Digital Commons Network^™

Detecting Sars-Cov-2 In Ct Scans Using Vision Transformer And Graph Neural Network, Kamorudeen Amuda, Almustapha Wakili, Tomilade Amoo, Lukman Agbetu, Qianlong Wang, Jinjuan Feng

Electrical & Computer Engineering Faculty Publications

The COVID-19 pandemic has presented significant challenges to global healthcare, bringing out the urgent need for reliable diagnostic tools. Computed Tomography (CT) scans have proven instrumental in detecting COVID-19-induced lung abnormalities. This study introduces Convolutional Neural Network, Graph Neural Network, and Vision Transformer (ViTGNN), an advanced hybrid model designed to enhance SARS-CoV-2 detection by combining Graph Neural Networks (GNNs) for feature extraction with Vision Transformers (ViTs) for classification. Using the strength of CNN and GNN to capture complex relational structures and the ViT capacity to classify global contexts, ViTGNN achieves a comprehensive representation of CT scan data. The model was …

Potential Of Lidar And Hyperspectral Sensing For Overcoming Challenges In Current Maritime Ballast Tank Corrosion Inspection, Sergio Pallas Enguita, Jiajun Jiang, Chung-Hao Chen, Samuel Kovacic, Richard Lebel

Electrical & Computer Engineering Faculty Publications

Corrosion in maritime ballast tanks is a major driver of maintenance costs and operational risks for maritime assets. Inspections are hampered by complex geometries, hazardous conditions, and the limitations of conventional methods, particularly visual assessment, which struggles with subjectivity, accessibility, and early detection, especially under coatings. This paper critically examines these challenges and explores the potential of Light Detection and Ranging (LiDAR) and Hyperspectral Imaging (HSI) to form the basis of improved inspection approaches. We discuss LiDAR’s utility for accurate 3D mapping and providing a spatial framework and HSI’s potential for objective material identification and surface characterization based on spectral …

High-Fidelity Soh Prediction In Lithium-Ion Batteries Using Hybrid Ml Networks, Shafiyee Islam, Gon Namkoong

Electrical & Computer Engineering Faculty Publications

Accurate and efficient prediction of lithium-ion battery state of health (SOH) is critical for ensuring reliability in electric vehicles, grid storage, and aerospace systems. Traditional SOH estimation methods often struggle with nonlinear degradation behaviors and lack sensitivity to subtle electrochemical signals, limiting their real-world deployment. To address these challenges, this study examines hybrid deep learning models that integrate differential capacity (dQ/dV) analysis to enhance predictive accuracy. Four hybrid architectures - hybrid CNN-LSTM multihead, CNN extractor for LSTM, DNN-LSTM, and DNN Bi-LSTM - were developed and evaluated using the NASA randomized battery usage dataset, offering a realistic benchmark under diverse operational …

A Method For Ultrasound Servo Tracking For Puncture Needle, Shitong Ye, Bo Yang, Hao Quan, Shan Liu, Minyu Tang, Jiawei Tian

Electrical & Computer Engineering Faculty Publications

Computer-aided surgical navigation technology helps and guides doctors to complete the operation smoothly, which simulates the whole surgical environment with computer technology, and then visualizes the whole operation link in three dimensions. At present, common image-guided surgical techniques such as computed tomography (CT) and X-ray imaging (X-ray) will cause radiation damage to the human body during the imaging process. To address this, we propose a novel Extended Kalman filter-based model that tracks the puncture needle-point using an ultrasound probe. To address the limitations of Kalman filtering methods based on position and velocity, our method of Kalman filtering uses the position …

A Customized Large Single-Piece Bifrontal Implant For Post-Craniectomy Defect Reconstruction: A Case Study, Omid Ghaderzadeh, Ehsan Amirbeyk, Seyed Roholah Ghodsi, Zahra Namazi, Lobat Tayebi

Electrical & Computer Engineering Faculty Publications

Background: Large bifrontal defects pose unique reconstruction challenges due to their complex curvature and mechanical requirements. This case demonstrated how computer-aided design/manufacturing (CAD/CAM) enabled precise single-piece polymethyl methacrylate (PMMA) implant fabrication, thereby overcoming traditional limitations. Case presentation: A 25-year-old male who had undergone bifrontal decompressive craniectomy suffered a severe traumatic brain injury. The autologous bone flap had been temporarily stored in a subcutaneous fat area of the abdomen for 3 months to preserve its viability. A secondary cranioplasty was then performed using titanium miniplates and self-tapping screws for final fixation. After 2 years, the patient developed empyema and a brain …

