Digital Commons Network^™

Physical Simulation Experiments On 4d Visualization Of Dynamic Methane Diffusion And Adsorption In Low-Porosity And Low-Permeability Coals, Liu Tong, Jiao Baizhuo, Lin Baiquan, Sang Shuxun, Yang Wei, Liu Shiqi, Liu Ting, Li He, Yang Mingxing

Coal Geology & Exploration

Objective and Method The diffusivity of methane (CH₄) in coal seams significantly influences the surface extraction of coalbed methane (CBM) and underground gas drainage. However, the visualized characterization of the diffusion and migration processes of CH₄ in coals remains challenging. To address this issue, this study systematically demonstrated the similarity between krypton (Kr) and CH₄ in their adsorption and diffusion behavior in coals. Utilizing Kr—a gas with high X-ray attenuation—as a tracer substitute for CH₄, this study achieved the transparent observation of the dynamic gas migration process in low-porosity, low-permeability, and heterogeneous coals using …

3d Point Cloud Analysis With Classification, Segmentation And Few-Shot Learning, Jiajing Chen

Dissertations - ALL

Deep learning for 3D point cloud analysis has made significant progress, yet several critical challenges, including the following, remain underexplored: (1) traditional max-pooling operations discard a substantial portion of learned features, resulting in information loss and inefficient use of computational resources; (2) existing few-shot point cloud classification models lack robustness when faced with occlusion, missing points, and limited training data; (3) semantic segmentation methods often fail to fully exploit background–foreground interactions, leading to reduced accuracy. Moreover, in domains such as gait recognition and visual program synthesis, research has been largely dominated by 2D-based approaches, leaving the potential of point cloud …

Green Ai-Enhanced Deep Learning Model For Breast Cancer Detection And Classification In Mammography Images: Bc-Net-512, Nesma Abd El-Mawla, Mohamed A. Berbar, Nawal A. El-Fishawy, Mohamed A. El-Rashidy

Mansoura Engineering Journal

This study champions a sustainable approach for developing a Deep Learning (DL) model for medical image analysis, specifically focusing on breast cancer (BC) detection in mammograms. By prioritizing low-computing algorithms to achieve high diagnostic accuracy while minimizing the model's environmental footprint, that aligns with the principles of Green AI. In this paper, an innovative architecture called BC-Net-512 was constructed for the classification of BC mammography. It is composed of lightweight Convolutional Neural Network (CNN) blocks for texture, density, and structure feature extraction and detection, a thin, fully connected layer for learning complex patterns and correlations in the extracted features, and …

A Method For Determining Integrity Degree Of Tunnel Surrounding Rock Based On Mobilenet, Liu Houxiang, Yang Caixia

Journal of China & Foreign Highway

To determine the integrity degree of tunnel surrounding rock more efficiently,a precise determination method for the integrity degree of tunnel surrounding rock based on the lightweight neural network MobileNet-v 2 was proposed.Firstly,the image was grayscaled and denoised,and the edges of cracks were detected.Then,the lightweight neural network MobileNet-v 2 model was pre-trained on the ImageNet dataset,and combined with transfer learning to complete data detection on the training,validation,and testing sets.Finally,a comparative experiment was conducted with traditional neural networks RestNet- 50 and VGG 16.By identifying the area,width,and length of cracks,the crack ratio Ks was introduced as an indicator to evaluate the integrity of …

Latent Action Trajectory Optimization, Rahul Milind Kandekar

Master's Theses

Learning from demonstrations offers a path to bypass the sample inefficiency of reinforcement learning, but obtaining action-labeled expert demonstrations remains expensive and often impractical. Learning from Observations (LFO) addresses this by learning policies from observation-only demonstrations. Recent LFO work relies heavily on behavior cloning: VPT and LAPO use observation-only data combined with limited action labels to train BC policies, while AIME offers an alternative policy inference approach but requires the majority of its training data to have action labels. Through systematic experiments in the Lunar Lander environment, we investigate whether latent action methods can function when state and action dimensionalities …

A Decision Support Model For Building Material And Component Reuse In The Context Of Circular Buildings, Havva Aksel

