Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 104581 - 104610 of 5209454

Full-Text Articles in Entire DC Network

A Hierarchical, Data-Driven Analytical Paradigm For Strategic Planning, Operational Decision-Making, And Resilience Enhancement In United States Electric Power Systems Under Extreme Demand Conditions, Anyama Hanson Tettey Jan 2026

A Hierarchical, Data-Driven Analytical Paradigm For Strategic Planning, Operational Decision-Making, And Resilience Enhancement In United States Electric Power Systems Under Extreme Demand Conditions, Anyama Hanson Tettey

Dissertations

Historical evidence indicates that the United States electric power grid continues to face persistent criticism for reliability challenges during peak demand conditions. Extreme ambient temperatures are a primary driver of such peaks, rendering the grid most vulnerable precisely when electricity demand is highest. These demand surges are largely driven by coincident operation of heating, ventilation, and air-conditioning systems across customer classes, a trend expected to intensify as sectors such as transportation increasingly rely on electrification. Efforts to mitigate demand related unreliability have traditionally focused on system-level demand forecasting and planning, typically at the scale of cities or entire utilities. However, …

Go to article

Threatened To Testify : Juror Perceptions Of Coercive Eyewitness Interviews, Alexa A. Mecikalski Jan 2026

Threatened To Testify : Juror Perceptions Of Coercive Eyewitness Interviews, Alexa A. Mecikalski

Dissertations

The effects of coercive investigative questioning techniques have been extensively studied in the context of suspect interrogations; however, few studies have evaluated outcomes related to coercive questioning of eyewitnesses. Therefore, the present study investigated mock juror perceptions of the use of interrogation tactics during eyewitness questioning. Participants read a trial summary and provided trial judgments (e.g., verdict, eyewitness credibility, perceived coerciveness of the interview) pertaining to a case in which an eyewitness is questioned using either (1) maximization tactics (e.g. high pressure questioning, threats), (2) minimization tactics (e.g., minimizing severity or consequences), or (3) no tactics (e.g., statement provided voluntarily). …

Go to article

Comprehending Levels Of Explainability And Ai Recommendations (Clear) Study Series, Virginia Sullivan Jan 2026

Comprehending Levels Of Explainability And Ai Recommendations (Clear) Study Series, Virginia Sullivan

Dissertations

AI systems can offer a great deal to improve decision-making through efficiency and predictive accuracy due to their unique ability to rapidly analyze large amounts of data relevant to the decision. Yet many AI systems remain opaque, limiting users’ ability to evaluate outputs and leading to issues of mistrust or over-reliance. This dissertation investigates how varying levels of AI explainability affect trust, perceived reliability, understanding, and confidence, and identifies perceptual and behavioral indicators of over-reliance behavior in AI-assisted decision making scenarios. This dissertation is organized as a three-study series. The CLEAR survey study uses a mixed design to examine the …

Go to article

Role Of Mkp-2 In Pancreatic Beta Cell Function & Development Of Diabetes, Nabin Ghimire Jan 2026

Role Of Mkp-2 In Pancreatic Beta Cell Function & Development Of Diabetes, Nabin Ghimire

Dissertations

Diabetes mellitus is a chronic metabolic disease characterized by persistent hyperglycemia. Type 1 diabetes results from autoimmune destruction of β-cells, whereas Type 2 diabetes is associated with obesity and insulin resistance. Type 2 diabetes (T2D) and metabolic-associated fatty liver disease (MAFLD) are closely linked, as individuals with T2D are twice as likely to develop MAFLD. Previous work from our lab demonstrated that overexpression of MKP-2 in obesity promotes hepatic steatosis, diet-induced obesity, reduced insulin sensitivity, and increased body weight. However, the role of MKP-2 in the onset and progression of diabetes remains unclear. The objectives of this study were to …

Go to article

Mechanisms Of Interface Formation In Bi-Metallic Components Fabricated Using Additive Manufacturing Processes, Michael P. Santangelo Jan 2026

