Digital Commons Network^™

Transfer Learning Neural Networks For Nuclear Forensic Image Morphology Using Image Splitting Techniques, Niko A. Petrocelli, Lee C. Lambert, Brett J. Borghetti, Abigail A. Bickley

Faculty Publications

Manual morphological analysis of actinide particles from scanning electron microscope (SEM) imagery is a critical component of nuclear forensics but is prone to significant inter-analyst variability. To address this challenge, this work develops and evaluates an automated classification method using deep learning. We introduce a methodology based on partitioning 1906 SEM images, representing 13 classes of uranium compounds, into smaller patches for analysis. Three convolutional neural network (CNN) architectures of increasing complexity were compared: a custom baseline CNN, a simple transfer learning model using ResNet50v1, and a complex model featuring hierarchical feature extraction and a spatial attention mechanism built upon …

Dynamic Magnetic Null Behavior In Planar Ion Diodes: Particle-In-Cell Analysis Of Field Oscillations And Ion Beam Dynamics, Jesse C. Foster, Stephen B. Swanekamp, Paul F. Ottinger

Faculty Publications

Particle-in-cell simulations of a 1.75 MV, 375 kA, and 50 ns planar pinched-beam diode reveal that the strongest gigahertz-frequency oscillations in electric field and ion current arise from the dynamic motion of the magnetic null near the anode tip. These oscillations, which appear when the ion transit time becomes comparable to the local field-variation timescale, periodically expand the effective anode–cathode gap and generate bursts of over-accelerated ions. The resulting ion energy spectrum broadens substantially near the null while maintaining excellent beam uniformity along the anode. The simulations, therefore, demonstrate a direct physical linkage between ion transit time instability and magnetic …

A Comprehensive Biomechanical Material Characterization Of The Human Breast Fibro-Structural Support System, Aroj Bhattarai, Gregory P Reece, Kristy K Brock, Krishnaswamy Ravi-Chandar

Faculty, Staff and Student Publications

Breast surgery for aesthetic purposes, such as breast augmentation or breast reduction, and breast reconstruction after cancer treatment require an accurate structural (anatomical) and mechanical (functional) understanding of the breast components, including the fascial-ligamentous support system of the breast, to achieve optimal results. This paper aims to provide a comprehensive description of the mechanical behavior of the ligamentous and fascial connective tissues of the human female breast. Fasciae and ligaments obtained from 17 patients between 35 and 85 years of age who were undergoing mastectomy and three female cadavers were tested. Uniaxial tensile tests were conducted, and three constitutive models …

A High-Fidelity Multimodal Synthetic Dataset Generation Framework For Off-Road Unstructured Terrain Navigation Training Of Autonomous Robots, Liyana Wijayathunga, Dulitha Dabare, Alexander Rassau, Douglas Chai, Syed Mohammed Shamsul Islam

Research outputs 2022 to 2026

The success of deep learning methods in a wide range of application areas has inspired many recent developments in the urban and off-road autonomous navigation domain. In particular, techniques for semantic scene understanding, a key aspect of the navigation pipeline, have been researched extensively, resulting in many real-world and synthetic datasets. However, in comparison to urban semantic segmentation datasets, the availability of datasets for off-road environments remains sparse. In this paper, we aim to overcome this challenge by introducing a methodology capable of efficiently generating photorealistic synthetic datasets for off-road environments with support for multiple sensor modalities. The developed approach …

An Explainable Transformer-Based Model For Phishing Email Detection: A Large Language Model Approach, Mohammad Amaz Uddin, Md Mahiuddin, Iqbal H. Sarker

Research outputs 2022 to 2026

Phishing email is a serious cyber threat that tries to deceive users by sending false emails with the intention of stealing confidential information or causing financial harm. Attackers, often posing as trustworthy entities, exploit technological advancements and sophistication to make the detection and prevention of phishing more challenging. Despite extensive academic research, phishing detection remains an ongoing and formidable challenge in the cybersecurity landscape. In this research paper, we present a fine-tuned transformer-based masked language model, RoBERTa (Robustly Optimized BERT Pretraining Approach), for phishing email detection. In the detection process, we employ a phishing email dataset and apply the preprocessing …