Journal of Sustainable Construction Materials and Technologies

Construction activities cause significant environmental impacts such as waste generation, pollution, resource consumption, and land use, which are expected to increase with global construction demands. To mitigate these environmental problems, the circular building occurs as an emerging concept depending on in the circular economy, which aims to minimize waste and redefine the “end-of-life” concept by reducing, reusing, recycling, and recovering materials. The reuse of building materials and components (BMCs) from existing structures represents a crucial strategy for achieving circularity in the built environment. Within this framework, design plays a key role. However, designing with reclaimed BMCs remains complex due to …

Cache-Conscious Sparse Matrix Dense Matrix Multiplication On Gpus, Haoqiang Guo

LSU Doctoral Dissertations

Over the past decade, high-performance deep learning has evolved into a critical research domain, driven by the demand for efficient models and high inference throughput. Deep learning architectures have shifted from stacked convolutional layers to transformer-based models, while pruning techniques and graph-structured data have established sparse matrix–dense matrix multiplication (SpMM) as a fundamental kernel—particularly in graph neural networks (GNNs). Modern GPUs, with their massive parallelism and high-bandwidth memory, offer immense potential for accelerating these workloads. While SpMM implementations using the compressed sparse row (CSR) format remain common to avoid conversion overhead, preprocessing-based methods have recently demonstrated superior potential. In GNN …

Mapping Sustainability To Cybernetic-Generative Artificial Intelligence-Based Education: An Innovative Neutrosophic Orbifold-Lattice Methodology, Mona Mohamed, Ahmed A. Metwaly

Neutrosophic Systems with Applications

The lightning-fast development of artificial intelligence (AI), notably generative artificial intelligence (Gen AI) technologies, has intrigued multiple disciplines, particularly education. In this context, Large Language Models (LLMs) serve as beneficial cognitive resources that address knowledge deficits and provide tailored educational support for learners and staff. For learners, LLMs are regarded as knowledgeable educators who offer prompt, focused responses and rationales to tricky queries. Whereby LLMs for staff, Strength enhancer, automating tedious tasks, and creating intelligent resources.Gen AI’s rapid growth offers enormous obstacles for educational systems, compelling them to discover solutions for these obstacles.

Conceptually, cybernetics is leveraged for bridging the …

Vibrissae-Inspired Vision-Based Magnetic-Actuated Whisker, Zhixian Hu, Yi Cheng, Juan P. Wachs, Yu She

School of Industrial Engineering Faculty Publications

Tactile perception is significant for robotic operation in unstructured environments. Whisker-based sensors offer lightweight bio-inspired solutions, yet most rely on single-whisker sensing and are limited by passive interaction and constrained functionality. Here we present a circular array of eight independently actuated whiskers, each driven by a pulse-switchable permanent magnet and tracked by a camera. This design enables simultaneous multi-point sensing and coordinated actuation, supporting diverse functions. Quantitative analyses demonstrate accurate pixel-to-physical mapping, consistent pixel-to-force characterization, and long-term repeatability. In this work, we show that an vibrissae-inspired vision-based magnetic-actuated whisker array integrating distributed perception with active interaction achieves reliable physical mapping, …

Characterization And Control Of Rod-Like Soft Robots, Tianrui Li

Mechanical Engineering Research Theses and Dissertations

Micro-scale robotic systems have garnered significant interest for applications in micromanufacturing and biosensing, yet quantitative design rules linking geometry, stiffness distribution, and magnetic actuation to locomotion performance at low Reynolds number remain limited. This thesis investigates magnetically actuated rod-like soft robots composed of hydrogel filaments with embedded micro-magnets and tunable hard:soft length ratios. Four- and eight-magnet swimmers with hard:soft ratios ranging from 1:1 to 2.5:1 and 4:3:1 are fabricated using a simple molding-and-insertion process and tested in water and silicone oil. A triaxial Helmholtz coil system generates rotating magnetic fields from 1 to 10 Hz, and a custom image-processing pipeline …

Application Of Reinforcement Learning To Precision Aerial Delivery System Control In Adverse Wind Conditions, Radman Zarbock

The Journal of Purdue Undergraduate Research

Precision aerial delivery systems (PADS) are a subset of airdropped parachute-leveraging package delivery systems that use autonomous guidance, navigation, and control (GNC) to reach targets with high degrees of accuracy. This technology emerged in the 1990s, and strides have been made since to improve the reliability of traditional physics-based controllers that guide PADS. However, these algorithms still struggle to deliver acceptable performance results when PADS are subjected to austere operating environments, such as those with unpredictable wind. Building on a foundational study in 2022 that used artificial intelligence (AI) and machine learning to improve PADS GNC performance, this study aims …

Flood Prediction With Sentinel-1 Synthetic Aperture Radar From Hurricane Helene, Jingyu Xiao, Jessica Li

The Journal of Purdue Undergraduate Research

Floods are the most common natural disaster globally, causing thousands of deaths every year. Timely and accurate flood forecasts are crucial for developing early warning systems, evacuation plans, and effective strategies to enhance community resilience. Soil moisture is an important parameter in flood forecasting. Unfortunately, existing soil moisture sensor networks and optical remote sensing–based techniques for soil moisture estimation lack the spatial resolution needed for accurate flood forecasting. This study presents an approach for flood prediction using Sentinel-1 C-band synthetic aperture radar (SAR) data. SAR offers high spatial resolution and operates day and night under all weather conditions, making it …

Implications Of Noninvasive Blood Pressure Pumps On Mean Arterial Pressure, Sammie Miller

The Journal of Purdue Undergraduate Research

Noninvasive blood pressure pumps are recommended as the primary form of acquiring patient blood pressure to test for blood poisoning. The Philips IntelliVue Patient Monitor MP5, the Philips SureSigns VS4/VS3 Vital Signs Monitor, the Philips EarlyVue VS30 Vital Signs Monitor, the Philips IntelliVue Patent Monitor MP2/X2, the Philips IntelliVue Patent Monitor MMS, and the Philips IntelliVue Patent Monitor MP3/X3 were tested for accuracy. The control condition for hypotension was 95/55 (68) mmHg, normal blood pressure was 120/80 (93) mmHg, and hypertension was 155/85 (108) mmHg. The order of values is arrayed according to diastolic, systolic, and mean arterial pressure. The …

From Test Tracks To Carbon Tracks: Evaluating The Carbon Emissions Of Autonomous Vehicle Development, Sarah Deniz

The Journal of Purdue Undergraduate Research

Autonomous vehicle (AV) development has seen a sharp increase in the past 10 years, and there is a significant energy cost of training AVs to meet safety regulations. The training process includes virtual simulation training as well as physical training on public roads and within private testing facilities. The high energy expenditure associated with AV training has a respective environmental cost that can be quantified as a lifetime “carbon debt” of released carbon emissions. The environmental sustainability of AVs has not been thoroughly studied in currently available literature, and this paper showcases a model that quantifies the total “carbon debt” …

Control Techniques And Design Of Load-Side Controls For The Mitigation Of Late-Time High-Altitude Electromagnetic Pulse, Connor A. Lehman, Rush Robinett, Wayne Weaver, David G. Wilson

Michigan Tech Publications

This paper introduces a novel control archetype designed to mitigate high-altitude electromagnetic pulse (HEMP) (Formula presented.) disturbances on the power grid, as well as information on performance and specifications of different control laws for the controller archetype. This method of protection has been overlooked in the literature until now. A controlled voltage supply is placed on the load-side of a transformer, diverting unwanted power from the transformer core to prevent saturation. The controlled voltage source is modeled using four control laws: an integral controller (capacitor), Linear Quadratic Regulator (LQR), an energy storage minimized feedforward control law, and a Hamiltonian feedback …

Probing The Mechanisms Of Reinforcement Learning: Reinforcement Learning, Ventral Striatal Astrocytes, And The Dynamic Coordination Of Information Seeking With Learning, Fatih Sogukpinar