Mechanisms Of Interface Formation In Bi-Metallic Components Fabricated Using Additive Manufacturing Processes, Michael P. Santangelo

Dissertations

As the expansion of metal additive manufacturing (MAM) brings forward new techniques and processes, compatibility between combinations of materials in multi-material components needs to be considered. Currently, the process by which compatibility between various metal alloys are evaluated is through laborious characterization of representative samples, which are products of both the additive manufacturing (AM) process used as well as the material chemistry. If a methodology for understanding the driving mechanisms behind formation of a compatible metallic interface can be created with the use of a predictive model, then wider implementation of multi-material MAM can be achieved. The objective of this …

Go to article

Thermodynamic Properties Of Cluster Outskirts, Leo Moraczewski Jan 2026

Thermodynamic Properties Of Cluster Outskirts, Leo Moraczewski

Dissertations

We present the temperature, density, entropy, and pressure profiles of the intracluster mediums of eight galaxy clusters observed out to the virial radius with complete azimuthal coverage by the Suzaku X-ray space telescope. Suzaku’s low background was vital to probing the lower x-ray surface brightness of cluster outskirts that could not be studied by X-ray telescopes such as Chandra and XMM-Newton which have a higher background level. The eight clusters being examined are the last observed out to the virial radius by Suzaku that have not had their properties published. As all eight clusters have complete azimuthal coverage, we also …

Go to article

Rocket Injector Flowfield Characterization Through Local, Instantaneous Gas Composition Tracing Using Laser Induced Breakdown Spectroscopy, Michaela Renee Hemming Jan 2026

Rocket Injector Flowfield Characterization Through Local, Instantaneous Gas Composition Tracing Using Laser Induced Breakdown Spectroscopy, Michaela Renee Hemming

Dissertations

Laser induced breakdown spectroscopy (LIBS) was developed for applications in the characterization of rocket engine injectors to evaluate the instantaneous, local gas concentration, or local mixture ratio of the injector flowfield. In this work, LIBS was tested in steady flows of premixed methane and air to create the correlation of the LIBS spectral species ratios H/O ratio, followed by a steady non-premixed flow to extract the localized mixing and shape of the flow field, then a transient study was performed to measure the development of the flow of the reactants in a pentad impingement injector previously used in RDE tests. …

Go to article

Thermal Analysis Of The Fiber Fuse Effect, John Seekins Jan 2026

Thermal Analysis Of The Fiber Fuse Effect, John Seekins

Dissertations

The fiber fuse effect is a self-sustaining damage propagation mechanism that can occur in the core of optical fibers. Under sufficient levels of applied power, laser light is absorbed as heat in the fiber. This phenomenon is characterized by a brightly glowing spot in the fiber that propagates towards the source of laser light at about 1 𝑚/𝑠. A numerical simulation of the fiber fuse effect is developed that solves the transient heat equation with source terms in cylindrical coordinates utilizing an explicit finite difference discretization. For the first time in a simulation of this type, a radiation transport equation …

Go to article

Diffusion Behavior Of Uranium Fission Products In A Centrifugal Nuclear Thermal Rocket, Mitchell Schroll Jan 2026

Diffusion Behavior Of Uranium Fission Products In A Centrifugal Nuclear Thermal Rocket, Mitchell Schroll

Dissertations

Centrifugal nuclear thermal rockets (CNTR) are an advanced concept engine first proposed in the 1950’s that would allow for specific impulses of up to 1800 seconds. A major difference in this engine is that the liquid fuel allows for fission products to move through the fuel layer and even exit out of the reactor completely. This dissertation seeks to answer the question, how does the migration of fission products within a centrifugal nuclear thermal rocket affect its operation and performance?” To accomplish this a reduced order model was developed to simulate and track the fission products generated during the firing …

Go to article

An Incremental Approach For Recovering Decompiled Variable Data Types Using Graph Neural Networks With Learned Confidence Estimates, Caleb Stewart Jan 2026

