Engineering Commons^™

A Bert-Based Model For Classifying Customers In The Financial Sector: A Case Of Zb Bank, Fungai Jacqueline Kiwa, Martin Muduva

African Conference on Information Systems and Technology

This study explores the implementation of a BERT-based model in ZB Bank, Zimbabwe, to improve complaint management and enhance customer satisfaction. Traditional manual handling of client complaints leads to slow responses and unresolved issues. The study aims to develop an accurate complaint classification model using advanced Natural Language Processing (NLP) and machine learning techniques, specifically the BERT model, and assess its real-world performance. The methodology involved collecting a dataset of customer complaints from ZB Bank, pre-processing the text data, and applying the BERT model within the Team Data Science Process (TDSP). The dataset was split into training (80%) and testing …

Anomalous Transaction Detection In Bank Credit Card Data Using Machine Learning, Lerdinia Varaidzo Mapepa, Jerremiah Musariwa, Lucia Makwasha, Samuel Mugijima

African Conference on Information Systems and Technology

Illegal money changers pose a number of risks to the financial system, including but not limited to money laundering, fraud, and other under-the-carpet dealings intended to frustrate regulatory efforts for financial integrity. The efficiency and accuracy of anti-money laundering (AML) measures using machine learning (ML) models in the detection of suspicious patterns in bank card transactions are investigated in this paper. The key focus will be to develop an efficient machine learning framework that should be proficient in underlining main transactions dealing with illegal money changers and other similar fraudulent activities. The features indicative of illicit behaviour are determined by …

Ai Bioelectricity Management System, Fungai Jacqueline Kiwa, Tawanda Bundukutu, Thoko Matnell Mawoyo, Batsiranai Linda Chiduku, Martin Muduva, Belinda Ndlovu

African Conference on Information Systems and Technology

This document emphasizes on the generation of electricity from trees and its usability in all the sectors of Zimbabwe. The research focused on positively changing the lives of citizens through the provision of uninterrupted and reliable bioelectricity. The literature review was completely and accurately performed through finding out the current news associated with the use of trees in producing electricity and the use of AI to manage the flow. The Scrum’s development model was adopted and followed during the research project to address issues like transparency, early mitigation of risks and constant feedback. The Scrum-model is one of the best …

Reconciling Modern Engineering Education With The Everyday Of Rural Schools And Youths, Malle R. Schilling, Jacob R. Grohs

Journal of Pre-College Engineering Education Research (J-PEER)

We highlight the impacts of inequitable distributions of resources across geographies, structural challenges faced in partnerships with rural schools, and the importance of asset-based arguments to recognize and engage with systemic challenges. Precollege engineering education often focuses on engaging students and teachers hands-on with novel technologies and experiences that frequently distract from systemic inequities, particularly pertaining to place. Given national efforts in rural STEM education, there is a need to recognize important contextual factors influencing precollege engineering education. Through a lens of working with rural Appalachian schools, we hope to challenge practices and assumptions in precollege engineering education.

Prediction Of Moisture Resistance Of Aggregate Binder System Through Physicochemical And Mechanical Assessment, Khaja Sameer Sadat

Student Theses and Dissertations

Moisture sensitivity has been a significant factor in pavement deterioration for several decades. The primary objective of the proposed research is to quantify the interface-level adhesion forces between bitumen samples and various types of aggregates. Aggregates and binders from varying sources with an anti-stripping agent were utilized for routine tests, micro-level tests, and elemental analysis. Pneumatic Adhesion Tensile Testing Instrument (PATTI) was discovered to be a more straightforward, simple, and repeatable adhesion testing method. The PATTI test revealed that sandstone exhibited higher adhesion values due to its greater porosity and absorption potential than limestone. The Texas Boiling test removed human …

Fine-Tuning Cesium Lead Chloride Perovskite Field-Effect Transistors For Sensing Applications: Bridging Numerical Modeling And Experimental Validation, Gehad Ali, Reem Mahmoud, Mohamed Wafeek, Motaz Yousef, Sameh O. Abdellatif

Electrical Engineering

No abstract provided.