McKelvey School of Engineering Graduate Student Theses & Dissertations

While reinforcement learning has been a vital component in artificial intelligence and machine learning, there exist many open questions about its implementations and how to improve them, in both minds and machines. Among these are i) the contribution of non-neuronal cell types to reinforcement learning, and ii) information-seeking behavior during reinforcement learning. In this thesis, we studied these main topics pertaining to reinforcement learning. In the first chapter, we examined the role of astrocytes in reinforcement learning, and in the second, we investigated human information seeking during reinforcement learning. Neurons in the human and animal brain have been known to …

Evaluation And Calibration Of Coupled Low-Cost Particulate Matter Sensors, Tyler Cargill

McKelvey School of Engineering Graduate Student Theses & Dissertations

Low-cost sensors (LCS), if used appropriately, are useful instruments to elucidate human exposure to particles suspended in the air (i.e. particulate matter, PM). Characterizing this exposure is crucial, as exposure to PM2.5 (i.e. particles with aerodynamic diameter ≤ 2.5 μm) negatively affects the respiratory, cardiovascular, and other organ systems and is the leading environmental burden for global mortality. Similarly, exposure to particles with aerodynamic diameters greater than 2.5 μm and less than or equal to 10 μm, here forth termed as PMCoarse, is known to cause health ailments for the upper respiratory system. This dissertation focuses on the MODULAIRTM-PM (MOD-PM), …

Fasttree-Guided Genetic Algorithm For Credit Scoring Feature Selection, Rashed Bahlool, Nabil Hewahi Prof., Youssef Harrath Dr.

Research & Publications

Feature selection is pivotal in enhancing the efficiency of credit scoring predictions, where misclassifications are critical because they can result in financial losses for lenders and exclusion of eligible borrowers. While traditional feature selection methods can improve accuracy and class separation, they often struggle to maintain consistent performance aligned with institutional preferences across datasets of varying size and imbalance. This study introduces a FastTree-Guided Genetic Algorithm (FT-GA) that combines gradient-boosted learning with evolutionary optimization to prioritize class separability and minimize falserisk exposure. In contrast to traditional approaches, FT-GA provides fine-grained search guidance by acknowledging that false positives and false negatives …

Cybernest: A Step Forward For Training Cybersecurity Professionals, Justin Mott

Theses and Dissertations

The growing complexity of cyber threats has exposed a critical gap between academic cybersecurity education and the operational demands of the workforce. This thesis presents a pilot study for a use-case of CyberNEST, a simulation-based training platform that integrates adversary emulation and threat-informed learning to create realistic, hands-on experiences for cybersecurity students.(17) The system was designed to replicate Security Operations Center (SOC) environments and incident response workflows, allowing participants to investigate, analyze, and respond to simulated attacks under authentic conditions. This pilot-study performed training simulations using the CyberNEST platform, developed by Brigham Young University, with students, collecting data from pre- …

Integration Of Renewable Energy Networks Into Smart Grid Infrastructure: A Matlab/Simulink-Based Simulation Approach, Saturday Noghayin Osaretin

Electrical Engineering Theses

The rising demand for sustainable and resilient energy systems has accelerated the transformation from traditional power grids toward smart grids integrated with renewable energy networks. This thesis explores the integration of solar energy sources into smart grids to replace conventional fossil-fuel-based generation. A simulation model is developed using MATLAB/Simulink to evaluate the operational performance, stability, and adaptability of the proposed smart grid architecture. Key challenges, including intermittency, synchronization, and bidirectional power flows, are identified, and corresponding solutions, such as energy storage systems, are proposed to address these issues. Simulation results demonstrate enhanced grid stability, reduced carbon footprint, and improved power …

A Comprehensive Review Of Dental Diseases Detection And Classification Based On Artificial Intelligence Techniques, Nermeen N. Noaman, Yasmin M. Alsakar, Naira E. Elazab, Waleed M. Mohamed, Mohamed E. Ezzat, Mohammed M. Elmogy

Mansoura Engineering Journal

In dentistry, many diseases, such as gum, cavities, and oral cancer, affect people of all ages. Early treatment and diagnosis are crucial for minimizing dental diseases' effect on overall health and saving money in the long run. Traditional dental diagnosis methods, such as manual probing and visual inspection, are time-consuming and can be subject to human errors. Hence, a computer-aided diagnosis system based on computer vision and artificial intelligence (AI) techniques is needed. The considerable progress in computer vision and AI techniques offers many possibilities in dental diagnosis based on dental X-ray imaging modalities. Dental X-rays are used to diagnose …