An Incremental Approach For Recovering Decompiled Variable Data Types Using Graph Neural Networks With Learned Confidence Estimates, Caleb Stewart

Dissertations

When software is compiled into machine code, the high-level data types defined in the original source code are lost. Binary type inference is the process of attempting to recover these high-level data types from compiled binary code. This dissertation investigates binary type inference using graph neural networks (GNNs) to predict data types for decompiled variables. The study is organized into three phases. Phase one presents DRAGON, a GNN model that predicts simple data types for decompiled variables using input graphs derived from decompiled abstract syntax trees (ASTs). DRAGON also produces confidence estimates indicating the degree of faith the model places …

Go to article

The Parallel And Perpendicular Diffusion Of Energetic Particles In The Inner Heliosphere Using Nonlinear Theories And Observations, Nibuna Siranjeevi Madam Subashchandar Jan 2026

The Parallel And Perpendicular Diffusion Of Energetic Particles In The Inner Heliosphere Using Nonlinear Theories And Observations, Nibuna Siranjeevi Madam Subashchandar

Dissertations

Energetic-particle transport in the near-Sun solar wind is strongly controlled by magnetic turbulence and its geometry. Using Parker Solar Probe observations from encounters E1--E19, we investigate parallel, perpendicular, and momentum diffusion coefficients for energetic protons in the inner heliosphere. The observed turbulence spectra are decomposed into slab and two-dimensional components using a composite turbulence model. The parallel diffusion coefficient is calculated using second-order quasi-linear theory, while the perpendicular diffusion coefficient is obtained from unified nonlinear transport theory. The results show that parallel diffusion increases with heliocentric distance but decreases with increasing turbulence amplitude, indicating enhanced pitch-angle scattering in stronger turbulence. …

Go to article

Diffusion Of Excitons In Thin Films Of Quantum Dots, Dustin Roberts Jan 2026

Diffusion Of Excitons In Thin Films Of Quantum Dots, Dustin Roberts

Dissertations

Quantum dots are heavily used in modern devices, such as consumer television screens, lasers, medical sensors, solar cells, and quantum computing. Their tunability and photo-stability make them candidates for a variety of applications which formerly required either dyes or significant amounts of band structure engineering. Despite all of the current and active applications, there is a gap in the current literature with regards to how energy is transported through thin films of quantum dots, and what methods may be used to control transport direction and range. The goal of this dissertation is to help fill those gaps, towards the end …

Go to article

Going On Vocation, Rodney Palmer Jan 2026

Going On Vocation, Rodney Palmer

Faculty Publications

No abstract provided.

Go to article

The Measure Of Librarianship: How Accessibility, Compassionate Service, And Practical Action Reveal The Heart Of Adventist Librarianship, Zorislav Plantak Jan 2026

The Measure Of Librarianship: How Accessibility, Compassionate Service, And Practical Action Reveal The Heart Of Adventist Librarianship, Zorislav Plantak

Faculty Publications

No abstract provided.

Go to article

Low Frequency Oscillation Observed In The Ionosphere Around The Substorm Onsets, Simon Wing, Elmer Rivera, A. J. Hull, P. A. Damiano Jan 2026

Low Frequency Oscillation Observed In The Ionosphere Around The Substorm Onsets, Simon Wing, Elmer Rivera, A. J. Hull, P. A. Damiano

Faculty Publications

No abstract provided.

Go to article

The Construction Of A Theological System, The Sanctuary, And Adventist Theology, Adriani Rodrigues Jan 2026

The Construction Of A Theological System, The Sanctuary, And Adventist Theology, Adriani Rodrigues

Faculty Publications

No abstract provided.

Go to article

Identifying Phrase Boundaries In The Samaritan Pentateuch With Machine Learning, Oliver Glanz Jan 2026

Identifying Phrase Boundaries In The Samaritan Pentateuch With Machine Learning, Oliver Glanz

Faculty Publications

No abstract provided.