Development Of 2d Microfluidics Surface With Low-Frequency Electric Fields For Cell Separation Applications, Madushan Wickramasinghe, Dharmakeerthi Nawarathna

Electrical & Computer Engineering Faculty Publications

Cell separation techniques are widely used in many biomedical and clinical applications for the development of screening, diagnosis and therapeutic tests. Current 3D microfluidics-based cell separation methods have limited applications in part due to low throughput and technical complexity. To address these critical needs, we have developed a 2D microfluidics surface which is the miniaturized version of a 3D microfluids cell separation device. Using low-frequency electric fields (1–10 Vpp and 1 kHz–20 MHz), we have first studied dielectrophoresis, AC electro-osmosis and capillary flow within a sessile drop, and finally utilized the results to develop the 2D cell separation surface. Our …

A Novel Intelligent Thermal Feedback Framework For Electric Motor Protection In Embedded Robotic Systems, Mohamed Shili, Salah Hammedi, Hicham Chaoui, Khaled Nouri

Electrical & Computer Engineering Faculty Publications

As robotic systems advance in autonomy and sophistication while being used in uncertain environments, the challenge of building reliable and robust electric motors that are embedded into robotic systems has never been a more important engineering problem. Thermal distress caused by extended operation or excessive loading can negatively affect a motor’s performance and efficiency and lead to catastrophic hardware failure. This paper proposes a novel intelligent control framework that includes real-time thermal feedback for hybrid electric motors that are embedded into robotic systems. The framework relies on adaptive control techniques and lightweight machine learning techniques to estimate internal motor temperatures …

Advances In Battery Modeling And Management Systems: A Comprehensive Review Of Techniques, Challenges, And Future Perspectives, Seyed Saeed Madani, Yasmin Shabeer, Ananthu Shibu Nair, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, Shi Xue Dou, Khay See, Saad Mekhilef, Françios Allard

Electrical & Computer Engineering Faculty Publications

Energy storage systems (ESSs) and electric vehicle (EV) batteries depend on battery management systems (BMSs) for their longevity, safety, and effectiveness. Battery modeling is crucial to the operation of BMSs, as it enhances temperature control, fault detection, and state estimation, thereby maximizing efficiency and preventing malfunctions. This paper thoroughly examines the most recent advancements in battery and BMS modeling, including data-driven, thermal, and electrochemical methods. Advanced modeling approaches are explored, including physics-based models that incorporate mechanical stress and aging effects, as well as artificial intelligence (AI)-driven state estimation. New technologies that facilitate data-driven decision-making, real-time monitoring, and simplified systems include …

Novel Micro-And Nanoformulations Of Paclitaxel For Targeting Metastatic Breast, Non-Small Cell Lung, And Pancreatic Cancers, Lobat Tayebi, Mehran Alavi

Electrical & Computer Engineering Faculty Publications

Nonlinear pharmacokinetics resulting from high lipophilic and low oral bioavailability, and hypersensitivity reactions and hyperlipidemia caused by formulation by Cremophor EL have limited clinical effectiveness of paclitaxel (Taxol). In this way, there is the critical necessity of innovative drug delivery systems (DDSs) to mitigate severe side effects and overcome clinical limitations of paclitaxel. In recent years, various micro- and nanoformulations, specifically polymeric nanoparticles (NPs) and lipid NPs, have been presented and approved by the Food and Drug Administration (FDA). In addition, other nanoformulations, such as polymeric nanoparticles (NPs), micelles, liposomes, and mesoporous silica nanoparticles, have shown promising results in vitro …

Cellax Nanoparticles: Taxane Nanoformulations For Solid Tumor Targeting, Lobat Tayebi, Mehran Alavi

Electrical & Computer Engineering Faculty Publications

Nanoparticles (NPs), specifically polymer-modified NPs, have illustrated unique therapeutic advantages compared to bulk materials. Cellax NPs have provided a promising approach to cancer therapy by improving drug delivery, targeting the tumor microenvironment, and potentially overcoming drug resistance, all while reducing overall toxicity compared to traditional taxane treatment. By the flash nanoprecipitation (FNP) method, docetaxel and cabazitaxel have been formulated with polyethylene glycol (PEG) modified-acetylated carboxymethylcellulose (CMC) polymer to increase biocompatibility, bioavailability, specific targeting, and modulate the tumor microenvironment. However, there are some challenges and clinical limitations related to this formulation, encompassing optimum targeted delivery to tumors, overcoming biological barriers, such …

Drone-Based Medication Delivery For Rural, Flood-Prone Coastal Cities, Yin-Hsuen Chen, Amro M. El-Adle, Kevin J. O'Brien, Taylor Wentworth, Heather G. Richter

Center for Geospatial Science, Education & Analytics Faculty Publications

Access to healthcare remains a critical challenge for rural populations, particularly in flood-prone coastal communities where transportation barriers limit access to essential medical services. This study evaluates the effectiveness of drone-based medication delivery in improving healthcare accessibility for vulnerable populations on Virginia’s Eastern Shore. Compared to traditional personal vehicle travel, drone delivery reduced trip times from up to 50 minutes to under 10 minutes for more than 80% of the population, including elderly patients. Using publicly available datasets, we developed two transportation vulnerability indices that incorporate age, travel time, and flood risk to prioritize patients for drone-based pharmaceutical delivery. These …

From Cyclones To Cybersecurity: A Call For Convergence In Risk And Crisis Communications Research, Ann Marie Reinhold, Ross J. Gore, Barry Ezell, Clemente I. Izurieta, Elizabeth A. Shanahan

VMASC Publications

Effective risk and crisis communication can improve health and safety and reduce harmful effects of hazards and disasters. A robust body of literature investigates mechanisms for improving risk and crisis communication. While effective risk and crisis communication strategies are equally desired across different hazard types (e.g., natural hazards, cyber security), the extent to which risk and crisis communication experts utilize the “lessons learned” from scientific domains outside their own is suspect. Therefore, we hypothesized that risk and crisis communication research is siloed according to academic disciplines at the detriment to the advancement of the field of risk communications research writ …

Advanced Nanocomposite-Based Electrochemical Sensor For Ultra-Sensitive Dopamine Detection In Physiological Fluids, Megha Shinde, Gymama Slaughter

Center for Bioelectronics Publications

This study presents a novel point-of-care electrochemical sensor for dopamine (DA) detection, featuring a flexible laser-induced graphene (LIG) modified with a unique nanocomposite comprising Nb₄C₃T_x MXene, polypyrrole (PPy), and iron nanoparticles (FeNPs). The LIG-Nb₄C₃T_x MXene-PPy-FeNPs is characterized by scanning electron microscopy to confirm the successful surface modification. The electrochemical performance of the fabricated sensor via cyclic voltammetry showed significant electrochemical activity upon Nb₄C₃T_x MXene-PPy-FeNPs nanocomposite modification of the LIG surface with an increased peak anodic current (Ipa) from 43 μA to 104 μA. The sensor …

Gold Nanoparticle-Enhanced Molecularly Imprinted Polymer Electrode For Non-Enzymatic Lactate Sensing, Christopher Animashaun, Abdellatif Ait Lahcen, Gymama Slaughter

Center for Bioelectronics Publications

We are reporting the development of a high-performance, non-enzymatic electrochemical biosensor for selective lactate detection, integrating laser-induced graphene (LIG), gold nanoparticles (AuNPs), and a molecularly imprinted polymer (MIP) synthesized from poly(3,4-ethylenedioxythiophene) (PEDOT). The LIG electrode offers a highly porous, conductive scaffold, while electrodeposited AuNPs enhance catalytic activity and signal amplification. The PEDOT-based MIP layer, electropolymerized via cyclic voltammetry, imparts molecular specificity by creating lactate-specific binding sites. Cyclic voltammetry confirmed successful molecular imprinting and enhanced interfacial electron transfer. The resulting LIG/AuNPs/MIP biosensor demonstrated a wide linear detection range from 0.1 µM to 2500 µM, with a sensitivity of 22.42 µA/log(µM) and …

