Results 181 to 190 of about 42,243 (288)

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

open access: yesAdvanced 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   +5 more
wiley   +1 more source

Proximity Engineering of Fe‒N4 Twins for Oriented Generation of Singlet Oxygen for Hospital Wastewater Treatment

open access: yesAngewandte Chemie, EarlyView.
Precise modulation of Fe–N4 site distances constructs spin‐regulated Fe–N4 twins, triggering a volcano‐type Fenton‐like activity and promoting oriented singlet oxygen generation. The twin‐site catalyst enables highly selective and efficient hospital wastewater purification with simultaneous pharmaceutical degradation and disinfection under low ...
Xinhao Wang   +10 more
wiley   +2 more sources

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

open access: yesAdvanced 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   +3 more
wiley   +1 more source

SuperResNET: Model‐Free Single‐Molecule Network Analysis Software Achieves Molecular Resolution of Nup96

open access: yesAdvanced Intelligent Systems, Volume 7, Issue 3, March 2025.
SuperResNET is a powerful integrated software that reconstructs network architecture and molecular distribution of subcellular structures from single molecule localization microscopy datasets. SuperResNET segments the nuclear pore complex and corners, extracts size, shape, and network features of all segmented nuclear pores and uses modularity analysis
Yahongyang Lydia Li   +6 more
wiley   +1 more source

Adaptive rateless coded blockchain for dynamic IoV scenarios. [PDF]

open access: yesSci Rep
Zhang S   +4 more
europepmc   +1 more source

From Droplet to Diagnosis: Spatio‐Temporal Pattern Recognition in Drying Biofluids

open access: yesAdvanced Intelligent Systems, EarlyView.
This article integrates machine learning (ML) with the spatio‐temporal evolution of biofluid droplets to reveal how drying and self‐assembly encode distinctive compositional fingerprints. By leveraging textural features and interpretable ML, it achieves robust classification of blood abnormalities with over 95% accuracy.
Anusuya Pal   +2 more
wiley   +1 more source

Optimal Complexity of Parameterized Quantum Circuits. [PDF]

open access: yesEntropy (Basel)
Correr GI   +3 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy