energy, laser pulse, receiver material substrate, donor layer thickness, and …

Using Statistical Clustering Of Trajectory Data To Support Analysis Of Subject Movement In A Virtual Environment, Martín Alejandro Galicia Avila

Theses and Dissertations

The rising use of virtual reality software requires new methods of spatiotemporal analysis to enhance the user experience. This investigation is focused on forming clusters from spatiotemporal trajectories within a virtual environment and analyzing them in search of human immersion and behavior insights. The cluster centroids are plotted and analyzed to identify associations with the trajectories and user demographics.

Effects Of The Build Orientation And Support Patterns On The Geometric Accuracy In Printing Parts With Overhang Structure: An Experimental Study, Bala Murali Krishna Mohan

Theses and Dissertations

Additive manufacturing is becoming increasingly popular in industries such as manufacturing due to its ability to use raw materials more efficiently and require less machining than traditional methods(Calignano et al., 2017). However, constructing overhanging structures in additive manufacturing can be challenging, potentially affecting the overall geometric quality of the printed components. The objective of this study was to identify the most effective printing orientation for overhanging designs in Fused Deposition Modeling (FDM) using two different support structures. To achieve this, the researchers used a laser scanner to collect point cloud data and conducted a comparative study to determine the …

Gaze Tracking Embedded Collaborative Robots For Automated Metrology And Reverse Engineering, Sachithra H. Karunathilake

Theses and Dissertations

Conventional geometric metrology, or three-dimensional (3D) scanning, and reverse engineering heavily rely on the experience of the operators. With an increasing need for automation, robot arms have been adopted for this task. However, due to the large variety of parts and designs, automated path planning could provide a scanning solution that may overlook the critical area, which could potentially deteriorate the scan results. This study explores the integration of collaborative robotics (cobots) with eye tracking technology to improve the autonomous 3D scanning process. The primary objective of this study is to enhance the accuracy and efficiency of cobots in …

Gpu Based Monte Carlo Estimation Of Eddy Current Losses In Electromagnetic Coil-Core System, Adwaith Ravichandran

Theses and Dissertations

A novel parallelizable probabilistic approach to model eddy currents in AC electromagnets is presented in this research. Consequently, power loss associated with the formation of these eddy currents is estimated and validated using experimental data. Furthermore, predicting the effect of ferromagnetic alternating field enhancement on power loss in the source excitation winding has been an active area of research. Unlike a stationary field, an alternating sinusoidal field diffuses partially into the ferromagnetic material leading to a predictably sub-optimal field enhancement. To model these physics, finite element techniques employ nonlinear iterative solvers which are time consuming. A novel method is developed …

A System Theoretic Process Analysis Framework And Model Based Approach For Resilient Space Architecture Design, Eric T. Sommer

Theses and Dissertations

As the capabilities provided by space-based systems offer significant contributions toward defense applications, potential adversaries stand to gain significant value in disrupting them. Therefore, the United States must pursue the development and operation of resilient space architectures, capable of delivering capabilities in the face of disruptions. To support this development, systems engineering methods require innovation to effectively ensure design of complex space architectures to meet their objectives. This thesis recommends and demonstrates a System-Theoretic Process Analysis (STPA) framework to qualitatively analyze space architectures. The analysis outputs identify design considerations, requirements, and constraints required for resilience. To enable a model-based systems …

The Private Pilot Check Ride: Applying The Spacing Effect Theory To Predict Time To Proficiency For The Practical Test, Michael Scott Harwin

Theses and Dissertations

This study examined the relationship between a set of targeted factors and the total flight time students needed to become ready to take the private pilot check ride. The study was grounded in Ebbinghaus’s (1885/1913/2013) forgetting curve theory and spacing effect, and Ausubel’s (1963) theory of meaningful learning. The research factors included (a) training time to proficiency, which represented the number of training days needed to become check-ride ready; (b) flight training program (Part 61 vs. Part 141); (c) organization offering the training program (2- or 4-year college/university vs. FBO); (d) scheduling policy (mandated vs. student-driven); and demographical variables, which …

Experiments And Simulations Of Liquid Mass Gauging And Slosh Dynamics In Microgravity, Jedediah Morse Storey