Emerging Design Paradigms And Microstructural Innovations In Refractory High-Entropy Alloys: A Critical Review, Deyu A. Jiang, Lai Chang Zhang, Kuaishe Wang, Mahmoud Ebrahimi, Wen Wang, Liqiang Wang, Weijie Lu, Di Zhang

Research outputs 2022 to 2026

Refractory high-entropy alloys (RHEAs) are being developed to meet mechanical, thermal and chemical requirements that exceed what current super-alloys can withstand. This review explains how composition design, processing routes and the resulting microstructures now combine to realize that potential. We first link phase selection in BCC-, FCC- and dual-phase RHEAs to atomic-size mismatch, mixing enthalpy and valence-electron concentration, and compare manufacturing paths ranging from arc melting to powder metallurgy, additive manufacturing and vapor deposition, showing how each reshapes grain structure and defect chemistry to improve high-temperature strength, corrosion resistance and irradiation tolerance. Computation-led tools—density-functional theory, calculation of phase diagrams and …

State Of Charge Estimation Of Ev Secondary Battery Pack Using Hybrid Hedge Feedforward Feedback-Based Gated Recurrent Unit To Extend Lifespan, Md Ohirul Qays, Iftekhar Ahmad, Daryoush Habibi, Mohammad A.S. Masoum, Paul Moses

Research outputs 2022 to 2026

Accurate estimation of state of charge (SoC) and maintaining balanced charge levels across secondary battery cells are crucial in battery management systems (BMSs) to extend battery life while improving the performance and thermal stability of Li-ion batteries (LIBs) in electric vehicles (EVs). However, there are still underexplored challenges associated with circulating currents in electrochemical cells during continuous operation which can overheat battery packs, reducing their life span or result in dangerous thermal runaways. This paper investigates SoC estimation using various real-world charging and discharging profiles, along with charge-balancing strategies to enhance the longevity of parallel-connected Li-ion battery cells. A newly …

Explainable Artificial Intelligence Models For Detecting Suspicious Bank Transactions, Narasimha Kumar Narasapuram, Syed Afaq Ali Shah, Mohd Fairuz Shiratuddin, Ferdous Sohel

Research outputs 2022 to 2026

Detecting financial crime is a complex challenge due to evolving criminal strategies and fragmented detection systems, particularly in the areas of money laundering and fraud. While it is easy to implement, traditional rule-based approaches lack adaptability to new threats, and machine learning models, though more effective, often function as opaque "black boxes," limiting their practical use in regulated domains like banking, where interpretability and accountability are essential. This research presents a novel framework that combines intrinsic and post-hoc XAI techniques to detect suspicious bank transactions. Intrinsic methods provide model-inherent transparency, while post-hoc methods offer behavior-level explanations, enabling robust cross-verification of …

Graph Convolution Neural Network And Deep Q-Network Optimization-Based Intrusion Detection With Explainability Analysis, Kelvin Mwiga, Mussa Dida, Leandros Maglaras, Ahmad Mohsin, Helge Janicke, Iqbal H. Sarker

Research outputs 2022 to 2026

As networks expand in size and complexity, coupled with an exponential increase in intrusions on network and IoT systems, this leads to traditional models failing to capture increasingly intricate correlations among network components accurately. Graph Convolution Networks (GCNs) have recently acquired prominence for their capacity to represent nodes, edges, or entire graphs by aggregating information from adjacent nodes. However, the correlations between nodes and their neighbours, as well as related edges, differ. Assigning higher weights to nodes and edges with high similarity improves model accuracy and expressiveness. In this paper, we propose the GCN-DQN model, which integrates GCN with a …

Towards Automated Assessment Of Students Self-Explanations In Code Comprehension, Jeevan Chapagain