Application Of Process Mining Algorithms To Surgical Training: A Study Of Healthcare Settings, Fazla Rabbi

Student Theses and Dissertations

Healthcare professionals must be experts at carrying out complex surgical procedures to fulfill their responsibilities. The aim of the medical treatments is fewer complications, shorter hospital stays, and a better patient experience. They often report on problems with surgical processes, skipped procedures, and lengthy transition times. The event log data allows process mining methods to deliver professionals with understandable findings using Petri Net. This study identifies the parallels and discrepancies between the pre-and post-stages and their respective frequency on each typical Central Venous Catheter (CVC) installation activity, where pre-stage they were given a briefing, and in post-stage they had hands-on …

Air Content Variation In Concrete At Different Stages Of Its Lifecycle, Mohammad Sarfaraz Uddin

Student Theses and Dissertations

In cold climates, concrete structures are susceptible to deterioration from the freezing and thawing of water within the concrete. The arrangement of air voids is crucial for the concrete to endure the freeze-thaw cycles. This research investigates changes in the air void system within concrete using a super air meter and the properties of both fresh and hardened concrete at various stages, including mixing and after pumping. Laboratory mixes used different dosages of air-entraining admixes and included Rice Husk Ash (RHA) as a supplementary material. Adding RHA to the mix resulted in a decrease in air content of about 2.2%, …

Application Of Haines And Terbrugge Chart For Suitable Slope Angles – A Case Study Of Artisanal And Small-Scale Mining, Carol Mgiba, Steven Rupprecht

Journal of Sustainable Mining

Significant hazards in Artisanal and small-scale mining (ASM) are rock failure and slope collapse caused by overly steep pit walls, poor mine design and water pressure. There is a lack of expertise and capital in ASM. Providing a simple and cost-effective slope stability analysis and designing systems that can mitigate the risk of slope collapse is essential. This article aims to assess whether stability charts and estimations can be used to establish suitable slope angles to mitigate the overwhelming cases of slope collapse in ASM. The Bieniawski’s Rock Mass Rating system and Heins and Terbrugge stability chart were used to …

Review Of Hardware Implementation For The Two-Wheeled Self-Balancing Robot, Ghaidaa Hadi Salih Elias

Al-Bahir

The working principle of a self-balancing robot is similar to that of an inverted pendulum, with the mobile robot's controller playing a crucial part in both self-balancing and stabilization. It is the kind that constantly modifies itself to keep balance when it rides on two wheels. This review will center on the basic construction of the suggested robot, summarize the recent studies relative to control methods and the building of the two-wheeled self-balancing robot, and discuss the outcomes of control experiments conducted on hardware systems. It will assist researchers in building and designing two-wheeled mobile robots in the future.

Advanced Transistor-Based Dynamic Equivalent Circuit Modeling Of Mesostructured-Based Solar Cells, Eman Farouk Sawires, Sameh O. Abdellatif

Electrical Engineering

This study introduces a pioneering transistor-based equivalent circuit model explicitly tailored for mesostructured-based solar cells, primarily focusing on dye-sensitized solar cells (DSSCs) and perovskite solar cells (PSCs). By incorporating the experimental data spanning various inorganic, organic, and hybrid solar cell technologies across different optical injection levels, the model aims to provide a comprehensive understanding of the electrical behavior of these advanced photovoltaic devices. In addition to the circuit schematic, a Verilog-A script was created to elucidate the behavior of the cells, facilitating the utilization of such a block by the research community in developing interfacing circuits and implementing dc–dc converters …

Development Of Bio-Based Organogels For The Replacement Of Silicone Elastomers In Cosmetic & Personal Care Applications, Courtney A. Lemasney

Theses and Dissertations

Silicone elastomers (SE) are a major component in many cosmetic and personal care products, providing excellent spreading properties, leaving a dry, silky feel on the skin. Unfortunately, the manufacturing of silicone is a high energy consuming process, and these products are not biodegradable. Capryloyl/glycerin/sebacic acid (CGS) copolymers are an economical, nontoxic platform for synthesizing bio-based materials with tailored properties. These polyester networks are formed through esterification with water as its only side product. By altering feed ratios and reaction conditions, final products can vary from branched fluids to highly crosslinked elastomers. This thesis investigated controlling the crosslink density of the …