Evaluating Traffic Safety And Geometric Characteristics Using Machine Learning Ensemble Techniques: A Case Study Of Egyptian Rural Multi-Lane Divided Roads, Sania R. Elagamy, Ahmed N. Awaad, Usama E. Shahdah, Sherif M. El-Badawy, Marwa E. Elbany, Eman K. Ali

Mansoura Engineering Journal

Crash prediction models are essential for evaluating traffic safety by analyzing crash occurrence, frequency, or severity. Recently, machine learning techniques have gained prominence in statistical regression modeling and data analysis. This study assesses the effectiveness of machine learning in predicting crashes on Egyptian rural multi-lane divided roads using limited regional data. Supervised machine learning ensemble techniques were applied to predict crash-prone segments (classification) and estimate the total number of crashes per segment (regression). A comparative analysis aims to identify the most suitable method. The Synthetic Minority Oversampling Technique (SMOTE) addressed data imbalance, while K-means Clustering (KC) enhanced regression model accuracy, …

Comparative Analysis Of Machine Learning And Statistical Models For Railroad–Highway Grade Crossing Safety, Erickson Senkondo, Deo Chimba, Masanja Madalo, Afia Yeboah, Shala Blue

Civil and Architectural Engineering Faculty Research

Railroad-highway grade crossings (RHGCs) are critical points of conflict between roadway and rail systems, contributing to over 2000 crashes and 250 fatalities annually in the United States. This study applied machine learning methods (ML) techniques to model and predict crash frequency at RHGCs, using a comprehensive dataset from the Federal Railroad Administration (FRA) and Tennessee Department of Transportation (TDOT). The dataset included 807 validated crossings, incorporating roadway geometry, traffic volumes, rail characteristics, and control features. Five ML models—Random Forest, XGBoost, PSO-Elastic Net, Transformer-CNN, and Autoencoder-MLP—were developed and compared to a traditional Negative Binomial (NB) regression model. Results showed that ML …

Optimization Of Research Pipeline To Characterize The Effects Of Atp-Sensitive Potassium Channels Mutations On Native Skeletal Muscle Fibers And Evaluate Potential Drug Therapy, Yuezhou Chen

McKelvey School of Engineering Graduate Student Theses & Dissertations

The ATP-sensitive potassium (KATP) channel is a critical metabolic sensor in skeletal muscle, yet its definitive molecular composition and functional roles remain contested. In this study, I conclusively demonstrate that the Kir6.2/SUR2 complex forms sarcolemmal KATP channel in mouse fast-twitch muscle. Genetic knock-out (KO) of Kir6.2 (Kcnj11−/−) or SUR2 (Abcc9−/−) resulted in a similar phenotype with increased fatigue resistance and a pathological rise in unstimulated resting tension at high-frequency stimulation. In contrast, SUR1 (Abcc8−/−) KO was ineffective. Furthermore, a CRISPR/Cas9 knock-in mouse model of a human SUR2A truncation variant (KCGV/KCGV) recapitulated the abnormal force accumulation, demonstrating that even loss-of-function of …

Functional Characterization Of Abcc8 Mutations Potentially Linked To The Transition From Hyperinsulinemic Hypoglycemia To Diabetes, Hao Zhang

McKelvey School of Engineering Graduate Student Theses & Dissertations

ATP-sensitive potassium (KATP) channels, composed of the SUR1 and Kir6.2 subunits encoded by the ABCC8 and KCNJ11 genes, are critical regulators of membrane excitability and insulin secretion in pancreatic β-cells. Gain-of-function (GOF) mutations in these genes cause neonatal diabetes mellitus through impaired insulin secretion and persistent hyperglycemia, whereas loss-of-function (LOF) mutations lead to congenital hyperinsulinism (CHI) with hypoglycemia due to β-cell hyperexcitability. I have addressed a paradoxical form of maturity-onset diabetes of the young (MODY) arising from KATP mutations, in which patients transition from CHI to glucose intolerance later in life. My experiments indicate that many KATP mutations associated with …