Electronic Theses and Dissertations Archive

The field of computer science faces a significant challenge in meeting the growing demand for skilled graduates, despite increasing interest in CS education. A persistent gap between supply and demand is partly attributed to high attrition rates of 30-40% (or higher) in introductory CS courses (CS1 and CS2). While various interventions have been proposed, the scalable assessment of students’ understanding of programming concepts remains a critical challenge, particularly in the context of code comprehension exercises. This dissertation addresses the challenge of automated assessment in code comprehension by developing and evaluating novel approaches for analyzing students’ self-explanations of program code. We …

Vaccination Games Of Boundedly Rational Parents Toward New Childhood Immunization, Wei Yin, Martial L. Ndeffo-Mbah, Tamer Oraby

School of Mathematical & Statistical Sciences Faculty Publications

Infectious diseases harm societies through disease-induced morbidity, mortality, loss of productivity, and inequality. Thus, controlling and preventing them is critical for public health and societal well-being. However, societies can hinder efforts to control the spread of diseases by failing to adhere to public health recommendations, such as through vaccine hesitancy. Various disease-transmission models have been utilized to help policymakers respond to (re)emerging outbreaks. The usefulness of such models in assessing the effectiveness of public health policies is significantly dependent on human behavior. This paper introduces a new model of parental behavior toward a new childhood immunization. The model incorporates societal …

A Manifesto For Plant Science Education, Elizabeth Alvey, Andrea Paterlini, Mary E. Williams, Mia E. Cerfonteyn, Samantha Dobbie, Steven Dodsworth, Sonja D. Dunbar, Lauren R. Headland, Anastasia Kolesnikova, Pankaj Kumar, Silvia Manrique, Catherine Mansfield, Sebastian Stroud, Shannon Woodhouse, Hailey Ashton, Yoselin Benitez-Alfonso, Emily Breeze, Kelsey J.R.P. Byers, Chana P. Chetariya, Beth C. Dyson, Alec Forsyth, Beatriz Gonçalves, Camila Gonzalez, Daniel M. Jenkins, Joanna Kacprzyk, Kirsten Knox, George R. Littlejohn, Sara Lopez-Gomollon, Enrique López-Juez, Claudia Martinho

School of Biological and Marine Sciences

Societal Impact Statement: Plants provide oxygen, food, shelter, medicines and environmental services, without which human society could not exist. Tackling pressing and global challenges requires well-trained plant scientists and plant-aware individuals. This manifesto provides a practical evidence-based vision to strengthen plant science education, focused on five strategic priorities. It is relevant to all stakeholders within plant science and beyond: from frontline educators to institutional leaders; from commercial or charitable professionals to entrepreneurs and donors; from individual community members to their legislative representatives. Strengthening plant science education demands concrete actions from all stakeholders, ultimately to the benefit of us all. Summary: …

Systematic, Bibliographic And Statistical Aspects On Multi Generation Recycled Concrete Materials Research: A Review, Henrique Comba Gomes, Maozhou Meng, Katie Jones, William Vevers, Aissa Bouaissi, Boksun Kim

School of Engineering, Computing and Mathematics

This article aimed to review the current literature related to the topic of multiple generation recycled concrete materials considering systematic, bibliographic and statistical aspects. The review was conducted from an adaptation from the systematic review for engineering and experiments (SREE) method. Papers wrote in English with scientific relevance, title and abstract full aligned with the topic were selected from Scopus and Web of Science databases. Bibliographic aspects highlighted the research novelty, the quality of research and prominence for future works. The systematic review aimed to provide insights in the literature concerning multiple recycling concrete materials. Some of the main aspects …

Temperature Dependence Of The Imaging Properties Of Holographic Lenses, Tomás Lloret, Jorge Lasarte, Suzanne Martin, Izabela Naydenova, Inmaculada Pascual

Research Outputs: 2025-Present

The demand for advanced photonic technologies to enhance augmented reality (AR) devices has led to a significant interest in new optical materials suitable for operation in sometimes challenging environmental conditions, such as elevated temperatures levels. Holographic optical lenses (HOLs), fabricated using holographic recording, offer several advantages over traditional refractive lenses, including greater versatility, lower cost, lower weight, and increased adaptability. In this study, we investigated the optical and thermal performance of HOLs recorded on four different photosensitive materials: Bayfol HX200, Bayfol HX120, a PVA/acrylamide-based photopolymer (AA/PVA), and a photopolymerisable hybrid sol–gel (PHSG). The lenses were exposed to thermal cycles 20 …

