Engineering Commons^™

Optimizing And Training An Svm-Based Breast Cancer Tumor Classifier, Kevin Lopatka

Master's Theses

With advancements in technology, turning to machine learning has become a popular choice for aiding clinicians in the diagnoses of breast cancer malignancies. While the neural networking approach has been vetted thoroughly, this work aims to take advantage of traditional machine learning techniques; mainly support vector machine learning and the optimizing of feature extraction. The discrete-wavelet transform is used in the feature extraction stage of machine learning. Previous works that use this feature extraction technique are analyzed and expanded upon by utilizing a variety of different wavelets as well as other color-spaces with the goal of achieving higher result metrics …

Modeling And Analysis Of A Hybrid Ac/Dc Green Seaport Power System With Photovoltaic Generation And Battery Energy Storage Systems, Corey Zaas

Master's Theses

This thesis investigates the modeling, simulation, and analysis of a Green Seaport power system integrating photovoltaic (PV) generation, battery energy storage systems (BESS), and coordinated protection within a hybrid AC/DC framework. The work improves a previously established model, enhancing it with detailed protection studies and simultaneous AC/DC power flow analysis using EasyPower software. The system was evaluated under a wide range of operating conditions, including varying solar irradiance, battery charge and discharge states, and both full and zero load conditions. Key performance indicators included voltage regulation, power factor behavior, equipment loading, protection device coordination, and total system power losses. Simulation …

Survival Signature Estimation For All-Terminal Networks By Solving The Multi-Objective Bottleneck Spanning Tree Problem, Dewan Maisha Zaman

Graduate Theses and Dissertations

This research examines the problem of estimating the survival signature of all-terminal networks using Monte Carlo (MC) simulation. Following a recent similar result for twoterminal networks, we show that the work required within each MC replication corresponds to solving a multi-objective bottleneck spanning tree (MOBST) problem. We implement the resulting MC procedure using a “Blocks” algorithm from the literature to solve the MOBST in each replication by identifying its minimal set of non-dominated points. We compare this implementation against intuitive benchmark procedures for completing the work within an MC replication. We conduct numerical experiments to assess the efficacy of multi-objective …

Advanced Day-Ahead Scheduling Of Hvac Demand Response Control Using Novel Strategy Of Q-Learning, Model Predictive Control, And Input Convex Neural Networks, Rahman Heidarykiany, Cristinel Ababei

Electrical and Computer Engineering Faculty Research and Publications

In this paper, we present a Q-Learning optimization algorithm for smart home HVAC systems. The proposed algorithm combines new convex deep neural network models with model predictive control (MPC) techniques. More specifically, new input convex long short-term memory (ICLSTM) models are employed to predict dynamic states in an MPC optimal control technique integrated within a Q-Learning reinforcement learning (RL) algorithm to further improve the learned temporal behaviors of nonlinear HVAC systems. As a novel RL approach, the proposed algorithm generates day-ahead HVAC demand response (DR) signals in smart homes that optimally reduce and/or shift peak energy usage, reduce electricity costs, …

Understanding The Breadth And Impact Of The Ias [President’S Message], Ayman El-Refaie

Electrical and Computer Engineering Faculty Research and Publications

No abstract provided.

Integrating Blockchain Technology Into Telemedicine: A Framework For Enhancing Data Privacy And Security, Harsha Sammangi, Aditya Jagatha, Jun Liu

Research & Publications

This paper presents a blockchain-based framework designed to enhance data privacy, integrity, and security in telemedicine systems. The proposed architecture employs distributed ledger technology to ensure transparency, traceability, and immutability of patient data exchanges among healthcare providers. Smart contracts automate access permissions and auditing processes, reducing the risks of unauthorized data sharing. The study evaluates the framework’s performance in secure data handling, highlighting blockchain’s role in fostering patient trust and resilience against cyberattacks in remote healthcare environments.

Decentralized Multi-Hop Federated Reinforcement Learning For Energy-Efficient And Secure Routing In Lorawan-Based Smart City Infrastructure, Harsha Sammangi, Aditya Jagatha, Jun Liu

Research & Publications

This paper proposes a decentralized hybrid framework that integrates Federated Learning (FL) and Reinforcement Learning (RL) to enable energy-efficient and secure multi-hop routing in LoRaWAN-based smart city networks. The method allows local model training at gateways and relay nodes, combining real-time routing decisions with privacy-preserving federated aggregation. Key metrics such as residual energy, link quality, and node trust levels are embedded into the reward function, and lightweight encryption plus differential privacy safeguard routing metadata. Simulation results demonstrate substantial gains in packet-delivery ratio, latency, network lifetime and resilience to adversarial attacks when compared to traditional routing protocols.