Effective Integration Of Waste Plastics In Hot Mix Asphalt Mixtures: Towards Sustainable Infrastructure, Venkatsushanth Revelli

Theses and Dissertations

The study investigated the potential of waste plastics such as low density polyethylene(LDPE), high density polyethylene(HDPE), polyethylene terephthalate(PET) and polystyrene (PS) for designing superior performing asphalt mixtures. Both wet mixing and dry mixing methods were adopted for designing plastic modified asphalt mixtures. Initially LDPE and HDPE were selected for developing plastic modified binders, based on melting characterization, determined from differential scanning calorimeter(DSC). In wet mixing process, the influence of dosage, size of plastic, blending duration and interaction between plastic and asphalt were assessed. Plastics were found to exhibit phase separation with asphalt, while finer particles take only longer to segregate …

Implementing Reactivity In Molecular Dynamics Simulations With Harmonic Force Fields, Jordan J. Winetrout, Krishan Kanhaiya, Josh Kemppainen, Pieter J. In ‘T Veld, Geeta Sachdeva, Ravindra Pandey, Behzad Damirchi, Adri Van Duin, Gregory Odegard, Hendrik Heinz

Michigan Tech Publications

The simulation of chemical reactions and mechanical properties including failure from atoms to the micrometer scale remains a longstanding challenge in chemistry and materials science. Bottlenecks include computational feasibility, reliability, and cost. We introduce a method for reactive molecular dynamics simulations using a clean replacement of non-reactive classical harmonic bond potentials with reactive, energy-conserving Morse potentials, called the Reactive INTERFACE Force Field (IFF-R). IFF-R is compatible with force fields for organic and inorganic compounds such as IFF, CHARMM, PCFF, OPLS-AA, and AMBER. Bond dissociation is enabled by three interpretable Morse parameters per bond type and zero energy upon disconnect. Use …

Mechanical Behavior Of Nixcr Alloys With Ti3sic2 Nanoparticle Inclusions Using Molecular Dynamics, Brendan Martin Crutchfield

Student Theses and Dissertations

Many materials used for solid lubrication are expensive and difficult to replace after abrasive wear, thus new compounds have to be considered and explored for their feasibility in solid lubrication. Nickel-chromium alloys are a potential replacement due to its high chemical and thermal stability, and Ti3SiC2 nanoparticle inclusions are considered to improve the wear rate of these materials. In this study, molecular dynamics (MD) simulations are utilized to assess the mechanical behavior of NixCr (x = 1, 2, 3, 4) alloys with and without Ti3SiC2 nanoparticle inclusions of radii 13, 20, and 27 Å. MD uniaxial tension tests are conducted …

Evolution Of Physical, Thermal, And Mechanical Properties Of Poly(Methyl Methacrylate)-Based Elium Thermoplastic Polymer During Polymerization, Swapnil S. Bamane, Prathamesh Deshpande, Sagar Patil, Marianna Maiaru, Gregory Odegard

Michigan Tech Publications

Elium-based thermoplastic composites are a key material for future use in the marine, wind energy, and automotive industries because of their recyclability and ease of manufacture. To optimize the processing of the Elium composites to yield optimal structural properties, computational process modeling can be used to relate processing parameters to residual stresses and material durability. The key ingredient for reliable and accurate process modeling is the evolution of physical, thermal, and mechanical properties during polymerization. The objective of this study is to use molecular dynamics to predict the mass density, bulk modulus, shear modulus, Young’s modulus, Poisson’s ratio, glass transition …

Big Geospatiotemporal Data Approaches To Monitoring And Mitigating Environmental Impacts In Agriculture, Olatunde D. Akanbi, Vibha S. Mandayam, Erika I. Barcelos, Arafath Nihar, Yinghui Wu, Jeffrey Yarus, Roger H. French

Student Scholarship

This research explores the application of geospatial techniques for global agricultural monitoring, integrating satellite imagery and soil data to assess crop health and soil conditions. Our approach provides actionable insights to improve agricultural productivity and sustainability, addressing food security challenges through advanced machine learning models.

