Engineering Commons^™

Predicting Battery Levels Of Sensor Nodes Using Reinforcement Learning In Harsh Underground Mining Environments, Manish Anand Yadav, Mohamed Elmahallawy, Sanjay Madria, Samuel Frimpong

Computer Science Faculty Research & Creative Works

Underground mining is a hazardous environment, with frequent accidents leading to significant loss of life each year. To enhance safety, sensor nodes monitor key environmental factors such as temperature, toxic gases, and miners' locations, as well as transmit critical messages. Miners interact with these sensors, which track their movements, enabling their location to be determined even without GPS signals. Therefore, predicting the battery life of these sensors is essential for: (i) rerouting miners during emergencies, (ii) ensuring timely maintenance, and most importantly (iii) identifying sensors that need energy harvesting to maintain vital communication within the mine. In this work, we …

Life Cycle Assessment Of Co-Located Floating Solar And Offshore Wind, Danela Sadikaj, Meghann Smith

Department of Earth and Environmental Studies Faculty Scholarship and Creative Works

Is combining floating solar and offshore wind platforms feasible for increasing energy capacity while displacing the environmental impacts that each of these systems has independently? In recent years offshore wind has become a very popular option to decarbonize the energy sector without overtaking valuable land. While floating solar is not a new technology, using solar in a marine environment is still in an experimental phase. This research proposes a Life Cycle Assessment (LCA) model of co-located solar technology within the proposed offshore wind farms near New Jersey’s coastline. While both technologies themselves are zero-emission while operating, they each require a …

Reducing Emissions And Increasing Resource Efficiency In Offshore Wind Turbines: Insight From Life Cycle Analysis, Jean Claire Pineda, Meghann Smith

Department of Earth and Environmental Studies Faculty Scholarship and Creative Works

Globally, offshore wind (OSW) has been identified as a key technology for decarbonization. While OSW’s development timeline remains uncertain in the United States, New Jersey has set the ambitious goal of 11 GW by 2040. OSW produces zero carbon emissions; however, it relies heavily on resource-intensive materials like steel, rare earth elements, and copper, and manufacturing those materials have numerous environmental impacts, including carbon emissions. Supply chain disruptions—from COVID-19, rising material costs, and geopolitical challenges—add further complexity. Previous research modelled the environmental impacts of Atlantic Shores OSW South Project with an established domestic supply chain, producing 0.013kg CO2 per kWh. …

Memory-Augmented Llm Agent For Predicting Locomotion Modes In Construction Activities, Ehsan Ahmadi

LSU Doctoral Dissertations

The construction industry faces significant challenges, including labor shortages, high physical demands, and safety risks, necessitating advanced assistive technologies like exoskeletons to enhance worker efficiency and reduce injuries. However, effective exoskeleton control in dynamic construction environments requires accurate locomotion prediction, a task complicated by the diversity of activities and reliance on supervised learning methods that struggle to generalize. This study investigates a multimodal approach to locomotion prediction, leveraging speech commands and visual data from smart glasses to enable adaptive and safe human-exoskeleton interaction. The research unfolds in two stages: the first develops a framework to evaluate the zero-shot capability and …

Real-World Implementation Of A Noninvasive, Ai-Augmented, Anemia-Screening Smartphone App And Personalization For Hemoglobin Level Self-Monitoring, Robert G. Mannino, Julie Sullivan, Jennifer K. Frediani, Paul George, Jeremy Whitson, James Tumlin, L. Andrew Lyon, Erika A. Tyburski, Wilbur A. Lam

Engineering Faculty Articles and Research

Anemia, characterized by low blood hemoglobin (Hgb) levels, afflicts >2 billion individuals worldwide. Here, we report real-world data generated by a smartphone app that noninvasively screens for anemia using only “fingernail selfies.” App data for anemia screening were obtained from >1.4 million uses across the United States enabling geographic mapping of Hgb levels. Of those, 9,061 users also self-reported complete blood count Hgb levels for comparison, resulting in accuracy and performance that match gold standard laboratory testing and a sensitivity and specificity of 89% and 93%, respectively, when using an anemia cutoff of 12.5 g/dL. Geotagged data enabled construction of …

Computational Complexity Of Soundness Verification For Neural Networks, Scott Sirri

