Engineering Commons^™

Design And Development Of A Clinical Decision Support System For The Diagnosis Of Parkinson’S Disease Using Artificial Intelligence, Saravanan S

Theses and Dissertations

Parkinson’s disease (PD) is a degenerative neurological condition marked by motor symptoms like tremors, bradykinesia, and stiffness. It is observed that early and precise diagnosis of this disease is crucial, as that will have a significant impact on effective disease management and intervention. This thesis explores the technical feasibility of applying AI techniques to recognize patterns from spiral and wave drawings, which are usually a unique signature type for PD patients.

The focus of the work is to diagnose the disease through novel deep transfer learning techniques, to diagnose the severity of the disease, and also to develop effective model …

Heat Transfer To Arrays Of Oscillating Impingement Jets, Alex Q. Clay

Doctoral Dissertations and Master's Theses

In gas turbine engines, the desire to increase turbine entry temperatures has become more relevant in order to increase engine efficiency. However, materials used in these engines can only withstand temperatures that are so high. Because of this, the ability to cool hot section components will always limit operating temperatures. Impingement cooling jets have become a common way of cooling due to the high rates of heat transfer that can be achieved. However, previous research has shown that the interaction of impingement jets with cylinder wake can improve the intensity and uniformity of heat transfer. The goal of this study …

Development And Application Of A Particle-Based Reactor Network Model For Entrained Flow Gasifier Design, Eric Christian Monson

Theses and Dissertations

A novel particle-based reactor network model (PRNM) was developed to predict the performance of a dry-feed, pressurized, single-stage, slagging entrained flow gasifier under various operational parameters. This model provides improved detail of particle conversion as a function of gasifier location, particle size, and fuel type not available in standard reactor network models. The model inputs were designed to allow changes in geometry, firing rate, stoichiometric ratio, fuel type, and inlet gas composition. Key performance metrics included the gas and refractory temperature profiles, axial gas compositions, and particle burnout. PRNM used a network of idealized reactors to specify the flow field …

A Personalized Chat Application For Career Profiling: A Case Study, Dhiraj Choithramani

Harrisburg University Dissertations and Theses

Artificial intelligence (AI) has rapidly transformed numerous fields over the past decade, significantly influencing industries such as software engineering and computer science. One of the most impactful developments in this area is the rise of AI-driven chat applications, which have evolved from simple, rule-based systems to sophisticated platforms capable of simulating human-like conversations. These chatbots are increasingly being utilized across various sectors, including customer service, healthcare, and education, to provide users with quick, personalized responses. This research paper presents a case study of a personalized chat application designed specifically for career profiling, leveraging advanced AI technologies to deliver contextually relevant …

Environmental Impacts Potential Of Natural Gas Production Through Life Cycle Assessment, Akmal Al Afghani, Mochamad Adhiraga Pratama, Astryd Viandila Dahlan

Journal of Materials Exploration and Findings

Life cycle assessment (LCA) is a methodology used to evaluate potential environmental impacts in various industry sectors, including the oil and gas industry to quantify the environmental impacts and determine the processes that have significant impacts along their production cycle. This environmental impact study adheres to ISO 14040:2016 and 14044:2017 standards, using the ReCiPe methodology within a gate-to-gate scope to analyze potential environmental impacts of 1 MMSCFD natural gas production. The impact categories analyzed in this study are Global Warming Potential (GWP), Particulate Matter Formation (PM), Ozone Formation (OF), and Terrestrial Acidification (TA). The results of this study identified several …

Implementation Of Machine Learning Using Deep Neural Networks To Estimate The Failure Risk Caused By Leakage In Pressure Relief Devices, Adi Yudho Wijayanto, Yossi Andreano, M. Ali Yafi Rizky, Dedi Priadi

Journal of Materials Exploration and Findings

The primary objective of deploying Pressure Relief Device (PRD) equipment is to ensure the safety of pressure vessels within a pressurized system. Over time, PRD equipment may degrade and fail to perform its intended function, which must be identified as a failure mode. To mitigate potential risks associated with this, it is recommended that an approach such as risk-based inspection (RBI) be implemented. Despite the widespread adoption of RBI, the method relies on qualitative techniques, leading to significant variations in equipment risk assessments. This study proposes a novel risk analysis method that uses deep learning-based machine learning to develop a …

Inspection Planning Of Subsea Pipeline Using Risk-Based Inspection, Ni Luh Triska Adelia, Badrul Munir, Johny Wahyuadi Soedarsono