Interpretable Machine Learning For Personalized Profiling Of Mild Cognitive Impairment From Daily Activities, Budhitama Subagdja, Ah-Hwee Tan, Kenneth Kwok, Iris Rawtaer

Research Collection School Of Computing and Information Systems

Continuous monitoring of individual daily activities is essential to detect mild cognitive impairment (MCI) wherein timely intervention can still be applied to prevent more severe mental decline. Recent approaches in predicting MCI are mostly considering digital biomarkers across individuals but often neglecting specific indicators from a single person over a long period of time. Making this personalized, dynamic, and highly noisy prediction model with irregular distribution of missing information to be explainable and actionable for clinical use, remains a challenge. This paper presents a study on a personalized MCI prediction and profiling from an in-home and mobile cognitive health monitoring …

A Novel Privacy-Preserving User Information Queries Scheme With Functional Policy, Yuhang Lei, Rui Shi, Yang Yang, Chunjie Cao, Huamin Feng

Research Collection School Of Computing and Information Systems

Privacy-preserving information queries enable a requester to obtain only the value f(x) computed over sensitive data x, while preventing disclosure of the underlying records. Existing approaches typically reveal full data, incur high on-chain overhead, or lack fair and verifiable delivery of function outputs. We propose a general-purpose, blockchain-compatible framework that ensures the requester learns only f(x) with no extra leakage and that the provider receives fair payment. The design integrates Adaptor Signatures (AS) for fair exchange and Inner-Product Functional Encryption (IPFE) for fine-grained function extraction. The framework is domain-agnostic and applicable to privacy-sensitive applications such as medical insurance and financial …

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Hindi

Theses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). The thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows.

The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Stard-Net: Spatiotemporal Attention For Robust Detection Of Tiny Airborne Objects From Moving Drones, Hasibur Rahman, Sanjay Kumar Madria

Computer Science Faculty Research & Creative Works

The rapid adoption of drones across various domains, alongside advancements in computer vision, has driven growing interest in vision-based airborne object detection from moving aerial platforms. However, this task remains challenging due to the small scale of objects, camouflage within cluttered backgrounds, and occlusions. To address these challenges, we introduce an end-to-end detection framework that integrates a Drone Receptive Field Block (DRFB) to extract multiscale and geometrically diverse features, specifically designed to enhance the detection of small and camouflaged airborne objects. To model motion patterns over time while preserving spatial structure, particularly for detecting camouflaged, cluttered and occluded objects with …

A Survey On Heterogeneous Computing Using Smartnics And Emerging Data Processing Units, Nathan Tibbetts, Sifat Ibtisum, Satish Puri

Computer Science Faculty Research & Creative Works

The emergence of new, off-path smart network cards (SmartNICs), known generally as Data Processing Units (DPU), has opened a wide range of research opportunities. Of particular interest is the use of these and related devices in tandem with their host's CPU, creating a heterogeneous computing system with new properties and strengths to be explored, capable of accelerating a wide variety of workloads. This survey begins by providing the motivation and relevant background information for this new field, including its origins, a few current hardware offerings, major programming languages and frameworks for using them, and associated challenges. We then review and …

Intramolecular Nonbonding Interactions And Geared Phenyl Twisting In Para-Disubstituted 1,4-Diphenylazines: Electron Correlation Effects On Molecular Conformations And Enantiomerization, Kaidi Yang, Harmeet Bhoday, Rainer Glaser

Chemistry Faculty Research & Creative Works

The results are reported of potential energy surface (PES) analyses of six symmetrical azines Y_p − Ph − RC=N − N=CR − Ph − Y_p, namely, the benzaldehyde azines 1H, 2H, and 8H with R = H and the acetophenone azines 1M, 2M, and 8M with R = Me. The Y substituents Cl (1), Br (2), and Me (8) were studied because sets of polymorphs I (C2-symmetry, azine twist τ ≈ 135 ± 10°, disrotatory phenyl twists ϕi ≠ 0°) and II (Ci-symmetry, τ = 180°, conrotatory ϕi ≠ 0°) were crystallized for these three azines. The …