Go to article

Lost In Instructions: Study Of Blind Users' Experiences With Diy Manuals And Ai-Rewritten Instructions For Assembly, Operation, And Troubleshooting Of Tangible Products, Monalika Padma Reddy, Aruna Balasubramanian, Jiawei Zhou, Xiaojun Bi, Iv Ramakrishnan, Vikas Ashok Jan 2026

Lost In Instructions: Study Of Blind Users' Experiences With Diy Manuals And Ai-Rewritten Instructions For Assembly, Operation, And Troubleshooting Of Tangible Products, Monalika Padma Reddy, Aruna Balasubramanian, Jiawei Zhou, Xiaojun Bi, Iv Ramakrishnan, Vikas Ashok

Computer Science Faculty Publications

AI tools like ChatGPT and Be-My-AI are increasingly being used by blind individuals. Although prior work has explored their use in some Do-It-Yourself (DIY) tasks by blind individuals, little is known about how they use these tools and the available product-manual resources to assemble, operate, and troubleshoot physical/tangible products – tasks requiring spatial reasoning, structural understanding, and precise execution. We address this knowledge gap via an interview study and a usability study with blind participants, investigating how they leverage AI tools and product manuals for DIY tasks with physical products. Findings show that manuals are essential resources, but product-manual instructions …

Go to article

Explainable Convolutional Neural Network Model Provides An Alternative Genome-Wide Association Perspective On Mutations In Sars-Cov-2, Parisa C. Hatami, Richard Annan, Luis Miranda, Jane L. Gorman, Mengjun Xie, Letu Qingge, Hong Qin Jan 2026

Explainable Convolutional Neural Network Model Provides An Alternative Genome-Wide Association Perspective On Mutations In Sars-Cov-2, Parisa C. Hatami, Richard Annan, Luis Miranda, Jane L. Gorman, Mengjun Xie, Letu Qingge, Hong Qin

Computer Science Faculty Publications

Identifying informative genomic features in SARS-CoV-2 can help clarify patterns of viral evolution. In this study, we developed an explainable convolutional neural network (CNN) model to classify SARS-CoV-2 genomic sequences into the WHO-designated Variants of Concern (VOCs), Alpha, Beta, Gamma, Delta, and Omicron. Using a balanced dataset of genomes, the classification CNN achieved 99.96% accuracy on the held-out test set. To interpret the model’s predictions, we applied SHapley Additive exPlanations (SHAP) to estimate the contribution of each nucleotide position to VOC-label prediction and compared aggregated attributions with a chi-square GWAS baseline applied to the same categorical labels. SHAP prioritized several …

Go to article

Variational Autoencoder Inverse Mapper For Extraction Of Compton Form Factors: Benchmarks And Conditional Learning, Douglas Adams, Md Fayaz Bin Hossen, Joshua Bautista, Gia-Wei Chern, Simonetta Liuti, Marie Boër, Marija Čuić, Michael Engelhardt, Gary R. Goldstein, Huey-Wen Lin, Yaohang Li Jan 2026

Variational Autoencoder Inverse Mapper For Extraction Of Compton Form Factors: Benchmarks And Conditional Learning, Douglas Adams, Md Fayaz Bin Hossen, Joshua Bautista, Gia-Wei Chern, Simonetta Liuti, Marie Boër, Marija Čuić, Michael Engelhardt, Gary R. Goldstein, Huey-Wen Lin, Yaohang Li

Computer Science Faculty Publications

Deeply virtual exclusive scattering processes (DVES) serve as precise probes of nucleon quark and gluon distributions in coordinate space. These distributions are derived from generalized parton distributions (GPDs) via Fourier transform relative to proton momentum transfer. QCD factorization theorems enable DVES to be parameterized by Compton form factors (CFFs), which are convolutions of GPDs with perturbatively calculable kernels. Accurate extraction of CFFs from DVCS, benefiting from interference with the Bethe–Heitler (BH) process and a simpler final state structure, is essential for inferring GPDs. This paper focuses on extracting CFFs from DVCS data using a variational autoencoder inverse mapper (VAIM) and …