Journal of Materials Exploration and Findings

Pipelines are an important tool in oil and gas exploration. Pipeline is a transmission and liquid collection lines, including their accessories, which transport fluids from one plant to another. In transmission and collection process, there is a possibility of failure which can have minor to major impact on personnel injury, the environment and interrupt the business process. To maintain safety and to prevent accidents, the source and cause of failure needs to be calculated. Risk-based inspection (RBI) is a method that can be used to calculate the risk and determine the inspection planning both schedule and method, by combining the …

Effect Of Impurities In Supercritical Co2 Environment On Steel Corrosion Behavior – An Overview, Shilla Rizqi Widianto, Johny Wahyuadi Soedarsono, Rini Riastuti, Badrul Munir

Journal of Materials Exploration and Findings

Carbon capture, utilization, and storage (CCUS) technology is one of the available technologies to reduce presence of greenhouse gasses. Implementation of CCUS technology strongly relates with the CO₂ transportation from the capturing facility to the storage in the geological reservoir. The most economical method for large-scale and long-distance CO₂ transportation is using pipeline in supercritical phase. Moreover, presence of impurities such as water, O₂, SO₂, H₂S, NO₂ may cause detrimental effect towards carbon steel pipeline. This paper intends to provide an initial information for supercritical CO₂ pipeline material selection, which …

Feasibility Study Of Using Energy Extracted From The Process Of Electrochemically Consumed Of Al 2024 For Powering Daily Used Electric Car, Yanuar Mohamad Marda, Rini Riastuti, Muhammad Hamka Ibrahim

Journal of Materials Exploration and Findings

Usage of green energy for transportation has become important due to the contribution of transportation activity to climate change. Electrochemical energy has been used as a source of green energy. The objective of this work is to evaluate sufficiency of energy provided by electrochemically consumed Al 2024 for supplying energy to daily used PHEV electric car. Study of previous articles, observation of typical amount of energy required, electrochemical galvanic cell experiments, and simple calculations have been conducted to determine produced energy feasibility. Electrical energy produced by consuming 340 gr of Al 2024 in galvanic cells has the total lifetime of …

Maintenance Notes To Improve The Reliability Of Wheel Flange Failure For Overhead Crane, Fakhri Burhanuddin, Akhmad Herman Yuwono

Journal of Materials Exploration and Findings

Overhead traveling cranes in the industry have utility workload classifications and require high standards of safety and reliability by mobilizing lifting and transporting capacity variants of steel products, equipment, and other supports. The crane wheels are the main support in moving the end carriage so that the crane can work according to its function. Failures in the operation and maintenance cycle have occurred. Therefore, proper repair and maintenance methods are highly needed to restore the original design function to its working integrity. Logic tree analysis was used to breakdown all causes of failure; thus, mitigation was performed by carrying out …

Hollow Connecting Rod Thin Wall Austempered Ductile Iron (Twadi) For Manufacturing Light Weight Components, Ricardina Freitas Da Silva, Bambang Suharno, Rianti Dewi Sulamet-Ariobimo

Journal of Materials Exploration and Findings

Efforts made by the automotive industry to reduce energy consumption have encouraged researchers to carry out various studies. One way is to make components lighter by casting thin wall austempered ductile iron (TWADI). Reducing the weight of components such as connecting rods (conrod) will result in lower energy consumption, but provided that these components still meet standards in terms of mechanical properties and microstructure or even exceed them. In this research, design optimization was applied to conrod by making the area I-beam zero mm (hollow), with hope that it can replace conrod Vespa PX-150. While the manufacturing process is divided …

Analysis Risk Based Inspection Api 581 On Lpg Spherical Tank At Pt. Xyz, Sigit Trahmawan, Eddy Sumarno Siradj, Jaka Fajar Fatriansyah

Journal of Materials Exploration and Findings

Liquified petroleum gas (LPG) spherical tanks are pressure vessel equipment for storing fuel gas products. The high pressure along with the fuel gas inside as flammable and combustible substance means that this equipment might result major accident hazard such as explosion, fires and environmental pollution. This study is aimed calculated and mitigate risk on 500 metric ton capacity LPG spherical tank using Risk-based inspection (RBI) analysis method that makes risk as its foundation. This RBI method uses quantitative analysis referring to API 581 to determine the risk of LPG Spherical Tank by determining the probability of failure (PoF) and the …

Design And Validation Of Sensing Knee Sleeve Rehabilitation Device Utilizing Large Deflection Strain Gauges, Kurt Christian Jensen

Theses and Dissertations

Total knee arthroplasty (TKA) procedures are increasingly common in the US and globally. However, rehabilitation outcomes may be negatively affected by limited access to physical therapy and patients' tendency to not fully adhere to recommended exercises between therapy sessions. This study aims to develop a remote system to aid rehabilitation, building upon recent sensor development at Brigham Young University, providing physical therapy-like biofeedback during unsupervised at-home exercises. The system developed by this research consists of three primary components: (1) a sensor array for measuring leg/knee biomechanics, (2) a machine learning algorithm to predict knee flexion angle from the sensor data, …

Root Cause Analysis Of Leakage Tube Boiler: A Study Case, Lydia Kartika Basaria Sitompul, Dedi Priadi

Journal of Materials Exploration and Findings

Oil and gas industry can have catastrophic implications for human life, the environment, and the economy. This paper investigated failure analysis using root cause analysis especially for boiler tube leakage of Heat Exchanger. Identify the issue using microscopic examination and energy dispersive x-ray analysis were conducted on the tube inside and outside surface to determine root cause of the failure. The formation of a protective film in the aluminum-brass tube during the starting stage is very important for ensuring adequate film protection throughout the service life of the heat exchanger. During this stage, exposure to unpolluted water is essential. The …

Lifetime Prediction Of Pan Feeder Based On 3d Laser Scanning For Wear Assessment, Nony Maulidya, Dedi Priadi, D. Rizal Asral

Journal of Materials Exploration and Findings

Apron feeder is one of stages in crushing circuit to convey material in short distance. Pan flight is the main component of apron feeder that is severely exposed to wear mechanism due to its direct contact with open cut abrasive ore. With this operating environment of apron feeder, regular maintenance and inspection must be conducted to assess wear rate of pan’s surface to maintain equipment availability and provide information and sign before the equipment undergoes severe and sudden degradation. 3D laser scanning is method used in this study as Non-Destructive Testing (NDT) based inspection. The aim of using 3D scanning …

Acousto-Dielectric Tweezers Enable Independent Manipulation Of Multiple Particles, Liang Shen, Zhenhua Tian, Kaichun Yang, Joseph Rich, Jinxin Zhang, Jianping Xia, Wesley Collyer, Brandon Lu, Nanjing Hao, Zhichao Pei, Chuyi Chen, Tony Jun Huang

Faculty Publications

Acoustic tweezers have gained substantial interest in biology, engineering, and materials science for their label-free, precise, contactless, and programmable manipulation of small objects. However, acoustic tweezers cannot independently manipulate multiple microparticles simultaneously. This study introduces acousto-dielectric tweezers capable of independently manipulating multiple microparticles and precise control over intercellular distances and cyclical cell pairing and separation for detailed cell-cell interaction analysis. Our acousto-dielectric tweezers leverage the competition between acoustic radiation forces, generated by standing surface acoustic waves (SAWs), and dielectrophoretic (DEP) forces, induced by gradient electric fields. Modulating these fields allows for the precise positioning of individual microparticles at points where …

Charlotte: A Modern Tool For Cave Surveying, Luca Tringali Mr., Giacomo Canciani Dr., Alexander Debenjak, Tecla Tripari

International Journal of Speleology

The future of cave surveying is a full 3D scan, as automatic as possible, capturing all morphologically relevant details. However, the vast majority of cavers are still using tools designed more than 15 years ago. The advancements in tools for architects, CAD designers, programmers of VR and robotics could be helpful also for the caving community. That’s why Charlotte, a cheap DIY 2.5D scanner designed for cave surveying, was developed and built. To demonstrate its capabilities, a new survey of Grotta Regina del Carso cave (cad. nr. 2328/4760VG), the biggest cave in the Gorizia Karst, has been realized and published. …

Final Report - Integration Of Aerial Manipulation, Haptics-Based Human-In-The- Loop Control, And Augmented Reality For Bridge Deck Hosing, Paul Oh, Blake Hament, Dongbin Kim

Project AS-9

This Year 5 and Year 6 report integrates the designs, analyses, and results of the previous years. These have culminated into the design, development and deployment of a hosing-drone. This drone carries and 3000 PSI (pounds per square inch) pressure washer often used to clean bridges. This accomplishment leverages the work in aerial manipulation, human-in-the-loop control, haptics, and augmented- and virtual-reality (AR/VR) executed in prior years. Additionally, this report presents results using a cable-driven parallel robot (CDPR) and telescopic mast. This robot provides another platform that has applications in bridge inspection, maintenance and repair.