McKelvey School of Engineering Graduate Student Theses & Dissertations

Neural networks are an increasingly ubiquitous tool in systems of varying complexity across a range of domains. While these tools can be used to learn and predict complex functions, their opaque nature limits the scope of their acceptable applications. In particular, a lack of performance guarantees means that they are unsuitable for safety-critical applications such as self-driving cars and scheduling systems. Neural networks trained to solve NP-complete problems, in particular, are unlikely to be able to solve the problem exactly. However, a weaker soundness guarantee may be sufficient for some systems, e.g., that positive instances of the problem may be …

On The H-Property For Step-Graphons: Residual Case, Wanting Gao

McKelvey School of Engineering Graduate Student Theses & Dissertations

We investigate the H-property for step-graphons. Specifically, we sample graphs Gn on n nodes from a step-graphon and evaluate the probability that Gn has a Hamiltonian decomposition in the asymptotic regime as n → ∞. It has been shown in Belabbas and Chen (2023); Belabbas et al. (2021) that for almost all step-graphons, this probability converges to either zero or one. We focus in this paper on the residual case where the zero-one law does not apply. We show that the limit of the probability still exists and provide an explicit expression of it. We present a complete proof of …

Multi-Modal Mri For The Pre-Clinical Evaluation Of Hiv-Linked Changes In The Central Nervous System, Gabriel Gauthier

Theses & Dissertations

Though the inception of anti-retroviral therapy (ART) has fundamentally changed the life expectancy of human immunodeficiency virus (HIV) patients, accessibility and outcomes vary enormously along demographic lines. Even for people living with HIV (PLWH) with perfect access and adherence to anti-retroviral drugs (ARVs), modern treatment plans are fundamentally unable to secure complete viral remission for patients. The cause of this perpetual infection is the persistence of viral reservoirs in the central nervous system (CNS), hidden beyond the reach of modern ARVs, leaving patients to deal with lifelong medication side-effects and risks of developing HIV-associated neurodegenerative disorders (HAND). Despite improving outcomes …

Feasibility Analysis For The Implementation Of An Anaerobic Digestion System In The City Of Pittsburgh, Pa, Gianna L. Kolencik

Electronic Theses and Dissertations

The current study is investigating the feasibility of an anaerobic digestion system

in Pittsburgh, Pennsylvania, at the old State Correctional Institute (SCI-Pittsburgh)

located at 1922 Westhall St. This location is immediately upstream of the Allegheny

County Sanitary Authority (ALCOSAN) along the Ohio River. Municipal solid waste

from ALCOSAN may be used as the main form of feedstock. ALCOSAN produced

roughly 36,500 tons of dry sludge in the reporting year 2023-2024. Based on the volume

of dry sludge from ALCOSAN it is estimated that an anaerobic digestion system could

yield approximately 29,930,000 kWh of energy, which is enough to power over …

Direct Computations Of Spatially Resolved Viscoelastic Moduli Of Biomolecular Condensates, Liwen Gu

McKelvey School of Engineering Graduate Student Theses & Dissertations

Biomolecular condensates are viscoelastic materials formed by liquid-liquid phase separations (LLPS) of biopolymers. In this study, we develop a modified graph Laplacian-based collective model to characterize viscoelastic heterogeneity within condensates based on results of lattice-based Metropolis Monte Carlo (MMC) simulations. By integrating random graph models and simulations of A1-LCD, a type of intrinsically disordered protein, we examine how network topology influences storage modulus, loss modulus, crossover frequency, and relaxation time spectra. Our results reveal a strong correlation between topological features and mechanical response, with the condensate interior exhibiting higher stiffness and faster relaxation than the interface. The relaxation spectra provide …

Development Of Interactive Games On An Affordable Braille Display, Daniel Tsivkovski, Dylan Ravel, Maryam Etezad

Student Scholar Symposium Abstracts and Posters

Developing an affordable and STEM learning-focused Braille display addresses a significant disparity in the market for Braille displays, where most fail to provide a cost-effective, accessible, and education-oriented solution. This research aims to bridge this gap through innovative hardware and software development, offering a comprehensive learning experience to elementary school children (K-6) who are blind/visually impaired. The hardware features a piezo-electric tactile display that displays up to six Braille characters at once or a shape in an 8x8 pin array configuration. The educational software includes a user-friendly website packed with engaging STEM activities specifically designed for blind/visually impaired children. The …