Go to article

Open Scholarly Information Systems: Status Quo, Challenges, Opportunities, Hannah Bast, Guillaume Cabanac, Paolo Manghi, Jian Wu, Marcel R. Ackermann Jan 2026

Open Scholarly Information Systems: Status Quo, Challenges, Opportunities, Hannah Bast, Guillaume Cabanac, Paolo Manghi, Jian Wu, Marcel R. Ackermann

Computer Science Faculty Publications

Over the past 30 years, a rich ecosystem of scholarly information systems has developed that openly provide their services to the scientific community. These systems include aggregators of bibliographic metadata (e.g., DBLP, OpenCitations, OpenAIRE Graph, OpenAlex, ORKG, Semantic Scholar, CiteSeerX, and CORE); publication, data, and software repositories (e.g., Arxiv.org, Figshare, Zenodo, Software Heritage, and Dataverse); and PID authorities (e.g., ORCID, ROR, Crossref, and DataCite). This interdisciplinary Dagstuhl Seminar "Open Scholarly Information Systems: Status Quo, Challenges, Opportunities" (25381) was the first of its kind to bring together practitioners from this ecosystem, as well as researchers investigating related questions or relying on …

Go to article

A Comparative Analysis Of Explainable Ai (Xai) Techniques For Transparent And Reliable Image Classification, Sovon Chakraborty, Shakib Mahmud Dipto, Kevin R. Pilkiewicz, Michael L. Mayo, Pratip Rana Jan 2026

A Comparative Analysis Of Explainable Ai (Xai) Techniques For Transparent And Reliable Image Classification, Sovon Chakraborty, Shakib Mahmud Dipto, Kevin R. Pilkiewicz, Michael L. Mayo, Pratip Rana

Computer Science Faculty Publications

Evaluating the trustworthiness of black-box machine learning models remains a significant methodological challenge. Their lack of transparency and interpretability limits applicability, because stakeholders often seek transparency before trusting the results of black-box machine learning models. Explainable AI (XAI) methods provide for human-understandable justifications and informed decision-making of these black-box architectures. Therefore, it is imperative to select the proper XAI model tailored to specific tasks. In this research, we focus on examining four XAI techniques: PEEK, LRP, GRAD-CAM, and LIME to understand how they perform against each other for image classification tasks. We evaluate the performance, robustness, generalizability, noise stability, and …

Go to article

Memebuddy: Dialog-Style Audio Representations For Engaging Non-Visual Meme Experiences, Chirag Bhansali, Vikas Ashok, Hae-Na Lee Jan 2026

Memebuddy: Dialog-Style Audio Representations For Engaging Non-Visual Meme Experiences, Chirag Bhansali, Vikas Ashok, Hae-Na Lee

Computer Science Faculty Publications

Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a …

Go to article

Privacy-Preserving Federated Learning With Optimized Ensemble Weighting And Knowledge Distillation For Covid-19 Detection From Non-Iid Medical Imaging Data, Richard Annan, Hong Qin, Robert Newman, Madhuri Siddula, Letu Qingge Jan 2026

Privacy-Preserving Federated Learning With Optimized Ensemble Weighting And Knowledge Distillation For Covid-19 Detection From Non-Iid Medical Imaging Data, Richard Annan, Hong Qin, Robert Newman, Madhuri Siddula, Letu Qingge