Flexible Load Conformance: A Work-In-Progress White Paper, Dana Paresa, Robert B. Bass

Electrical and Computer Engineering Faculty Publications and Presentations

Utilities have used residential loads for providing grid services to utility customers for decades, particularly for demand response. However, the number of customers participating in such programs remains low. New Flexible Load Management strategies for providing grid services have the potential to accelerate customer participation. Efforts to improve customer participation and experience will result in increased load balancing capacity of demand response, which will benefit both customers and electric utilities. This white paper investigates whether current smart grid devices (specifically water heaters) can provide needed services while meeting ANSI/CTA-2045 standard requirements.

Model Predictive Control Of A Grid-Scale Thermal Energy Storage System In Relap5-3d, Jaron Wallace, John Hedengren, Kody Powell, Matthew Memmott

Faculty Publications

This research delves into the integration and control of a Thermal Energy Storage (TES) system with a Small Modular Reactor (SMR), specifically the NuScale VOYGR SMR module in RELAP5-3D. The research methodology centered on modeling the NuScale VOYGR SMR, a light water pressurized water reactor (LWR) with a power output capacity of 77 MWe per module. The reactor and plant details were sourced from NuScale's final safety analysis report and supplemented by information from the NuScale website. The SMR plays a crucial role in energy generation, and to manage and dispatch the produced energy effectively, a robust storage system …

Introduction To Robotics Systems Assignment 2, Tarek Elderini

AI Assignment Library

An assignment was reformatted with respect to TILT using both Claude 3 and ChatGPT. One of the problems is that whatever pics in the file will not be added to the reformatted file. Also, I asked ChatGPT and Claude 3 to make a comparison between the two created assignments showing the pros and cons for each at the end. It was funny that both agreed that ChatGPT was more professional from the aspect of an engineering assignment. This document contains the original file, the 2 formatted assignments, and the comparison at the end.

Comparative Analysis Of Muskingum Routing: Traditional Vs. Ai-Assisted Methods, Vida Atashi

AI Assignment Library

In this assignment, students will apply traditional and AI-assisted Muskingum routing methods to real-world discharge data from the USGS over a 10-day period. The goal is to compare these approaches, enhancing skills in hydrological modeling and data analysis crucial for water resources engineering.

A Simulated Annealing Approach To The Scheduling Of Battery-Electric Bus Charging, Alexander Brown, Greg Droge

Electrical and Computer Engineering Faculty Publications

With an increasing adoption of battery-electric bus (BEB) fleets, developing a reliable charging schedule is vital to a successful migration from their fossil fuel counterparts. In this paper, a simulated annealing (SA) implementation is developed for a charge scheduling framework for a fixed-schedule fleet of BEBs that utilizes a proportional battery dynamics model, accounts for multiple charger types, allows partial charging, and further considers the total energy consumed by the schedule as well as peak power use. Two generation mechanisms are implemented for the SA algorithm, denoted as the "quick" and "heuristic" implementations, respectively. The model validity is demonstrated by …

Understanding And Enhancing Linux Kernel-Based Packet Switching On Wifi Access Points, Shiqi Zhang

Computer Science and Engineering Master's Theses

As the number of WiFi devices and their traffic demands continue to rise, the need for a scalable and highperformance wireless infrastructure becomes increasingly essential. Central to this infrastructure are WiFi Access Points (APs), which facilitate packet switching between Ethernet and WiFi interfaces. Despite APs’ reliance on the Linux kernel’s data plane for packet switching, the detailed operations and complexities of switching packets between Ethernet and WiFi interfaces have not been investigated in existing works. This paper makes the following contributions towards filling this research gap. Through macro and micro-analysis of empirical experiments, our study reveals insights in two distinct …

The Role Of Micromobility In The Changing Urban Mobility Landscape, Mostafa Jafarzadehfadaki

All ETDs from UAB

The growing prevalence of micromobility has significantly impacted urban mo-‎bility, offering a sustainable and convenient alternative for short trips in urban settings. ‎As cities grapple with increasing congestion, pollution, and the demand for efficient ‎mobility solutions, micromobility options like e-scooters and e-bikes have emerged as ‎popular modes of transportation, particularly in densely populated areas. While earlier ‎research has contributed to understanding micromobility and its impact on urban set-‎tings, significant knowledge gaps still exist. Therefore, a comprehensive study is neces-‎sary to explore the multifaceted dimensions of e-scooter adoption, usage patterns of mi-‎cromobility, and their implications for urban transportation systems and traffic …