Automated Identification Of Clinically Meaningful Biomechanical Phenotypes In Cerebral Palsy Through Multicenter Gait Data, Adam Graf, Joseph Krzak, Karen M. Kruger, Jon Davids, Ryan Smith, Brandon Steinlein, Anita Bagley

Biomedical Engineering Faculty Research and Publications

Background

Cerebral palsy is the most prevalent motor disability in childhood, encompassing various movement disorders that affect walking. Researchers have described gait patterns in cerebral palsy, but these are often subjective and based on clinician experience. This study introduces an automated approach to objectively identify clinically meaningful biomechanical phenotypes in cerebral palsy and test it on multicenter gait data. Utilizing instrumented gait analysis, this research aims to improve treatment strategies for gait dysfunction. This study addresses whether classification algorithms can objectively identify clinically meaningful gait patterns and if severe gait deviations are more frequent in advanced forms of cerebral palsy. …

Locked Dimerized Cxcl12 Exerts Radiosensitizing Effects In Head And Neck Cancer, Oscar Villarreal Espinosa, Musaddiq Awan, Abdullah A. Memon, Anne Frei, Jamie Foeckler, Rachel Kuehn, Jennifer Bruening, Becky Massey, Stuart J. Wong, Monica Shukla, Julia Kasprzak, Amit Joshi, Michael B. Dwinell, Heather A. Himburg, Joseph Zenga

Biomedical Engineering Faculty Research and Publications

Background

Head and neck squamous cell carcinoma (HNSCC) presents significant treatment challenges, particularly in cases unrelated to human papillomavirus (HPV). The chemokine receptor CXCR4, interacting with its ligand CXCL12, plays a crucial role in tumor proliferation, metastasis, and treatment resistance. This study explores the therapeutic potential of engineered monomeric and dimerized CXCL12 variants (CXCL121 and CXCL122, respectively) in HNSCC and evaluates potential additive effects when combined with radiation therapy.

Methods

Clinical HNSCC biopsies were evaluated for CXCR4 expression in both previously untreated and radiorecurrent disease. HNSCC cell lines were then treated with combinations of CXCL12 variants and radiotherapy and interrogated …

Involvement Of Long Non-Coding Rna (Lncrna) Malat1 In Shear Stress Regulated Adipocyte Differentiation, Justin Caron, Marjan Ghanbariabdolmaleki, Madison Marino, Chong Qiu, Bo Wang, Michael Mak, Shue Wang

Biomedical Engineering Faculty Research and Publications

Adipocyte differentiation plays an important role in bone remodeling due to secretory factors that can directly modulate osteoblast and osteoclast, thus affecting overall bone mass and skeletal integrity. Excessive adipocyte differentiation within the bone marrow microenvironment can lead to decreased bone mass, eventually causing osteoporosis. The mechanical microenvironment of bone marrow, including fluid shear, maintains the balance of adipocyte and osteoblast differentiation during bone remodeling. However, how mechanical cues interact with long noncoding RNA (lncRNA) and regulate adipocyte differentiation remains unexplored. In this study, we investigated the mechanosensitive role of lncRNA MALAT1 during mesenchymal stem cells (MSCs) adipocyte differentiation. By …

Characterizing Human Mobility Patterns In Saudi Arabia Using Cellular Data, Meshal Alnefaie

Theses and Dissertations

The study analyzes human mobility in Saudi Arabia. Using crowd-source data, Riyadh mobility is analyzed to find trends and highlight mobility patterns of individuals in Riyadh. Then, the mobility of Riyadh is compared with that of Jeddah and Dammam in a similar data collection and analysis. Four mobility metrics are utilized: Number of Visited Locations (NLOC), Number of Unique Locations (NULOC), Radius of Gyration (RGYR), and Distance Traveled (DTRV). The results show interesting outcomes about individuals in the three cities. Although these cities are far from each other, they observe the same mobility patterns. These findings have the potential to …

Implementation Of Unscented Kalman Filter-Based State Estimation For Multiple Spacecraft Using Global Positioning System Measurements, Bala Prenith Reddy Gopu

Theses and Dissertations

This study presents an implementation of state estimation for a drag-based rendezvous mission involving multiple chaser spacecraft and a single target, using Unscented Kalman Filtering (UKF) with Global Positioning System (GPS) measurements. The implemented method combines GPS navigation solutions with UKF to provide real- time state estimates of all spacecraft involved. Nonlinear least squares method is employed to process pseudorange and pseudorange rate measurements to determine receiver states, UKF utilizes these states as measurements to estimate absolute space- craft positions and velocities. This implementation also addresses practical challenges including raw GPS measurement processing, and varying GPS satellite geometries.