Theses and Dissertations

Advancements in liquid propellant management science and technologies are key to increasing safety, decreasing cost, and increasing payload mass of space missions. Propellant usually comprises a large portion of the total mass of launch vehicles and spacecraft, so liquid propellant sensing, as well as predicting and controlling the motion of it, are important. Electrical Capacitance Tomography (ECT) is an emerging sensing technology that is capable of measuring the distribution of liquid anywhere inside of a tank, potentially making it useful for measuring slosh and gauging mass. An ECT-instrumented tank was successfully tested in microgravity for the first time. Basics of …

How Students Learn: Examining The Differences In Learning Strategies Between Flight And Nonflight Students, Jennifer A. Torres

Theses and Dissertations

The purpose of this study was to determine if there were any differences in learning strategies between undergraduate flight and nonflight students attending a 4-year university that offered a Part 141 flight training program. Learning strategies were measured using Panadero et al.’s (2021) 30-item Deep Learning Strategies Questionnaire and its four subscales—Basic Learning Self-Regulation Strategies, Visual Elaboration and Summarizing Strategies, Deep Information Processing Strategies, and Social Learning Self-Regulation Strategies—all of which were the dependent variables. The primary independent variable was group membership, but the study also incorporated two covariates—self-efficacy and intrinsic value—which were measured using the respective subscales of Pintrich …

Safety Culture Surveys: Towards A Unified Method, Brandon Judy

Theses and Dissertations

This thesis examines the relationship between two aviation safety culture scales: the Airline Safety Culture Index (ASCI; Flight Safety Foundation, 2001) and the Organizational Safety Culture Questionnaire (OSCQ; Patankar, 2003). This study compared two safety culture instruments using a correlational methodology. The two scales were combined into a questionnaire distributed to hundreds of aviation students and professionals. The students were sampled using a stratified cluster sample method, and the professionals were sampled using a snowball method. There were 259 initial usable responses; after outliers were removed, the sample size was 244. A Pearson’s product-moment correlation found that the ASCI and …

Design Space Visualization And Exploration For Many Goal Problems Under Uncertainity, Niharika Balaji

Theses and Dissertations

ABSTRACT

Designing a complex engineered system is challenging due to many conflicting goals, uncertainties, and multiple interactions. Traditional optimization approaches often yield single-point solutions, which may not be suitable for early design stages due to their susceptibility to changes in conditions and uncertainties. To address this challenge, a satisficing approach is employed. This approach enables designers to effectively navigate the design space and identify satisficing solutions that balance conflicting goals in the face of uncertainties and changes in conditions. From a systems design perspective, we view design as an iterative process that involves making informed decisions based on available information …

Metasurface Beam-Steering Antenna At X-Band Frequencies With Cloaking Applications, Erik Jermaine Kosh

Theses and Dissertations

I intend to use metasurface materials to adjust antenna field properties while applying a cloaking application to the antenna. Cloaking applications have been used to shield the neighboring antenna waveforms so that they do not affect it’s antenna patterns and reduce the mutual coupling between the two antennas [15], [16]. In this application, I propose a metasurface beam-steering antenna at X-band frequencies using mantle-cloaking techniques to adjust and direct the beam-steering while ignoring other adjacent antenna patterns.

The first part of this application provides a method for cloaking antennas that are close to each other in distance (less than a …

Qasm-To-Hls: A Framework For Accelerating Quantum Circuit Emulation On High-Performance Reconfigurable Computers, Anshul Maurya

Theses and Dissertations

High-performance reconfigurable computers (HPRCs) make use of Field-Programmable Gate Arrays (FPGAs) for efficient emulation of quantum algorithms. Generally, algorithm-specific architectures are implemented on the FPGAs and there is very little flexibility. Moreover, mapping a quantum algorithm onto its equivalent FPGA emulation architecture is challenging. In this work, we present an automation framework for converting quantum circuits to their equivalent FPGA emulation architectures. The framework processes quantum circuits represented in Quantum Assembly Language (QASM) and derives high-level descriptions of the hardware emulation architectures for High-Level Synthesis (HLS) on HPRCs. The framework generates the code for a heterogeneous architecture consisting of a …