Computer Science Faculty Publications

Medical imaging enables rapid and accurate diagnosis of COVID-19, with CT scans proving especially effective. However, data privacy concerns limit collaborative model development across hospitals. To address this issue, we introduce a novel federated learning framework. It is referred to as Independent Knowledge Distillation with post-Ensemble Federated Learning (IKDEFL). Differential Privacy (DP) is integrated into the framework to improve privacy guarantees. Three DP mechanisms are evaluated. These include Fixed Gaussian, Gaussian Adaptive, and Tree Adaptive. The evaluation has been conducted on heterogeneous and Non-Independent and Identically Distributed (Non-IID) datasets. These datasets reflect real-world hospital scenarios. Results show that IKDEFL significantly …

Go to article

Toward An Event-Level Analysis Of Hadron Structure Using Differential Programming, Kevin Braga, Markus Diefenthaler, Steven Goldenberg, Daniel Lersch, Yaohang Li, Jian-Wei Qiu, Kishansingh Rajput, Felix Ringer, Nobuo Sato, Malachi Schram Jan 2026

Toward An Event-Level Analysis Of Hadron Structure Using Differential Programming, Kevin Braga, Markus Diefenthaler, Steven Goldenberg, Daniel Lersch, Yaohang Li, Jian-Wei Qiu, Kishansingh Rajput, Felix Ringer, Nobuo Sato, Malachi Schram

Computer Science Faculty Publications

Reconstructing the internal properties of hadrons in terms of fundamental quark and gluon degrees of freedom is a central goal in nuclear and particle physics. This effort lies at the core of major experimental programs, such as the Jefferson Lab 12 GeV program and the upcoming Electron-Ion Collider. A primary challenge is the inherent inverse problem: converting large-scale observational data from collision events into the fundamental quantum correlation functions (QCFs) that characterize the microscopic structure of hadronic systems within the theory of QCD. Recent advances in scientific computing and machine learning have opened new avenues for addressing this challenge using …

Go to article

Isotropic Shrinkage Of Patterned Vacancies Enables Three-Dimensional Nanoprecise Metastructures For Visible Light Applications, Quansan Yang, Gaojie Yang, Takahiro Nambara, Hiroyuki Kusaka, Yuichiro Kunai, Alex C. Matlock, Corban Swain, Brett Pryor, Yannick Salamin, Daniel Oran, Hasindu Kariyawasam, Ramith Hettiarachchi, Dushan Wadduwage, Marin Soljačić, Peter T. C. Soflaei, Edward S. Boyden Jan 2026

Isotropic Shrinkage Of Patterned Vacancies Enables Three-Dimensional Nanoprecise Metastructures For Visible Light Applications, Quansan Yang, Gaojie Yang, Takahiro Nambara, Hiroyuki Kusaka, Yuichiro Kunai, Alex C. Matlock, Corban Swain, Brett Pryor, Yannick Salamin, Daniel Oran, Hasindu Kariyawasam, Ramith Hettiarachchi, Dushan Wadduwage, Marin Soljačić, Peter T. C. Soflaei, Edward S. Boyden

Computer Science Faculty Publications

Three-dimensional metastructures with nanoscale feature sizes exhibit unique properties compared with structures with larger feature sizes, but are difficult to fabricate. Here we introduce implosion carving (ImpCarv), a method for photopatterning vacancies of complex geometry throughout materials, followed by isotropic shrinkage (>10-fold). ImpCarv works by photoactivating sensitizers to generate reactive oxygen species that cleave a swollen hydrogel at defined points, followed by controlled shrinkage via dehydration. ImpCarv creates three-dimensional metastructures where the refractive index of each point throughout a material can be specified with nanoscale precision via material presence or absence. By leveraging refractive index programmability for precise phase …

Go to article

Attf-Gnn: An Attention-Based Multi-Omics Graph Neural Network With Modality Learning For Disease Subtyping, Sovon Chakraborty, Eleni Adam, Terry Stilwell, Harold Riethman, Desh Ranjan, Pratip Rana Jan 2026

Attf-Gnn: An Attention-Based Multi-Omics Graph Neural Network With Modality Learning For Disease Subtyping, Sovon Chakraborty, Eleni Adam, Terry Stilwell, Harold Riethman, Desh Ranjan, Pratip Rana