Construction Of A Unified Knowledge Graph For Cyber Threat Intelligence, Moaz Usama Hassan Mr, Khaled , Nagaty, Noura Elmaghawry

Computer Networks

The rapid expansion and variety of cyber-threat information put enormous pressure on security operations centers (SOCs) that must convert unstructured data into understandable signals and make decisions upon it. This paper develops a Cyber-Threat-Intelligence (CTI) framework that integrates vulnerability information, product inventories, and weakness taxonomies into a domain-specific knowledge graph via automatic fusing. The proposed solution covers 284,296 CVEs, 101,644 CPE identifiers, and 965 CWE weaknesses, generating more than 800,000 typed edges linking threats, assets, tactics, and mitigations in an integrated CTI Knowledge graph. The graph was cross validated against four external standard datasets achieves full coverage of ATT&CK CAPEC, …

Evaluating The Performance Of The Primary Heat Exchanger In A Sco2 Brayton Cycle While Firing Solid Fuels, Brian Jeffrey Schooff

Theses and Dissertations

The sCO2 closed-loop Brayton cycle is an alternative to the standard steam-Rankine cycle for generating electrical power from a heat source. The sCO2 Brayton cycle is advantageous because it can be more efficient, use less water, and have smaller turbomachinery than the steam-Rankine cycle. While there are several research groups advancing the technology necessary to utilize the sCO2 Brayton cycle on an industrial scale, none of these groups use solid fuel combustion as the heat source. A Brigham Young University-led project developed and tested a pilot-scale sCO2 Brayton cycle unit (1.6 MWth) using natural gas, pulverized coal, and pulverized biomass …

Enhancing Aerosol Scattering Measurements: Performance Evaluation And Quality Assurance Of Airphoton Integrating Nephelometers In The Surface Particulate Matter Network, Kamlendra Singh Pathak

McKelvey School of Engineering Graduate Student Theses & Dissertations

Integrating nephelometers are key instruments for quantifying aerosol light scattering, a fundamental parameter governing the direct radiative effect of aerosols on climate and visibility, and for interpreting satellite observations of aerosol optical depth. The AirPhoton integrating nephelometer quantifies aerosol light scattering by measuring total scattering from the sample air and subtracting a clean-air reference that represents Rayleigh scattering, instrument wall scattering, and detector background noise. Measurement accuracy depends on rigorous calibration and regular performance evaluation to account for instrumental drift and environmental influences. This study presents a field performance evaluation of the AirPhoton integrating nephelometer within the global Surface Particulate …

Tests Without Borders: A Global Approach To Measuring Visualization Literacy, Olivia A. Guess

McKelvey School of Engineering Graduate Student Theses & Dissertations

Visualization literacy assessments shape how we understand people's ability to interpret data, yet most existing instruments embed Western datasets and assumptions that limit their relevance for global audiences. This thesis argues that because data is personal, assessments must also be culturally grounded. We introduce a unified framework for adapting the Mini-VLAT into 22 regionally responsive short-form assessments, each retaining the structure of the original test while incorporating datasets and scenarios tailored to specific regions around the world. To demonstrate how such adaptations can be customized and validated, we present a detailed case study of a Ghana-adapted Mini-VLAT, developed in collaboration …

Development Of A Multispectral Collagen Detection Dermatology Device For Delineation Of Non-Melanoma Skin Cancers, Anmol Jarang

McKelvey School of Engineering Graduate Student Theses & Dissertations

To diagnose and manage skin disease, clinicians primarily use visual inspection aided with dermatoscopes, which are cross-polarized magnifiers. In recent years, digital cross polarized multispectral imaging systems have been developed to quantitatively assess skin disease. For example, systems like the one developed by Yaroslavsky et al., which utilize red and blue filters, can non-invasively assess the collagen network in the dermis(Yaroslavsky et al., 2003). Visualization of collagen network disruption can make it easier to visualize the boundaries of skin cancers like keratinocyte carcinoma, and therefore easier to excise completely. Current systems use external bandpass filters in front of cameras to …