A Step Towards Automated Ethical Analysis In Journalism: Measuring Llms’ Performance In Extracting Sourcing Information, Jingsen Wang

Computer Science and Engineering Master's Theses

This thesis explores the potential of Large Language Models (LLMs) in automating the extraction of sourcing information from news articles, a crucial step towards enhancing transparency and ethical analysis in journalism. We evaluate the performance of two state-of-the-art LLMs, GPT-4 and Claude 3, in identifying and categorizing various source types across four diverse news articles. The thesis employs a zero-shot learning approach with two different prompt designs, assessing the models’ ability to adapt to varying source structures and prompt instructions.

Our findings reveal that while LLMs show promise in extracting sourcing information, their performance varies significantly across different article types …

Degradation Study Of Single Crystal Barium Titanate Capacitors Under Harsh Environment, Menglin Wang

Electrical Engineering Theses and Dissertations

Capacitors are critical for voltage source converter functionality. DC-link capacitors are known to have reliability issues. Resistance degradation at high temperatures is one of the primary failure modes in capacitors. The overall goal of this program is to improve the understanding of high voltage breakdown and resistance degradation in high dielectric constant inorganic ceramic capacitors, using single crystal BaTiO₃ as a model system to understand the impact and control of oxygen vacancy migration to maximize the long-term reliability of high voltage inorganic multi-layer ceramic capacitors, which allows higher frequency operation, reducing the size and cost of passive components in …

Projected Climate Change Impacts On The Number Of Dry And Very Heavy Precipitation Days By Century’S End: A Case Study Of Iran’S Metropolises, Rasoul Asfari, Mohammad Nazari-Sharabian, Ali Hosseini, Moses Karakouzian

Civil and Environmental Engineering and Construction Faculty Research

This study explores the impacts of climate change on the number of dry days and very heavy precipitation days within Iran’s metropolises. Focusing on Tehran, Mashhad, Isfahan, Karaj, Shiraz, and Tabriz, the research utilizes the sixth phase of the Coupled Model Intercomparison Project (CMIP6) Global Circulation Models (GCMs) to predict future precipitation conditions under various Shared Socioeconomic Pathways (SSPs) from 2025 to 2100. The study aims to provide a comprehensive understanding of how climate change will affect precipitation patterns in these major cities. Findings indicate that the SSP126 scenario typically results in the highest number of dry days, suggesting that …

Activity Map Generation And Event-Based Sensor Processing With Spiking Autoencoders And Sparse Dictionary Learning, Jack Easton

Computer Science and Engineering Theses and Dissertations

This thesis explores the potential of Spiking Neural Networks (SNNs) in processing event sensor data and generating high-fidelity activity maps. Event sensors capture asynchronous binary events with high dynamic range, but traditional processing methods often fail to leverage their advantages fully. SNNs, with their asynchronous, event-driven nature, offer a promising alternative.

A Spiking Autoencoder (SAE) was employed in this thesis to handle the stochastic and sparse event data, integrating deep dictionary learning to enhance the feature space and improve activity map quality. The encoder, modeled after the VGG network, extracts features from event streams generated by speckle patterns, which are …

Empty State Electronics, Reza Farsad Asadi

Electrical Engineering Theses and Dissertations

Field emitter arrays (FEAs) have the potential to operate at high frequencies and withstand harsh environments, such as radiation and high temperatures. However, they are sensitive to gaseous environments. This study examines the impact of different gas environments on silicon (Si) and gallium nitride (GaN) FEAs. To investigate the failure mechanisms, a vacuum system was designed and fabricated to monitor emission uniformity using a phosphor screen. Additionally, a vacuum system was created to introduce high-purity gases into the chamber while operating the devices. The results indicate that both types of FEAs are susceptible to oxidizing environments. Argon (Ar) did not …

Development Of A Nephelometer For Characterization Of Calcium Oxalate Crystal Concentrations Within Solution, Conrad Small

Electrical Engineering Theses and Dissertations

The prevalence of kidney stones has been steadily increasing over the last 30 years, affecting both men and women across all age groups. This rise is largely attributed to lifestyle changes associated with technological advancements, such as more sedentary lifestyles, dietary shifts towards more processed foods, and an increased incidence of metabolic diseases like diabetes. Despite the growing prevalence of kidney stones, the methods for early detection have remained relatively unchanged. Current testing involves collecting urine samples over a 24-hour period and sending them to a lab for microscopic and dipstick analysis. This process provides a comprehensive overview of urine …

Predictive And Prescriptive Analytics For Minimizing The Cost Of Recidivism, Adreana Julander

Operations Research and Engineering Management Theses and Dissertations

A problem faced by the United States is the ever increasing prison population. There are inmates serving long sentences, new inmates being sentenced for the first time, and those who have previously served prison sentences that reoffend. The third group and the reduction of recidivism are the focus this dissertation. It is estimated that over 80% of inmates released from prison will reoffend within the next ten years. Is there an optimal sentence length that reduces that chance of an ex-convict reoffending? Are there programs or opportunities that some inmates have while incarcerated that reduce the probability they will return …

A Fair Ontology For Aps Beamline Experiments, Gabriel Ponón, Balashanmuga Priyan Rajamohan, Mohommad Redad Mehdi, Finley Holt, Erika Barcelos, Pawan K. Tripathi, Roger H. French

Student Scholarship

Data produced at the 1-ID beamline APS are often serialized in large, disconnected tables, which can impede the effective reuse and replication of analysis performed for cutting edge research and instrumentation conducted at the facility. This poster describes an alternative approach of utilizing component-based FAIR (Findable, Accessible, Interoperable, and Reusable) ontologies as a framework for organizing and connecting experimental variables. Three packages were developed to facilitate the creation and connection of component ontologies into a fully connected FAIR ontology for an experiment. An ontology-based workflow is also discussed for beamline scientists and users to visualize and connect collected values alongside …

Knowledge Management Of Historical Data: Ontology Development For Chemical Reactions, Quynh D. Tran, Alexander Harding Bradley, Balashanmuga Priyan Rajamohan, Jonathan E. Gordon, Van D. Tran, Kiefer Lin, Erika I. Barcelos, Laura S. Bruckman, Roger H. French

Researchers, Instructors, & Staff Scholarship

Knowledge management of the literature and historical data is critical to accelerated drug and materials discovery. Currently, literature knowledge is scattered in journal articles in various formats: diagrams, texts, plots, etc. Historical data from past experiments are saved in a number of local computers under confusing folder structures with ambiguous file names. To manage and organize historical data and knowledge, our group (SDLE) at CWRU follows FAIR (Findable, Accessible, Interoperable, Reusable) principles, which outline the best practices for data stewardship and data provenance, and ontology, a formal representation of terms and concepts and their relationships, as a tool to improve …

Uncertainty Quantification In Machine Learning Models Via Gaussian Process Regression: A Comparative Study, Ayorinde E. Olatunde, Weiqi Yue, Pawan K. Tripathi, Roger H. French, Anirban Mondal

Faculty Scholarship

As the use of Machine learning models in science and engineering continues to increase, there is an increasing need for quantifying the uncertainties inherent in the predictions of these models. The more complex a model is, the more the uncertainties in its predictions increase. Amongst the plethora of methodologies used in quantifying uncertainties lies Gaussian Process Regression (GPR). GPR surmounts some of the popular shortfalls of other state-of-the-art methodologies. Although GPR has some quick wins in its application for uncertainty quantification, it is plagued with some shortfalls, such as scalability issues when the feature space increases as well as an …

Enhancing Fundraising Strategies In Higher Education Through Machine Learning, Laith Alatwah

Electrical Engineering Theses

This thesis presents a comprehensive application of machine learning techniques, namely Fine Gaussian SVM and RUS Boosted Trees, to enhance fundraising strategies in higher education institutions. Analyzing a rich dataset from Blackbaud Raiser's Edge NXT, spanning 2012 to 2022, the study focuses on donor profiles, including demographics, donation history, and engagement patterns. Key demographic insights include the increasing engagement of younger donors (20-29 age group) and significant contributions from older donors (70-99 age group). Geographical trends are also examined, revealing distinct patterns based on donors' city, state, and ZIP code. The Fine Gaussian SVM model demonstrates moderate discriminatory power, with …

Modeling Advancement In Spacefaring Through Deep Learning, Peng-Hung Tsai

Theses and Dissertations

Predicting advancement in space exploration technology allows space agencies and companies to strategically allocate resources, prioritize missions, and explore collaborations on complex projects. This foresight acts as a roadmap for future exploration, making the best use of valuable resources. The present study employs spacecraft lifetimes as an exemplar of technological progress and proposes a novel forecasting model based on Long Short-Term Memory (LSTM) networks. Existing research often suggests an increasing exponential relationship between technology performance and time (the generalized Moore's Law). However, applying this model directly to spacecraft lifetimes has a limitation. Spacecraft lifespans are unknown at launch, and recent …