09.09.2024 Orsp Connect, Liz Williamson

ORED Newsletter

New training course available: Sponsored Travel Guidance

OpenScholar Overview

Learn about Nature Masterclasses On-Demand Training

NSF Sessions on Phase 1 ISBIR/STTR Proposals

All You Need Is Unary: End-To-End Bit-Stream Processing In Hyperdimensional Computing, Mehran Shoushtari Moghadam, M. Hassan Najafi

Faculty Scholarship

Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm introduced to achieve energy efficiency with a lightweight and single-pass training model. Hypervectors (HVs) at the heart of the HDC systems play a fundamental role in elevating the accuracy and obtaining the desired performance. Image-based HV encoding requires two types of HVs: Position and Level HVs. State-of-the-art approaches utilize pseudo-random methods for generating these HVs, which might degrade system performance and cause higher power consumption due to poor randomness in HV generation. These conventional methods require iteratively calculating orthogonal Positional HVs for acceptable accuracy. This work proposes a fast, ultra-lightweight, and high-quality …

Redwater Test Data, Paul Van Susante, Kris Zacny

Michigan Tech Research Data

The RedWater mission is to extract water from subterranean glaciers found on Mars. Honeybee robotics has contracted the PSTDL to conduct small scale tests in order to collect data on the power consumed by a high-density cartridge heater to melt through cryogenic clear ice at Martian atmospheric pressure.

Reduced Order Modeling (Rom) Using Machine Learning Techniques For Analyzing Fluid Flow Around A Ground Vehicle, Emmanuel Ong'aro Ramogi

All ETDs from UAB

Predicting wind and temperature fields around military vehicles during extended missions is crucial to avoid detectability by infrared (IR) devices. Also, the abrupt shifting of wind direction can have a significant impact on vehicle stability. This is a challenging task due to the vehicles' geometric complexity and the unpredictable nature of wind direction, which can shift abruptly. Computational Fluid Dynamics (CFD) is routinely used for calculating the flow fields around ground vehicles. However, this requires extensive computational time and memory, making it unsuitable for real-time analysis. To address these challenges, this research focuses on machine learning (ML) techniques for accurate …

High-Frequency-Based Transmission Line Percentage Differential Protection With Traveling Wave Alignment, Igor F. Prado, Flavio Costa, Kleber M. Silva, Rodrigo P. Medeiros, Bruce A. Mork

Michigan Tech Publications

This paper presents a wavelet-based differential protection algorithm for transmission lines. It uses restraint and operating components obtained with high-frequency components of a few kHz from instantaneous energy values of the real-time boundary stationary wavelet transform instead of low-frequency components from phasor estimation. It does not require capacitive current suppression as well. Therefore, the proposed method overcomes the limitations of conventional percentage differential protection. Furthermore, the proposed technique uses traveling wave theory to perform the current sample alignment at a few kHz, thereby, not requiring the global positioning system (GPS). The performance of the proposed method is evaluated through extensive …

Integrated Environmental Vulnerability Assessment And Adaptation Strategies For Coastal Areas Under Sustainable Development, Lien-Kwei Chien, Yu-Chi Li, Chia-Feng Hsu

Journal of Marine Science and Technology–Taiwan

This research focuses on the holistic management and environmental vulnerability of coastal areas in Taiwan within the framework of sustainable development. With economic and social growth gravitating towards coastal regions, the strain on the natural environment is increasing. Therefore, discovering a balance between economic progress and environmental conservation is paramount. To decipher the vulnerability of Taiwan's coastal zones, this study first defines ‘Integrated Environmental Vulnerability of Coastal Areas.’Key vulnerability factors were identified across environmental, social, and economic dimensions. Seven core determinants were determined using the Fuzzy Delphi method: biodiversity, coastal erosion, water pollution, population density, population aging, land utilization, and …