Thermodynamically Consistent Incorporation Of The Langmuir Adsorption Model Into Compressible Fluctuating Hydrodynamics, Hyun Tae Jung, Hyungjun Kim, Alejandro L. Garcia, Andrew J. Nonaka, John B. Bell, Ishan Srivastava, Changho Kim

Faculty Research, Scholarly, and Creative Activity

For a gas–solid interfacial system where chemical species undergo reversible adsorption, we develop a mesoscopic stochastic modeling method that simulates both gas-phase hydrodynamics and surface coverage dynamics by coupling the Langmuir adsorption model with compressible fluctuating hydrodynamics. To this end, we derive a thermodynamically consistent mass–energy update scheme that accounts for how the mass and energy variables in the gas and surface subsystems should be updated according to the changes in the number of molecules of each species in each subsystem due to adsorption and desorption events. By performing a stochastic analysis for the ideal Langmuir model and the full …

Active Bone Marrow Dose Reconstruction In A Large-Scale Cohort Study Of Cancer Patients Treated With Photon Radiotherapy, Keith T Griffin, Kishan J Pithadia, Yeon Soo Yeom, Lior Braunstein, Kelly L Bolton, Lindsay M Morton, Choonsik Lee

2020-Current year OA Pubs

BACKGROUND: Previous studies have investigated the dose-response relationship between external beam radiotherapy (EBRT) and leukemia by reconstructing the mean active bone marrow (ABM) dose as part of the exposure assessment. However, no prior study has leveraged electronic medical records (EMR) to reconstruct ABM dose and dose-volume in an EBRT patient population.

PURPOSE: To support future studies on the relationship between radiation exposure and adverse health effects among EBRT patients, we demonstrate methods to retrospectively calculate ABM dose and dose-volume metrics in a large patient cohort using EMR.

METHODS: We retrieved complete EMR for 639 individuals (five pediatric and 634 adult) …

A Cryptographic Perspective On The Verifiability Of Quantum Advantage, Nai-Hui Chia, Honghao Fu, Fang Song, Penghui Yao

Computer Science Faculty Publications and Presentations

In recent years, achieving verifiable quantum advantage on a NISQ device has emerged as an important open problem in quantum information. The sampling-based quantum advantages are not known to have efficient verification methods. This article investigates the verification of quantum advantage from a cryptographic perspective. We establish a strong connection between the verifiability of quantum advantage and cryptographic and complexity primitives, including efficiently samplable, statistically far but computationally indistinguishable pairs of (mixed) quantum states (EFI), pseudorandom states (PRS), and variants of minimum circuit size problems (MCSP). Specifically, we prove that a) a sampling-based quantum advantage is either verifiable or can …

Math, And You! Math Tools Website For First-Grade Children With Instruction Provided Through Music Education, Tye Raymond

University Honors Theses

This thesis explores the conceptualization, exploration, and execution of a User Interface (UI) Design created as a supplemental mathematics education tool for grade one learners. Titled "Note Builder", this thesis project is a web design project, functioning as the prototype for a prospective website. Coding a website is a separate project; this project is comprised of the web design blueprint known as a prototype. The site uses a music-based digital reward system, which I constructed to motivate students as they explore new mathematics skills. All of the math questions used in this web design project are directly produced based on …

Online Tutorial On Survival Analysis For Biomarker Discovery, Jaka Kokošar, Ela Praznik, Martin Špendl, Nancy P Moreno, Alana Newell, Gad Shaulsky, Blaž Zupan

Faculty, Staff and Students Publications

In biomedicine, survival analysis addresses time-to-event data to study outcomes like patient survival and treatment response, and supports biomarker discovery. Yet, teaching this analysis is often hindered by mathematical and programming barriers. We present a structured, hands-on tutorial that goes beyond a typical online guide-offering integrated video lectures, literature, quizzes, and practical exercises. Built around Orange Data Mining, an open and free no-code visual analytics platform, the tutorial covers key concepts such as censoring, Kaplan-Meier curves, group comparisons, and biomarker discovery through real-world datasets. Organized in four pedagogical units, it progresses from basic survival data analysis to gene and gene-set …

Breaking Barriers, Transforming Digital Literacy, And Creating Immersive Learning Environments In The 21st Century, Romero D'Souza

Journal of Research Initiatives

This paper explores the future of educational technologies with a focus on breaking systemic barriers, enhancing digital literacy, and fostering immersive learning environments. Using Maharashtra, India as a case study, it examines disparities in infrastructure, internet access, and teacher readiness across government and private institutions. Local challenges are analyzed alongside initiatives like the Digital India Mission, while national policies and international best practices are reviewed for broader context. Cross-cutting themes of equity, access, and professional development highlight the need for inclusive technological integration. The pedagogical implications of emerging technologies—particularly AI and AR/VR—are assessed alongside ethical concerns around data privacy and …

Hybrid Deep Learning For Anti-Money Laundering: Unsupervised Detection Of Emerging Schemes Via Feature Fusion And Explainable Artificial Intelligence, Cosmas Ochieng Kungu, Kennedy Senagi, Evans Omondi

All Peer-Reviewed Publications

Traditional rule-based anti-money laundering (AML) transaction monitoring systems suffer from high false-positive rates and rigidity in detecting complex emerging risk. This limitation has prompted changes to the Financial Action Task Force (FATF) recommendation 16, mandating the use of advanced systems for detecting money laundering schemes in cross-border payments. This study developed a hybrid framework integrating VAE-learned behavioural latent factors, GNN-captured relational network signals, and rule-based heuristics for enhanced anomaly detection. The model was evaluated on 54,258 real-world cross-border transaction records from an East African commercial bank. The One-Class SVM, optimised via a rigorous grid search proved superior compared to Isolation …

Are Testing Accommodations Helping Or Not? A Review Of English Learner (El) Accommodations On Standardized Tests, Cole Forbes

Journal of English Learner Education

This paper examines and critiques English Learner (EL) testing accommodation policies. They have been ineffective at increasing test scores and accessibility. The policies have mandated that EL students participate in high-stakes assessments with accommodations, and sometimes without them. The purpose of the accommodation is to create an even playing field for all test-takers, so that no subgroup is put at a disadvantage, which would compromise their scores and lead to misclassification of students. Laws and Acts such as the Bilingual Education Act of 1968, No Child Left Behind, and the Every Student Succeeds Act have updated and mandated a more …

Differentiated Instruction For Multilingual Learners: A Thematic Analysis Of Research And Practice, Mohsine Bensaid, Jiayuan Jiang

Journal of English Learner Education

Differentiated instruction (DI) is widely promoted as a means of supporting diverse learners, yet its enactment for multilingual learners (MLs) remains uneven and under-theorized in mainstream classrooms. This study examines how DI is conceptualized and implemented to support MLs by attending to learners’ linguistic, cultural, and academic profiles. Using reflexive thematic analysis, this qualitative synthesis examines 20 peer-reviewed empirical studies published between 2010 and 2024 in English-medium K–12 contexts in the United States, with particular attention to elementary settings when specified. Analytic interpretation was supported by practitioner-based reflection functioning as an interpretive lens rather than a separate data source. Four …

Lessons In Pedagogy: My Experience With Problem-Based Learning, Leslie Y. Garfield Tenzer

Pace Law Review

This Article chronicles my experimental adoption of Problem-Based Learning (PBL) in first-year Contracts. After three decades of conventional teaching, I observed that Gen Z students struggled to transition from undergraduate memorization strategies to law school-level analytical reasoning, prompting my desire to engage in a fundamental pedagogical change. Drawing on successful PBL implementations in medical and mathematics education, I restructured my Contracts course around collaborative problem-solving in small groups, transforming my role from lecturer to facilitator. Students worked through authentic legal scenarios at whiteboards, developing rule-based reasoning through active engagement rather than passive reception.

This article first details my reasons for …