Results 131 to 140 of about 3,854 (234)

HeartSimSage: Attention-Enhanced Graph Neural Networks for Accelerating Cardiac Mechanics Modeling. [PDF]

J Comput Phys
Shi L, Chen Y, Vedula V.
europepmc   +1 more source

Structurally Cascaded Physics‐Informed Graph Neural Networks for Mechanotransduction‐Aware Tumor Microenvironment Modeling

Applied Research, Volume 5, Issue 5, October 2026.
This study introduces a structurally cascaded physics‐informed graph neural network to model tumor microenvironments accurately. By enforcing a directional dependency from mechanical strain to biochemical secretion, the method eliminates unphysical artifacts and significantly improves predictive accuracy for precision healthcare applications.
Xinyuan Chen, Nurashikin Saaludin, Mohd Nizam Husen   +2 more
wiley   +1 more source

Incremental refinement of relevance rankings: Balancing relevance depth and scope

Journal of the Association for Information Science and Technology, Volume 77, Issue 10, Page 1247-1270, October 2026.
Abstract Delivering both relevant and topically diverse results is a key challenge in information retrieval (IR). This study introduces a hybrid method that incrementally refines rankings by combining probabilistic topic modeling (latent dirichlet allocation [LDA]) with citation‐based pennant retrieval grounded in Relevance Theory (RT), optimizing for ...
Müge Akbulut, Yaşar Tonta
wiley   +1 more source

Generalizations of the quadratic bound optimization principle. [PDF]

Proc Natl Acad Sci U S A
Li XJ, Tian GL, Zhou H, Lange K.
europepmc   +1 more source

Subspace Acceleration for Efficient Nonlinear Water Wave Simulation

International Journal for Numerical Methods in Fluids, Volume 98, Issue 10, Page 1165-1180, October 2026.
We introduce an exponentially weighted subspace acceleration technique to reduce GMRES iterations for solving the Poisson equation with time‐dependent coefficients in nonlinear, dispersive free‐surface flows governed by the incompressible Navier‐Stokes equations. The method significantly reduces memory requirements and computational complexity compared
Rasmus Kleist Hørlyck Sørensen, Margherita Guido, Allan Peter Engsig‐Karup, Daniel Kressner   +3 more
wiley   +1 more source

When the Present Reads the Past: Critical and Social Literacy Practices as Transformative Uptake in Digital Reader Reviews

Reading Research Quarterly, Volume 61, Issue 4, October/November/December 2026.
This graphical abstract shows how Ryu Si‐min's 1985 Appeal Brief became available for civic reading in contemporary digital publics. The qualitatively led convergent mixed‐methods design combined sentence‐level rhetorical analysis of 184 source‐text sentences, directed qualitative analysis of 752 online reader reviews, and separate corpus‐level LDA ...
Goun Park
wiley   +1 more source

Joint Bayesian Nowcasting of Severe Acute Respiratory Illness and COVID-19 Positives in Brazil. [PDF]

Stat Med
Halliday A, Stoner O, Economou T, Bastos LS.   +3 more
europepmc   +1 more source

FedLucra: Federated Learning With Loss‐Utility Controlled Robust Aggregation

Expert Systems, Volume 43, Issue 10, October 2026.
ABSTRACT Federated learning enables collaborative model training without centralizing private data. However, conventional aggregation strategies generally determine client contributions primarily according to local data volume and do not directly consider differences in local model performance. To address this limitation, we propose FedLucra, a modular
Emin Akpinar, Murat Taskiran, Bulent Bolat   +2 more
wiley   +1 more source

Asynchronous proximal federated aggregation for heterogeneous healthcare networks. [PDF]

Front Digit Health
Sreelakshmi M, Delhibabu R.
europepmc   +1 more source

Cross‐Lingual Knowledge Transfer Framework for Multilingual Customer Support AI: An Expert System Perspective

Expert Systems, Volume 43, Issue 10, October 2026.
ABSTRACT This study presents a comprehensive methodology for processing multilingual customer support data to prepare it for training AI‐based conversational systems. Using a dataset of 36,599 unique customer interactions from a Finnish energy company, we employed language‐specific BERT models to identify and analyse thematic patterns within customer ...
Joona Mäntyvaara, Paavo Nevalainen, Jukka Heikkonen   +2 more
wiley   +1 more source