Results 211 to 220 of about 474,975 (277)

Topology‐Aware Machine Learning for High‐Throughput Screening of MOFs in C8 Aromatic Separation

Advanced Intelligent Discovery, EarlyView.
We screened 15,335 Computation‐Ready, Experimental Metal–Organic Frameworks (CoRE‐MOFs) using a topology‐aware machine learning (ML) model that integrates structural, chemical, pore‐size, and topological descriptors. Top‐performing MOFs exhibit aromatic‐enriched cavities and open metal sites that enable π–π and C–H···π interactions, serving as ...
Yu Li, Honglin Li, Jialu Li, Wan‐Lu Li
wiley   +1 more source

Enhanced composed fashion image retrieval with a multi-hop reasoning framework. [PDF]

Sci Rep
Yang N, Ma X.
europepmc   +1 more source

Advanced Experiment Design Strategies for Drug Development

Advanced Intelligent Discovery, EarlyView.
Wang et al. analyze 592 drug development studies published between 2020 and 2024 that applied design of experiments methodologies. The review surveys both classical and emerging approaches—including Bayesian optimization and active learning—and identifies a critical gap between advanced experimental strategies and their practical adoption in ...
Fanjin Wang, Anthony Harker, Mohan Edirisinghe, Maryam Parhizkar   +3 more
wiley   +1 more source

Knowledge-guided adaptation of pathology foundation models effectively improves cross-domain generalization and demographic fairness. [PDF]

Nat Commun
Huang Y, Zhao W, Zhang Z, Chen Y, Fu Y, Wu F, Jiang Y, Liang L, Wang S, Yu L.   +9 more
europepmc   +1 more source

A Physics Constrained Machine Learning Pipeline for Young's Modulus Prediction in Multimaterial Hyperelastic Cylinders Guided by Contact Mechanics

Advanced Intelligent Discovery, EarlyView.
A physics‐guided machine learning framework estimates Young's modulus in multilayered multimaterial hyperelastic cylinders using contact mechanics. A semiempirical stiffness law is embedded into a custom neural network, ensuring physically consistent predictions. Validation against experimental and numerical data on C.
Christoforos Rekatsinas, Panagiotis Krokidas, Vasileios Vavourakis, Clara Essmann, George Giannakopoulos   +4 more
wiley   +1 more source

A multi-modal prompt-tuning method of ultrasound diagnosis for thyroid nodule. [PDF]

Front Med (Lausanne)
Xiao X, Zhou Y, Zhu Y, Li Y, Qi T, Wang W.   +5 more
europepmc   +1 more source

A Generalized Framework for Data‐Efficient and Extrapolative Materials Discovery for Gas Separation

Advanced Intelligent Discovery, EarlyView.
This study introduces an iterative supervised machine learning framework for metal‐organic framework (MOF) discovery. The approach identifies over 97% of the best performing candidates while using less than 10% of available data. It generalizes across diverse MOF databases and gas separation scenarios.
Varad Daoo, Jayant K. Singh
wiley   +1 more source

Deep learning-driven image captioning: Progress through transformers and large language models. [PDF]

PLoS One
Panchal P, Polara V, U S, Baz A, Patel SK.   +4 more
europepmc   +1 more source

Multimodal prototypical network for interpretable sentiment classification. [PDF]

Sci Rep
Song C, Chao K, Jia B, Shen Y.
europepmc   +1 more source

Knowledge graph enhanced cross modal generative adversarial network for martial arts motion reconstruction and heritage preservation. [PDF]

Sci Rep
Yue X, Zhang L.
europepmc   +1 more source