Electrochemical And Nanomaterial Based Strategies For Nonenzymatic Glucose Detection: A Review, Reagan Aviha, Gymama Slaughter

Center for Bioelectronics Publications

Electrochemical glucose sensing technologies have undergone significant evolution, with continual advancements aimed at improving sensitivity, selectivity, and user convenience. This review systematically explores the development of emerging nonenzymatic glucose sensor designs. Nonenzymatic sensors are critically evaluated for their ability to overcome enzymatic limitations, leveraging novel materials and catalytic mechanisms. Additionally, the emergence of smartphone-integrated glucose monitoring systems is highlighted as the fifth generation, representing a paradigm shift toward personalized, real-time healthcare management. Emphasis is placed on the strategies employed to reduce the working electrode potential and enhance analytical performance. Key analytical metrics and real-sample applicability are evaluated, and persistent challenges …

Molecular Imprinting And Nanomaterial Synergy For Lactate Detection, Christopher Animashaun, Gymama Slaughter

Center for Bioelectronics Publications

Molecularly imprinted polymer (MIP)-based electrochemical sensors have emerged as promising non-enzymatic platforms for the selective and stable detection of clinically and environmentally relevant biomarkers. This review provides a critical, comprehensive analysis of recent advances in MIP-based lactate sensing, with particular emphasis on hybrid systems that integrate conductive nanomaterials including gold and silver nanoparticles, laser-induced graphene, and reduced graphene oxide. These synergistic combinations leverage enhanced surface area, electrical conductivity, and molecular recognition to improve sensor sensitivity, selectivity, and long-term operational stability. Key fabrication strategies, such as electropolymerization, green nanomaterial synthesis, and surface imprinting, are critically examined for their roles in optimizing …

Flipped Classroom Versus Lecture: A Quasi-Experimental Study Evaluating The Performance Of Dental Students.”, Manal Elhijazi, Ihsane Benyahya

Health Sciences

Background: The flipped classroom is an active pedagogical modality that improves learning, autonomy and critical thinking. This work aims to evaluate the impact of the flipped classroom on student performance compared to the lecture in a biomaterials course.

Material and methods:Second-year dental students were invited to participate voluntarily in this quasi-experimental study .Thus, they were divided into two groups: one group benefited́ from the flipped classroom while the control group attended the lecture. At the end of a formative evaluation for both groups, their average grades were compared using Student's test (significance threshold set at p

Results : …

Hydronic Parking Lots: A Solution For Urban Heat Island Mitigation, Sumeet Jinnappa Paramaj

Theses and Dissertations

The Urban Heat Island (UHI) effect has emerged as a critical challenge in modern cities. It contributes to elevated local temperatures, placing significant stress on urban ecosystems and public health. One of the primary drivers of this phenomenon is the widespread use of impervious surfaces, such as dark-colored parking lots, which absorb heat during the day and gradually release it at night. This ongoing cycle results in persistently warmer urban environments. As cities continue to expand and densify, the need for effective, sustainable strategies to reduce urban heat becomes increasingly urgent.

This project aims to explore innovative interventions, particularly in …

The Impact Of 'Decent Life' Initiative On Sustainable Urban Development: Abu Galal Village In Egypt As A Case Study, Sally Hassan Abd-Elazim, Sherif Ahmed Sheta, Medhat Ahmed Shaban

Mansoura Engineering Journal

The “Decent Life” Initiative aims to enhance living conditions and support sustainable urban development in Abu Jalal village, Sherbin city, Dakahlia Governorate, Egypt. The research aims to assess the effectiveness of the 'Decent Life' initiative in promoting sustainable urban development in Egyptian villages, focusing on improving its mechanisms for future use and maximizing benefits in other villages facing similar challenges.. The research employs various methods, including surveys and questionnaires targeting local residents, evaluation based on SDG 11, and GIS software for spatial analysis. Research identifies key areas of improvement across housing, healthcare, transport, education, infrastructure, job opportunities, disaster resilience, waste …

Computer Aided Detection System For Liver Cancer Using Computed Tomography Images Based On Artificial Intelligence, Noha Saad Badrawy, Hanan M. Amer, Apeer T. Khalil