Computer Science Faculty Publications

We propose AttF-GNN, an attention-based graph fusion strategy for diseases classification and subtyping. In multiomics analysis, not all types of molecular data are equally relevant for disease subtyping and considering all modalities equally may obscure discriminative signals and limit the effectiveness of predictive models by overlooking modality-specific contributions. Therefore, we design an attention-based multimodal GraphSAGE framework that can automatically emphasize the modalities providing the most relevant information for classification. At first, we have constructed three graphs using mRNA, RNA-seq and DNA methylation modalities, and train each omics with individual GraphSAGE encoders. Next, a unified intersection graph is formed using an …

Go to article

An Investigation Of Federated Gnns Under Aggregation, Data Poisoning, And Differential Privacy For Icu Length-Of-Stay Prediction, Shakib Mahmud Dipto, Soumya Banerjee, Sandip Roy, Ahmad F. Al Musawi, Preetam Ghosh, Sachin Shetty, Pratip Rana Jan 2026

An Investigation Of Federated Gnns Under Aggregation, Data Poisoning, And Differential Privacy For Icu Length-Of-Stay Prediction, Shakib Mahmud Dipto, Soumya Banerjee, Sandip Roy, Ahmad F. Al Musawi, Preetam Ghosh, Sachin Shetty, Pratip Rana

Computer Science Faculty Publications

Accurate prediction of ICU Length of Stay (LoS) is essential for clinical decision-making and healthcare resource management. Graph Neural Networks (GNNs), such as GraphSAGE, offer a natural fit by capturing patient data from Electronic Health Records (EHRs) through graph structures. However, the distributed and sensitive nature of this data raises both privacy and legal concerns regarding the aggregation and training of GNN models. This additionally leads to issues with data imbalance and model robustness. In this study, we perform an analysis of the Federated Graph Neural Network (GNN-FL) framework to enable decentralized learning on EHRs derived from the MIMIC-III dataset. …

Go to article

Deep Incomplete Multi-View Clustering Via Hierarchical Imputation And Alignment, Yiming Du, Ziyu Wang, Jian Li, Rui Ning, Lusi Li Jan 2026

Deep Incomplete Multi-View Clustering Via Hierarchical Imputation And Alignment, Yiming Du, Ziyu Wang, Jian Li, Rui Ning, Lusi Li

Computer Science Faculty Publications

Incomplete multi-view clustering (IMVC) aims to discover shared cluster structures from multi-view data with partial observations. The core challenges lie in accurately imputing missing views without introducing bias, while maintaining semantic consistency across views and compactness within clusters. To address these challenges, we propose DIMVC-HIA, a novel deep IMVC framework that integrates hierarchical imputation and alignment with four key components: (1) view-specific autoencoders for latent feature extraction, coupled with a view-shared clustering predictor to produce soft cluster assignments; (2) a hierarchical imputation module that first estimates missing cluster assignments based on cross-view contrastive similarity, and then reconstructs missing features using …

Go to article

Distributed Semi-Speculative Parallel Anisotropic Mesh Adaptation, Kevin Garner, Polykarpos Thomadakis, Nikos Chrisochoides Jan 2026

Distributed Semi-Speculative Parallel Anisotropic Mesh Adaptation, Kevin Garner, Polykarpos Thomadakis, Nikos Chrisochoides

Computer Science Faculty Publications

This paper presents a distributed memory method for anisotropic mesh adaptation that is designed to avoid the use of collective communication and global synchronization techniques. In the presented method, meshing functionality is separated from performance aspects by utilizing a separate entity for each - a multicore cc-NUMA-based (shared memory) mesh generation software and a parallel runtime system that is designed to help applications leverage the concurrency offered by emerging high-performance computing (HPC) architectures. First, an initial mesh is decomposed and its interface elements (subdomain boundaries) are adapted on a single multicore node (shared memory). Subdomains are then distributed among the …

Go to article

First Prev Next Last