Component Approach For A Combined Hurricane Wind And Rainwater Damage And Time Related Expenses Model In Mid/High-Rise Buildings, Zhuoxuan Wei

Theses and Dissertations

This dissertation focuses on mid/high-rise commercial residential buildings (MHRB) vulnerable to wind-driven rainwater ingress during hurricanes. The author developed the WHIP-MHRB model, a new probabilistic vulnerability model funded by the Wind Hazard Infrastructure Performance Center (WHIP-C). This model combines the estimates of rainwater ingress, distribution and propagation, and damage assessments, and time-related expenses (TRE) predictions for MHRB during hurricanes. Embedded within WHIP-MHRB is the WHIP-TRE model, which forecasts repair times, delay times, downtime, and recovery times post-hurricane explicitly.

Furthermore, taking advantage of the new model, this study presents two approaches to address the combined wind and rain vulnerabilities of MHRB …

Assessing The Thermodynamic Potential Of Deep Eutectic Solvents In The Absorption Of Greenhouse Gases Through Computational Methods, Thomas Michael Quaid

Theses and Dissertations

Greenhouse gas (GHG) capture is a fundamental technology in the fight against climate change. Some species of devastating GHGs like fluorinated compounds are released directly to the air from industrial processes. Some GHGs are co-produced in sustainably derived biofuels which require absorptive upgrading. The development of more efficient, cost effective, and environmentally friendly methods of capturing GHG’s from pollutant sources and industrial streams is of utmost importance in the fight against climate change. Deep eutectic solvents have entered the separations stage as potential disruptors to conventional solvent choices for a variety of applications. Deep eutectic solvents (DES) are compounds of …

Accelerating Machine Learning Inference For Satellite Component Feature Extraction Using Fpgas., Andrew Ekblad

Theses and Dissertations

Running computer vision algorithms requires complex devices with lots of computing power, these types of devices are not well suited for space deployment. The harsh radiation environment and limited power budgets have hindered the ability of running advanced computer vision algorithms in space. This problem makes running an on-orbit servicing detection algorithm very difficult. This work proposes using a low powered FPGA to accelerate the computer vision algorithms that enable satellite component feature extraction. This work uses AMD/Xilinx’s Zynq SoC and DPU IP to run model inference. Experiments in this work centered around improving model post processing by creating implementations …

Human-Centric Smart Cities: A Digital Twin-Oriented Design Of Interactive Autonomous Vehicles, Oscar G. De Leon-Vazquez

Theses and Dissertations

Autonomous vehicle (AV) technology is introduced as a solution to improve transportation safety by eliminating traffic accidents caused by human error, which is the leading cause of 90% of accidents. One key feature of AVs is sensing and perceiving their surrounding environment through processing observations collected from the environment. The perception system is essential for an AV to make informed decisions and safely navigate the environment. This study presents an image semantic segmentation algorithm developed in the area of computer vision to improve AV perception. The U-Net-based algorithm is trained and validated using a synthetically generated dataset in a simulation …

Underwater Image Enhancement: A Pipeline For Underwater Computer Visions, Humberto Lebron Rivera

Theses and Dissertations

Ocean exploration has surged in popularity and significance in recent years, including diverse areas like maritime archeology, underwater resources, and submerged structure inspection. The activities mentioned above heavily depend on vision and imagery, a challenge in the unpredictable marine world. This thesis presents a conditional generative adversarial network model for image-to-image translation problems. We designed and trained the model with the end goal of enhancing underwater images. Five metrics were employed for validation to quantify our model’s resulting enhanced images. By doing so, we aim to establish a pipeline that can leverage aerial computer vision algorithms for marine applications.

Our …

Stability And Control Flight Testing Of A Modified Cessna 172, Tatiana Dirrigl Forbes

Theses and Dissertations

The Cessna 172N is a small, fixed-wing, single-engine aircraft. The modified Cessna 172N included a swapped engine to a Lycoming O-360-A4M, tuned exhaust, and variable timing ignition installed. Test flights on this aircraft were performed order to evaluate the stability and control characteristics of the Cessna 172N, and compare them with the regulations in the Title 14 CFR Part 23 Airworthiness Standards for Normal, Utility, Acrobatic, and Commuter Category Airplanes. The flight test consisted of four separate tests performed during a single flight, departing from and returning to Melbourne Orlando International airport (KMLB). The data was collected through static and …

Development Of A Physics-Informed Neural Network For Prediction Of Blood Flow, Marcello Vittorio Mattei Di Eugenio

Theses and Dissertations

Abstract—Objective: We propose a new neural network architecture that accepts point clouds and outputs 3D velocity profiles for aneurysm geometries. Methods: We generated a synthetic aneurysm 3D flow dataset using CFD and used it to train our model architecture and compare it with other popular architectures like U-net and PointNet. We incorporate tools for improving model performance such as incorporating a distance function, a physics-informed loss to enforce the law of mass conservation, and the Huber loss to learn patterns across heterogeneous velocity components of multiple dimensions. Results: The tools implemented together with our architecture achieved the best performance on …

Effects Of Perforations On Internal Cathodic Protection And Recruitment Of Marine Organisms To Steel Pipes, Alexander John Paluzzi

Theses and Dissertations

Steel monopile support structures for offshore wind turbines require protection from corrosion on their external and internal surfaces. Cathodic protection (CP) works effectively to protect the external surfaces of monopiles, but internally, byproducts from aluminum sacrificial anode CP (SACP) and impressed current CP (ICCP) induce acidification that accelerates steel corrosion. This project investigated the effects of perforations on the performance of aluminum SACP and ICCP when used inside of steel pipes. Additionally, marine growth on the external and internal surfaces of the pipes was assessed to determine if CP byproducts affect marine organism development.

Two sealed and two perforated steel …

Optimization Of High-Order Statistical Moment Combinations To Best Represent Spray Flow Particle Probability Density Functions, Amanda Lynn Myers

Theses and Dissertations

Characterizing spray flows has been an issue of interest for years, particularly in regards to fuel injection in engines. Droplet velocity and diameter, among other characteristics, are crucial to understanding spray flows. One approach for determining these quantities in a spray is using a statistical approach that solves for the moments of droplet characteristics as they evolve in space and time. A theoretical probability density function (PDF) can be formulated using various combinations of moments which evolve according to derived moment transport equations (thus evolving the PDF), using the principle of maximum entropy as closure to the system. Building upon …

Investigating The Effects Of Collagen Alignment And Tricalcium Phosphate Incorporation On Osteoblast Cell Response, Kathryn Elizabeth Bock

Theses and Dissertations

Every year, over 20 million people globally are affected by bone tissue loss due to disease or trauma. Bone tissue engineering (BTE) is touted as a promising approach to promote bone tissue repair and regeneration. In this realm, development of collagen-based scaffolds incorporated with a bioceramic is often attempted to generate tissue scaffolds that resemble the organic and inorganic composition of native bone. In addition, a variety of different collagen processing techniques have been employed to produce anisotropically aligned scaffolds that can provide the essential biochemical and structural cues to guide cell response. While there have been numerous studies on …

Investigation On Mechanical, Tribological And Corrosion Resistance Properties Of Nano Sized Tio2/ Corrosion Resistance Properties Of Nano Sized Tio2/ B4c / Graphene Reinforced Aa 7075 Surface Composites B4c / Graphene Reinforced Aa 7075 Surface Composites Fabricated By Frictional Stir Processing Fabricated By Frictional Stir Processing, Majed Mohammed Hotami

Theses and Dissertations

Today, significant research efforts in the field of manufacturing engineering are focused on developing new lightweight, fuel-efficient and high-performance materials. The evolution of composite materials and related technologies has brought great advantages to material development throughout history. Composites are versatile materials with unique mechanical and physical properties tailored to specific application needs. Composites allow engineers to make design choices that traditional monolithic (unreinforced) materials cannot offer. Particle Reinforced Metal Matrix Composites (MMCs) offer a variety of advantages, including increased stiffness, improved fatigue resistance, increased wear resistance, and a low coefficient of thermal expansion. Aluminum MMC (AMMC) material systems outperform monolithic …