Mansoura Engineering Journal

The prevalence of liver cancer has surged in Egypt and worldwide, leading to increased use of AI for tumor detection and diagnosis. The objective is to boost accuracy and minimize errors in manually classifying liver images, a task that is laborious and time-consuming. This study seeks to create a high-performance system for detecting liver tumors in Computed Tomography "CT" scans, utilizing Convolutional Neural Networks "CNNs" and machine learning, which are prevalent in biomedical imaging. With a dataset of 9,255 CT images, the research involves three steps. First, three deep learning models are compared: that Liver Tuned High-Resolution Network (LTHR-Net), Deep …

An Investigation Into Energy Consumption And V2g Potential Of An Electric School Bus Fleet, Rupesh Dahal

Graduate Theses, Dissertations, and Problem Reports (ETD)

The transition towards sustainable public transportation demands detailed evaluation of alternative fuel technologies. This thesis presents a comprehensive energy assessment and comparative analysis of diesel and electric school buses (ESBs) operating within the Monongalia County school district, its Vehicle-to-Grid (V2G) potential, and efficiency analysis of charging system. Utilizing real-world operational data collected from buses running identical routes, the study quantifies and compares their mileage specific energy consumption. The analysis reveals an average fuel economy of approximately 6.17 miles per gallon (MPG) for the conventional diesel school bus, contrasted with an average energy consumption rate of 0.46 miles per kilowatt-hour (miles/kWh) …

A Limb-Speed-Driven Locomotor Control System And Its Ability To Adapt, Emily Marie Herrick

Graduate Theses, Dissertations, and Problem Reports (ETD)

Despite how simple walking may seem, the locomotor control system is structurally and functionally complex. Its hierarchical organization of supraspinal and spinal networks with forward and feedback pathways has many interactions at multiple levels that are dependent on the dynamics of a high-dimensional musculoskeletal system. Having a comprehensive understanding of sensorimotor integration within a healthy locomotor control system is crucial for understanding changes to the system due to age or neurologic disease and developing effective technologies to recover mobility in those populations. In this dissertation, we address persistent gaps in knowledge pertaining to how the nervous system controls locomotion.

In …

Numerical Investigation Of Pressurized Oxy-Combustion, Lei Li

Graduate Theses, Dissertations, and Problem Reports (ETD)

Pressurized oxy-combustion (POC) is emerging as a promising and transformative technology for carbon capture, utilization, and storage, offering advantages of low cost, low emissions, and high efficiency. POC operates by burning pulverized coal at elevated pressures in a recycled flue gas environment, typically rich in O₂ and CO₂. This study presents a comprehensive numerical investigation into the fundamental behaviors of lab-scale POC reactors, using both two-dimensional (2D) Reynolds-Averaged Navier-Stokes (RANS) simulations and three-dimensional (3D) Large-Eddy Simulations (LES) with the commercial computational fluidized dynamics (CFD) software package ANSYS Fluent.

The primary focus of this work is to understand flame stabilization and …

Rare Earth Element Recovery From Acid Mine Drainage Using Ion Exchange And Selective Precipitation Processes, Paubla Andrea Gallego Lopez

Graduate Theses, Dissertations, and Problem Reports (ETD)

Rare earth elements (REEs) are used in high-tech applications due to their electromagnetic and optical properties. As global demand for REEs surges, the limitation of primary mineral deposits has increased interest in alternative sources. One such source is acid mine drainage (AMD), which, although typically low in REE concentration, offers a promising avenue for recovery. Among the emerging recovery methods, ion exchange has shown promise due to its effectiveness at low concentrations and lower operational cost than conventional techniques such as acid leaching and solvent extraction.