Ecodrone: Autonomous Environmental Monitoring, Belsen Lee

Student Scholar Symposium Abstracts and Posters

This project presents EcoDrone, an autonomous aerial drone designed for continuous and automated environmental monitoring. Current environmental monitoring methods rely on stationary sensors or manual data collection, limiting real-time response capabilities. This reliance leads to delayed, incomplete, and spatially limited data and restricts the ability to capture real-time changes. Another challenge includes the difficulty of environmental monitoring in challenging terrain, whether it be wildfire areas, dense forestry, or mountainous terrain. EcoDrone overcomes these challenges by autonomously navigating difficult terrain to collect real-time data, offering more flexible and timely monitoring than stationary or manual methods. The central research question investigates integrating …

Praxly: An Online Ide For The Praxis Cs Test Pseudocode, Benjamin Saupp

James Madison Undergraduate Research Journal (JMURJ)

No abstract provided.

Characterization Of A Magnetically Contained Hot Filament Plasma Source With A Wide-Sweeping Langmuir Probe, Jonas Rowan

Doctoral Dissertations and Master's Theses

Ionospheric plasma research in the Space and Atmospheric Instrumentation Laboratory’s Space Plasma Chamber has been hindered by the lack of a suitable plasma diagnostic instrument and understanding of its hot-filament plasma source. This thesis describes efforts made to remedy both problems. A wide-range Sweeping Langmuir Probe was developed with a ±35 V sweeping range to fully analyze ion and electron saturation regions in the entire IV curve. A method was derived to estimate the chamber source’s filament temperatures. The new Langmuir probe was integrated into a refurbished automated system designed in Python to measure plasma parameters for various chamber conditions, …

Satellite Reorientation Using Reinforcement Learning Under Unknown Attitude Failure, Matthew Willoughby

Doctoral Dissertations and Master's Theses

This study presents a reinforcement learning (RL) approach for reestablishing communication with deep-space satellites under unknown attitude determination and control system (ADCS) failures. When traditional fault-tolerant control methods cannot restore signal, the proposed RL controller acts as a last-resort measure by autonomously reorienting the satellite’s antenna toward Earth while charging the battery via solar panels. A generic reward function, designed for the RL-based method, enables the controller to adapt to diverse failure scenarios, including severe actuator noise, misalignment, and complete actuator failure. Simulations are conducted in the Basilisk environment and trained with the tonic framework and demonstrate ranging capabilities of …

Soft Modular Robots: From Modular Tensegrity Structures To Bioinspired Sea Robots, Luyang Zhao

Dartmouth College Ph.D Dissertations

The rapid advancement of robotics necessitates systems capable of adapting to complex, unstructured environments. Soft robots, with their flexibility and compliance, excel in delicate interactions, making them ideal for medical applications and search-and-rescue missions. Modular robots, on the other hand, offer reconfigurability, enabling diverse task-specific adaptations in dynamic settings. Despite their individual advantages, the integration of soft and modular robotics remains underexplored. This proposal aims to develop soft modular robots that combine the adaptability of soft robotics with the versatility of modularity. These systems will be capable of autonomously transitioning between locomotion, manipulation, and infrastructure assembly across land, water, and …

Estimating Pedestrian Crossing Times At Scramble Crossings Via Machine Learning And Agent-Based Modeling, Sho Takami

Honors Capstones

Scramble crosswalks differ from conventional crosswalks in their ability for pedestrians to cross diagonally. This research compares the average crossing times and investigates the walking behaviors that pedestrians adopt to produce the speediest times in the two crosswalk configurations. Identification of the most efficient set of walking behaviors is done through an agent-based model, whereas producing polynomials relating crossing times to the most prominent walking behaviors is done through regression algorithms in machine learning. With the combination of these two approaches, it is revealed that pedestrians must adopt a relaxed walking style to make each crosswalk configuration efficient. Additionally, between …

05.05.2025 Ored Connect, Liz Williamson

ORED Newsletter

Research Showcase Photos

Showcase Raffle Winners

Chancellor's Award for Research and Creative Scholarship

Video of the ORED website

Recent U.S. Government Policy Literature On Critical And Strategic Minerals, Bert Chapman