Trends In And Factors Associated With Science Achievement Among Eighth Graders In Saudi Arabia: A Secondary Analysis Of Timss Data, Roba Alzahrani

Theses and Dissertations

This secondary analysis examined trends in and factors influencing science achievement among eighth-grade students in Saudi Arabia, using data from the Trends in International Mathematics and Science Study (TIMSS). However, Saudi Arabia's performance on the TIMSS science assessments fell below the international average, from 2003 through 2019. In addition, gender differences in science achievement have been observed, with female students outperforming male students by 30 or more points. This study addresses two problems: factors associated with the lower performance of Saudi students on TIMSS science assessments compared to global standards, and the small number of studies which explored factors which …

Fpso Motion In Synthetic Environments: Stereo-Driven Deep Learning For Wavefield Reconstruction, Motion Analysis, And Mooring System Assessment, Omar Jebari

Theses and Dissertations

This dissertation presents an integrated synthetic environment for simulating the motion and monitoring the integrity of a moored Floating Production Storage and Offloading (FPSO) vessel. The central hypothesis is that synthetic data-driven approaches can (1) accurately estimate spatio-temporal wave fields, (2) predict vessel motion, and (3) monitor the integrity of the mooring system—using stereo imagery of the wave field and structure motion, both of which can be acquired in real time. The first study develops a synthetic framework for estimating spatial wave fields using stereo images captured by dual cameras mounted on a moving FPSO. Dynamic sea states and vessel …

Optimization-Based Distributed Controller For Multi-Agents System In Microgrid Secondary Control, Fahad S. Alshammari, Ayman El-Refaie, Saleh Alyahya, Sheroz Khan

Electrical and Computer Engineering Faculty Research and Publications

Micro-grids function to connect to power system power produced by the renewable energy resources. In islanded micro-grids, grid-forming units collaborate to maintain the micro-grids voltage and frequency by utilizing droop control technique that includes primary, secondary and tertiary levels. Secondary control intervenes to improve power sharing and restore voltage and frequency to their nominal levels. However, the conventional droop control applied to a grid with mismatched line parameters experiences a trade-off between reactive power sharing and voltage regulations. This paper applies real-time trajectory tracking convex optimization to ensure by communicating power sharing between units in a consensus topology. The optimization …

Computationally Guided Liquid Crystal-Based Competitive Binding Sensing Platform For Optical Detection Of Spike Protein, Homa Ghaiedi, Shubham Pandey, Sophia Ezendu, Tibor Szilvasi, Karthik Nayani

Chemical Engineering Faculty Publications and Presentations

A liquid crystal (LC)-based sensing platform for the rapid optical detection of SARS-CoV-2 ' s spike protein's receptor binding domain (RBD) domain is introduced. This platform utilizes a thermotropic LC, hosted on metal-cation decorated substrates, onto which the spike protein can competitively bind. Density functional theory (DFT) calculations guide the experiments that reveal a homeotropic-to-planar transition in the LCs upon exposure to SARS-CoV-2 spike-decorated yeast, providing a basis for sensitive virus detection. The sensor's reversibility/specificity is confirmed through antibody-induced orientation recovery of the LCs initial orientation. Strikingly, the sensor can detect approximate to 2000 copies of the spike protein per …

Selecting Green Wall Adoption Best Solutions Using Optimization: Addressing Barriers And Maximizing Benefits, Samar Nadeem

Theses and Dissertations

This research explores the potential of green walls as a sustainable solution to mitigate urban challenges and align with global climate change objectives. Despite their ecological and social benefits, green wall implementation faces significant barriers, hindering their adoption. Consequently, this study aims to develop a comprehensive framework to identify the obstacles, propose feasible solutions, and provide actionable strategies for promoting green walls. This framework incorporates an optimization model specifically designed for government-led solutions, evaluating their feasibility based on administrative feasibility, community acceptance, technical feasibility, industrial acceptance, and long-term adoption potential. By quantifying and prioritizing solutions based on their cost, feasibility, …

Observing Mesospheric Gravity Waves With Nasa's Awe Mission And Correlating To Gnss Tec Maps, Jaime Aguilar Guerrero, Björn Bergsson, Sehin Mesfin, Pavel Inchin, Matthew Zettergren, Ludger Scherliess, Yucheng Zhao, Dominique Pautet

Space Dynamics Laboratory Publications

The Atmosphere Waves Experiment (AWE) is a NASA mission launched on November 9, 2023, and installed on the International Space Station (ISS). Its primary goal is to detect and characterize atmospheric gravity waves (AGWs) by measuring Earth’s mesospheric hydroxyl (OH) airglow with its key instrument, the Advanced Mesospheric Temperature Mapper (AMTM). Since its deployment, AWE has been quantifying the seasonal and regional variability of AGWs, investigating their occurrence and potential sources, and enabling the assessment of their broader impact on the atmosphere by comparing measurements at different altitudes by other instruments. AWE has collected extensive imagery and temperature data capturing …

Investigation Of Control Strategies For Swing-Up Maneuver Of A Double Inverted Pendulum On Rotating Link, Abdulrahman Mohammad Rahmani

Thesis/ Dissertation Defenses

This thesis is concerned with investigation of the swing-up control problem of underactuated mechanical systems namely the double rotary inverted pendulum using the optimal control theory. The research aims to develop a robust controller to achieve the swing-up and stabilization of the pendulum in the upright unstable equilibrium position while regulating the angular displacement of the rotating arm and the two pendulum angles. The performance of the designed controller was evaluated through numerical simulations in the MATLAB/Simulink environment. A comprehensive review of the literature was conducted and the challenges that researchers face in the control of underactuated mechanical systems were …

Estimation Of Breach Hydrograph Resulting From Dam Embankment Failure Due To Internal Erosion Or Overtopping: Comparison Of Simplified Methods With Real-Case Failure Data And Recommendations, Laurent Del Gatto, Jean-Robert Courivaud

5th International Seminar on Dam Protections Against Overtopping

The opening of a breach in an embankment dam, whether due to overtopping or internal erosion, is a critical failure mode for these structures. Estimating the resulting breach hydrograph is essential for assessing downstream risks. While no universal physical model covers all dam types, empirical formulas are commonly used. EDF analyzed 14 such formulas, comparing them with rupture data from 32 embankment dam failures. The best formulas - Froehlich 1995, Xu & Zhang 2009, and CLF 2020 - yield a “best estimate” for peak flow. However, due to variability, results should be interpreted cautiously. Consider estimating breach characteristics like width …

Breach Modeling Flume Tests, R. M. Monteiro-Alves, R. Moran, M. Á. Toledo, M. Morris, C. Picault, J-R. Courivaud

5th International Seminar on Dam Protections Against Overtopping

From previous flume tests conducted in the framework of the OVERCOME Project, intended to investigate the effect of different soil materials, overflow discharges, and upstream face watertightness on the breaching processes of overflowed levee sections, we determined the need for further investigation on the effect of test repeatability, content of fines and armouring caused by the coarser particles. This document presents the results of this new set of tests which have shown an impact of these variables on the breach macro erosion processes, erosion rates and breach dimensions.

Development Of Low-Carbon Cementitious Composites With Volcanic Ash And Calcium Carbide Residue Using Carbonation Curing, Jad Samir Bawab

Thesis/ Dissertation Defenses

The production and use of cement and concrete is a major contributor to numerous environmental problems, primarily centered around high carbon emissions, extensive resource depletion, and vast waste generation. This thesis aims to develop and characterize low-carbon concrete by using volcanic ash (VA) and calcium carbide residue (CCR) as partial cement substitutes while exposing the cementitious composite to accelerated carbonation curing. The study is a multi-level assessment of the incorporated materials and curing method divided into four phases. The first stage studied and optimized the CCR content and carbonation curing parameters of carbonation-cured concrete. It was revealed that using 5% …

Physically Based Assessment Of Flow Resistance In Stepped Chutes, T. L. Wahl, B. J. Heiner, K. R. Smithgall, C. C. Shupe, J. Falkenstine

5th International Seminar on Dam Protections Against Overtopping

Existing physically based methods for estimating stepped chute friction factors or energy dissipation rates consider relative step height and relative step-tip spacing to be key factors, but do not fully account for chute slope and associated step orientation. For slopes steeper than 45° each step acts as an offset into the flow, while for flatter slopes each step presents an offset away from the flow, but methods that consider only the step-tip spacing do not account for this difference. Furthermore, most experimental studies have been performed in open channel spillway models, where two-phase air-water flow and variable flow depths make …

Ahead Of His Time? A Reanalysis Of The Air-Tunnel Stepped Chute Studies Of Marcos José Tozzi, T. L. Wahl, J. A. Higgs, J. Matos

5th International Seminar on Dam Protections Against Overtopping

Stepped spillways offer energy dissipation advantages and construction efficiencies over smooth spillway chutes. Energy dissipation is typically estimated using empirical relations that depend on chute slope, unit discharge and relative step height. Open-channel tests of model spillways experience self-aerated air-water flow downstream from the aeration inception point, and the presence of air dramatically affects energy dissipation and flow depth, making it difficult to separately determine the effects of step geometry and other basic flow properties. The 1992 doctoral dissertation of Marcos José Tozzi from the Polytechnic School of the University of São Paulo included open channel stepped spillway tests with …