This research focused on developing a recovery process by combining ion exchange with selective …

Using Data Science And Sustainability Assessment Tools To Evaluate Wastewater Treatment Technologies, Haidar Shakuir Aldaach

Graduate Theses, Dissertations, and Problem Reports (ETD)

Wastewater management in small communities has faced numerous challenges in recent years, including population growth, limited budgets for operation and maintenance, and stringent effluent standards required by environmental regulations. These challenges motivate enhancing wastewater treatment processes to protect water quality. Wastewater treatment performance can be improved in small towns and rural regions by implementing data-driven strategies. Data science, life cycle assessment (LCA), and life cycle cost analysis (LCCA) are three data-driven decision-making tools that require data collection, modeling, computational models, and statistical analysis that could be utilized to improve wastewater treatment efficiencies. In this study, these three tools were adopted …

Implementation Of A Neural Network Execution Framework For Generalized And Cross-Platform Deep Learning Deployment And Inference On Spacecraft Systems, Rafael Polanco Segovia

Graduate Theses, Dissertations, and Problem Reports (ETD)

Recent advances in hardware and software technology have made it possible to implement more resource-demanding deep learning algorithms in constrained hardware environments. This creates opportunities to use deep learning for aerospace applications on increasingly smaller aerospace vehicles. This work presents the implementation of a Neural Network Execution Framework (NNEF), which aims to provide a cross-platform and reusable framework to deploy and execute trained neural networks for deep learning aerospace applications. The NNEF executes any neural network inference process regardless of the original deep learning framework in which it was created, for supported flight software platforms, and space-like computer boards. Users …

An Infrared Thermography Assessment For Monitoring Aging Mse Walls, Charles Lawal

College of Graduate Studies: Theses & Dissertations

Mechanically Stabilized Earth (MSE) walls play a vital role in ensuring the stability of transportation infrastructure, yet traditional inspection techniques often struggle to detect subsurface defects and demand significant labor. This research explores the application of Infrared Thermography (IRT) as a non-destructive, cost-effective approach for inspecting MSE walls across Southeast Georgia. By capturing thermal images under diverse environmental and operational conditions, the study aims to identify potential issues, including cracks, voids, delamination, and honeycombing, which can undermine integrity over time. Utilizing advanced image processing tools, the research implements specialized software to enhance the accuracy of defect detection, facilitating the generation …

Digital Modeling Of Temperature-Dependent Processes In Industrial Wastewater: Advancing Ultimate Oxygen Demand Prediction For Treatment Optimization, Fatima Iqbal

College of Graduate Studies: Theses & Dissertations

The pulp and paper industry is the third-largest consumer of freshwater globally and faces mounting pressure to optimize water usage and minimize environmental impact. Aerated stabilization basins are extensively utilized in the pulp and paper industry and play a crucial role in treating wastewater from these operations. The existing management practices fail to effectively optimize treatment processes due to the prolonged time required for testing key quality parameters. The utilization of models developed for treatment facilities presents a viable solution; however, existing open-source models often fall short in accurately predicting treatment efficiency across varying conditions and lack comprehensive accounting of …

Evaluating The Effectiveness Of Lidar And Photogrammetry For Inspecting Mse Walls In Bridges, Shakil Ahmed

College of Graduate Studies: Theses & Dissertations

Mechanically Stabilized Earth (MSE) retaining walls are vital components of transportation infrastructure, providing structural support for embankments and bridge approaches. As many walls approach or exceed their design life, concerns regarding long-term stability, settlement, and displacement have increased. Traditional visual inspection remains the most common assessment method; however, it is subjective and often unable to detect subtle geometric changes that may precede structural distress or failure. This study evaluates Terrestrial LiDAR (Light Detection and Ranging) Scanning (TLS) and Close-Range Photogrammetry (CRP) as nondestructive, noncontact alternatives for detecting displacement in MSE retaining walls. Three representative sites were investigated: a Control Wall …

An Approach To Quantifying The Lifecycle Sustainability Impacts Of Tungsten Carbide Tools, Gatewood Arnold, Julian Polizzi, Syed Ibn Mohsin, Daniel Carnesi, Julius Schoop, Fazleena Badurdeen

Mechanical Engineering Faculty Publications

Tungsten carbide cutting tools are widely used for their high machining performance and low cost. However, their cost does not currently reflect the material rarity, environmental costs, nor societal costs associated with their production. Critically, embodied energy makes a sizeable contribution to the total lifecycle energy consumption. This study quantifies the true triple bottom line cost of the tools with respect to established sustainability metrics by leveraging cross-disciplinary insights from the product, process, and system levels. Based on the adjusted cost, a comparative analysis of the cutting tool sustainability on the profitability of a nickel-based superalloy machining process was carried …