Libraries Faculty and Staff Scholarship and Research

Critical and strategic minerals have become increasingly important in U.S. government civilian and military policymaking in recent years. This is demonstrated by the heavy use of such minerals in many critical civilian and military infrastructures. This work will discuss how this subject has been addressed in laws, presidential documents, and works by government agencies along with congressional oversight committees and support agencies. It will stress how the United States is heavily dependent on strategic minerals from adversarial foreign countries such as China and will examine U.S. efforts to increase its ability to produce such materials in the United States by …

First-Principles Studies Of Electrical Polarization Effects In Ferroelectrics, Antiferroelectrics And Defects, Louis Alaerts

Dartmouth College Ph.D Dissertations

Over the last few decades, density functional theory (DFT) has emerged as a formidable tool in the field of computational material science. Not only has it become a complementary method approach to experiments by rationalizing the many complex properties of materials but its formidable predictive power can also be used to identify the most promising candidates for specific applications. Point defects in semiconductors have become an important platform for the development of quantum networks due to their ability to act as spin-photon interfaces. Spectral diffusion, the broadening of the optical emission line, can significantly impact the performance of these defect-based …

Intercellular Stress Generation During 1d Collective Migration Of Cancer Cells, Logan Waddle

Physics Undergraduate Honors Theses

Physical forces drive many cellular processes such as migration and proliferation. A metastatic tumor will have invasive strands/chains that extend from the main tumor. These chains of cells collectively migrate away from the main tumor to establish new colonies elsewhere in the body. However, how physical forces drive this collective invasion and the required energy for this process is not well understood. Invasion of a metastatic tumor to surrounding tissues leads to a majority of cancer-associated death and is often a collective effort among cells, it is therefore important to fully understand the process behind collective cancer invasion.

The goal …

A Hierarchical Soft Computational Model For Optimizing Agricultural Uavs: Recruiting Neutrosophic Theory And Tree Soft Sets, Mona Mohamed, Nurhan Alaa, Bilal Arain, Karam M. Sallam

Neutrosophic Systems with Applications

Precision agriculture is being transformed by Unmanned Aerial Vehicles (UAVs), which make it possible for yield optimization, targeted spraying, and sophisticated crop monitoring. With an emphasis on their operational capabilities, economic feasibility, and environmental implications, this research explores the revolutionary potential of UAV technology in contemporary farming systems. Practically speaking, the procedure of opting UAVs for agricultural applications is complicated by several competing aspects, inherent uncertainties, and differing stakeholder agendas. This paper suggests a new hybrid decision framework that combines Tree Soft Sets (TrSS), Neutrosophic theory, and Multi-Criteria Decision-Making (MCDM) to methodically handle these issues. Hence, the robust hybrid model …

Towards Explainable And Robust Nlp: Neutrosophic Probability Augmentation In Text Classification, Nabil M. Abdel-Aziz, Mahmoud Ibrahim, Khalid A. Eldrandaly

Neutrosophic Systems with Applications

The rapid growth of textual data necessitates advanced text classification models. However, traditional methods struggle with ambiguity and uncertainty in natural language, reducing classification reliability. To address this, we integrate neutrosophic logic, which explicitly models truth, indeterminacy, and falsity, into a DistilBERT-based text classification framework. Additionally, we employ data augmentation using synonym replacement to enhance generalization. Our approach is evaluated on the AG News dataset, classifying articles into four categories: World, Sports, Business, and Science/Technology. By incorporating neutrosophic attributes, the proposed framework assesses text quality, mitigates uncertainty, and improves robustness against ambiguous inputs. Experimental results demonstrate an accuracy of 94.10%, …

A Review Of Disassembly Systems For Circular Product Design, Giovanni Formentini, Joao Pj. Prioli, Junwon Ko, Buddhika M. Hapuwatte, Vincenzo Ferrero, Fazleena Badurdeen, Jeremy L. Rickli, Devarajan Ramanujan