Hydraulic Measurements In A Saf Stilling Basin With A Stepped Chute For Embankment Protection, B. M. Crookston, N. Young

5th International Seminar on Dam Protections Against Overtopping

Stepped chutes have become commonplace in embankment dam rehabilitation projects due to project economy, constructability, and improved chute energy dissipation. Consequently, for applications where a stilling basin is merited the interaction of stepped chutes and stilling basins is of high interest. A commonly used stilling basin type for many smaller embankment dams, the St. Anthony Falls stilling basin (SAF), has no specific hydraulic design guidance for use downstream of a stepped chute. Therefore, this study was conducted at the Utah Water Research Laboratory in a flume with 0.1 m tall steps, a total drop height of 1.8 m, and an …

Enhancing Patient Safety: Exploring Virtual Sitters' Role In Fall Prevention Through Remote Virtual Monitoring, Adama Diallo, Awatef Ergai Dr., Leeanna Spiva Dr., Meriel Mccollum Dr.

Symposium of Student Scholars

Remote Virtual Monitoring (RVM) technology enhances safety for both patients and care teams by reducing falls, improving the efficiency and effectiveness of continuous patient observation, and lowering costs associated with falls and staff support. The success of fall reduction efforts largely depends on the role of virtual sitters, individuals who remotely monitor high-risk patients to prevent falls. This study aims to explore the experiences of virtual sitters, identifying key themes, challenges, and opportunities to improve the intervention. Specifically, the research investigates how technology, work shifts, and institutional support impact the effectiveness and job satisfaction of virtual sitters.

Real Time Object Detection Using Yolo, Rohit Malik, Manisha Kumari, Sanghoon Lee

Symposium of Student Scholars

This project explores the implementation of real-time object detection using the You Only Look Once (YOLO) architecture. Leveraging its speed and accuracy, we developed a system capable of identifying and localizing multiple objects within live video streams. Our implementation focused on optimizing YOLO's performance for real-time applications, specifically addressing the trade-off between speed and accuracy.

We employed a pre-trained YOLO model and fine-tuned it on a custom dataset tailored to specific object classes. This fine-tuning process aimed to enhance the model's ability to recognize objects in our target environment. The system was implemented using Python and the OpenCV library, enabling …

Campus Navigator: A Mobile App For Seamless University Navigation, Hafsa Mohammed, Ali Rahimzadehfard, Rachab Wilson, Mathias Rossi, Turaj Ashuri, Amir Ali Amiri Moghadam

Symposium of Student Scholars

Navigation services play a big role in everyone’s daily lives, from directing them on new roads to guiding them through buildings. Outdoor navigation services have evolved from physical maps to digital ones like Google Maps for ease of use and accessibility. Upon conducting literature research, the team found that many navigation apps lack clear and accurate instructions for how to navigate university campuses such as Marietta campus. Due to the size of KSU’s Marietta campus and its buildings, effortless navigation has been a common challenge for students, faculty, and visitors alike. Additionally, all buildings are referred to by letters, numbers, …

Assessing A Solution For Ga Work Zone Safety Through Cross Classification, Asiah Lightfoot, Sunanda Dissanayake

Symposium of Student Scholars

Work zone safety is a health risk for drivers and construction workers. In Georgia, work zone crashes have decreased over the past 5 years, but the number of fatalities has still been over 1,000 each of those years. Studies have proven solutions such as lowering the speed limit or relying on current traffic control devices to be ineffective. The risks associated with these crashes must be recognized to improve upon previous solutions or innovate new ones from the results. The objective of this study is to utilize cross classification to identify factors that contribute to work zone crash deaths and …

Sandrapp: A Digital Intervention To Enhance Social Connectivity And Emotional Support Among Older Adults, Pavan Chowdary Chilukuri, Purna Chandu Anukula

Symposium of Student Scholars

Social isolation and loneliness are significant challenges affecting the well-being of older adults, often leading to adverse mental and physical health outcomes. Prolonged isolation has been linked to increased risks of depression, anxiety, cognitive decline, and chronic illnesses such as hypertension and cardiovascular diseases. As digital technology continues to evolve, innovative solutions have emerged to address these issues and foster meaningful social interactions for older adults.

SANDRApp is a user-friendly digital platform designed to reduce loneliness and enhance social connectivity among older adults. The platform caters to three primary user groups: (1) families with elderly loved ones living far away, …