Results 141 to 150 of about 4,069,375 (260)

Implementing the discontinuous-Galerkin finite element method using graph neural networks with application to diffusion equations

Machine learning (ML) has benefited from both software and hardware advancements, leading to increasing interest in capitalising on ML throughout academia and industry.
Chen, Boyang, Heaney, Claire E, Li, Linfeng, Xiang, Jiansheng, Dargaville, Steven, Pain, Christopher C   +5 more
core   +1 more source

De novo spatiotemporal modelling of cell-type signatures in the developmental human heart using graph convolutional neural networks. [PDF]

PLoS Comput Biol, 2022
Marco Salas S, Yuan X, Sylven C, Nilsson M, Wählby C, Partel G.   +5 more
europepmc   +1 more source

Link Performance Prediction of Power Fiber Optic Communication System Based on Attention Mechanism and Convolutional Neural Network Fusion

Electrica
In order to enhance the multi-objective optimization capability of power communication transmission networks, the author proposes an optimization method that integrates improved graph neural networks (GNNs) and genetic algorithms (GAs).
Yong Zhang, Yan Liu, Chunying Wang, Jiaojiao Dong   +3 more
doaj   +1 more source

Data‐Guided Photocatalysis: Supervised Machine Learning in Water Splitting and CO2 Conversion

Advanced Intelligent Discovery, EarlyView.
This review highlights recent advances in supervised machine learning (ML) for photocatalysis, emphasizing methods to optimize photocatalyst properties and design materials for solar‐driven water splitting and CO2 reduction. Key applications, challenges, and future directions are discussed, offering a practical framework for integrating ML into the ...
Paul Rossener Regonia, Christian Mark Pelicano   +1 more
wiley   +1 more source

Novel Solubility Prediction Models: Molecular Fingerprints and Physicochemical Features vs Graph Convolutional Neural Networks. [PDF]

ACS Omega, 2022
Lee S, Lee M, Gyak KW, Kim SD, Kim MJ, Min K.   +5 more
europepmc   +1 more source

Advances in Thermal Modeling and Simulation of Lithium‐Ion Batteries with Machine Learning Approaches

Advanced Intelligent Discovery, EarlyView.
Heat generation in lithium‐ion batteries affects performance, aging, and safety, requiring accurate thermal modeling. Traditional methods face efficiency and adaptability challenges. This article reviews machine learning‐based and hybrid modeling approaches, integrating data and physics to improve parameter estimation and temperature prediction ...
Qi Lin, Kang Fu, Junjie Ding, Kai Sun, Peng Tan   +4 more
wiley   +1 more source

FIRE‐GNN: Force‐Informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties

Advanced Intelligent Discovery, EarlyView.
This study introduces FIRE‐GNN, a force‐informed, relaxed equivariant graph neural network for predicting surface work functions and cleavage energies from slab structures. By incorporating surface‐normal symmetry breaking and machine learning interatomic potential‐derived force information, the approach achieves state‐of‐the‐art accuracy and enables ...
Circe Hsu, Claire Schlesinger, Karan Mudaliar, Jordan Leung, Robin Walters, Peter Schindler   +5 more
wiley   +1 more source

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

, 2020
Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system.
Bai, Lei, Wang, Can, Yao, Lina, Wang, Xianzhi, Li, Can   +4 more
core  

Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks. [PDF]

J Neuroeng Rehabil, 2022
Filtjens B, Ginis P, Nieuwboer A, Slaets P, Vanrumste B.   +4 more
europepmc   +1 more source

Sampling Strategy: An Overlooked Factor Affecting Artificial Intelligence Prediction Accuracy of Peptides’ Physicochemical Properties

Advanced Intelligent Discovery, EarlyView.
This study reveals that sampling strategy (i.e., sampling size and approach) is a foundational prerequisite for building accurate and generalizable AI models in peptide discovery. Reaching a threshold of 7.5% of the total tetrapeptide sequence space was essential to ensure reliable predictions.
Meiru Yan, Ankeer Abuduhebaier, Haojin Zhou, Jiaqi Wang   +3 more
wiley   +1 more source