Mechanical Engineering Faculty Publications

Circular Economy (CE) is described as a means for maintaining products and materials in circulation while regenerating nature. This shift requires considering aspects at the product design phase that were not previously prioritized. One such aspect, disassembly, is a key enabler for CE. Design for Disassembly methodologies have been deployed for several years to enhance disassembly performance. However, when CE is of interest, it is essential to consider how disassembly affects the entire product life cycle system. In this regard, this paper proposes a literature review of relevant DfD methods from a system engineering perspective to evaluate their effects on …

Toxicity And Biodegradability Of Novel Boronium Vs Conventional Ammonium Based Anti Microbial Compounds In Wastewater Treatment Systems, Noor Shalan

Poster Presentations

Quaternary ammonium compounds (QACs) are highly effective as disinfectants, herbicides, and pesticides; thus, overuse causes elevated levels of residual toxicity in domestic and industrial wastewater. QACs can be toxic to essential bacteria breaking down pollutants in wastewater treatment plants (WWTPs) and can remain untreated in effluent, harming the environment, and contributing to antibiotic resistance, posing risks to human health. Novel boronium-based antimicrobial compounds have demonstrated efficacy in eliminating bacteria, fungi, and viruses. If the boronium compounds exhibit lower residual toxicity, they could offer a promising alternative to QACs. Because these compounds are still in development, their potential toxicity to the …

Binary Solid/Liquid Equilibrium Of Mixtures Of Thermally Robust Salts And Molecular Compounds For Use As Heat Transfer Fluids, Jared Ridge Mathews

Poster Presentations

Fossil fuels, contributors to climate change that may bear catastrophic consequences, power the entire world. The human species is almost entirely dependent on fossil fuels for energy, but other sources of renewable and environmentally friendly energy must be developed. Concentrated solar power (CSP) is a promising source of renewable energy with hampered potential—better heat transfer fluids (HTFs) are needed for it to be economically feasible. Currently, the HTFs in industrial use are predominantly either synthetic oils or nitrate-based molten salts. Synthetic oils are only stable up to 400 °C, and molten salts often have high melting temperatures, making them prone …

Ghosts In Glass: Ghost Crabs (Ocypode Quadrata) As Judges Of Glass Sand For Coastal Restoration, Emily Parrish

Poster Presentations

Coastal erosion is heavily impacting coastal ecosystems across the Gulf. For instance, the state of Louisiana loses a football field worth of land every 100 minutes (Couvillion, 2017). The drastic loss of coastline highlights the dire need for restoration in the Northern Gulf Coast. An unexpected solution to this sediment loss may solve two major environmental issues at once by diverting millions of tons of glass waste from entering America’s landfills each year. By crushing glass to create sand and gravel for coastal restoration, we may generate a consistent and sustainable source of substrate. Our goal is to determine the …

Designing An Interactive Exit Ticket System To Enhance Learning In Engineering Education, Tapanga Witt

McNair Scholars Manuscripts

Within Grand Valley State University's (GVSU) Padnos College of Engineering, many first-year Engineering courses consistently see pass rates below 70%, signaling a need for stronger academic support. This is an issue across many universities; students are underprepared and face a lot of challenges with workload, pace, and independence due to the transition from high school to college (Flanigan, 2024). For this project, I designed and developed a website-based exit ticket system to support student reflection and instructor feedback. Using UX design principles, the platform offers a weekly self-reflection form that recommends resources like tutoring, office hours, or study groups. Gamification …

Low-Field Magnetoresistance In Nanocomposites Of La₀.₇Sr₀.₃Mno₃ And Metal Oxides, Nicholas K. Thiel-Hudson

University Scholar Projects

Pure La_0.7Sr_0.3MnO₃ (LSMO) exhibits colossal magnetoresistance (CMR) with large applied magnetic field over a narrow temperature range (intrinsic behavior), limiting its application to narrow temperature ranges. In contrast, the extrinsic CMR effect originates from inhomogeneities at larger length scales, such as grain boundaries and phase separation, where the structural features act as tunneling barriers, leading to a low-field magnetoresistance (LFMR) response, thereby expanding the application of LSMO into the low-field regime over a broader temperature range. In this work, the magnetotransport behavior of pure LSMO thin film is compared to the composite layered heterostructures of …

Controlling A Mobile Inverted Pendulum And Optimizing Leaning Angle To Apply Force Using Reinforcement Learning, Aryan Mediratta

2025 Spring Honors Capstone Projects - Archive

Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning …