Results 151 to 160 of about 457 (208)

Inter‐Material Transfer Learning for Accelerated Nanofluid Heat Transfer Prediction: A Machine Learning Approach for Energy Systems

Energy Science &Engineering, EarlyView.
This study presents an inter‐material transfer learning framework for nanofluid heat transfer prediction in energy systems. By leveraging knowledge from Al2O3‐water data, the model accurately predicts hybrid Al2O3‐TiO2 nanofluid performance with only 20 simulations, achieving R2 = 0.985 and reducing computational requirements by 78. ABSTRACT This paper
Soumaya Hadj Salah, Aymen Ochi, Sonia Bezi   +2 more
wiley   +1 more source

Entropies in Electric Circuits. [PDF]

Entropy (Basel)
Cuadras A, Ovejas VJ, Martínez-García H.   +2 more
europepmc   +1 more source

Graph Neural Network‐Based Prediction of Building Energy Consumption

Energy Science &Engineering, EarlyView.
A graph neural network that encodes a multi‐zone building as a graph accurately predicts hourly cooling and heating loads across three distinct climates, outperforming Random Forest and XGBoost baselines and serving as a fast surrogate to EnergyPlus simulations for scalable building energy management.
Ali Maboudi Reveshti, Jamal Dabbagh, Jhila Nasiri Reveshti, Karim Farajeyan Bonab, Farid Hosseini Mansoub   +4 more
wiley   +1 more source

Homophily modulates double descent generalization in graph convolution networks. [PDF]

Proc Natl Acad Sci U S A
Shi C, Pan L, Hu H, Dokmanić I.
europepmc   +1 more source

Altered gene expression in the liver and small intestine of horses with equine neuroaxonal dystrophy

Equine Veterinary Journal, EarlyView.
Abstract Background Equine neuroaxonal dystrophy/degenerative myeloencephalopathy (eNAD/EDM) is the second most common diagnosis of spinal ataxia in horses in the United States. The disease develops due to a combination of vitamin E deficiency and an unknown genetic risk factor(s), and there currently is no effective treatment.
Stephanie Ryan, Blythe Durbin‐Johnson, Kevin Woolard, Andrew D. Miller, Carrie J. Finno   +4 more
wiley   +1 more source

A New Implementation of Network GARCH Model for Stock Volatility and Co‐Volatility Forecasting

Journal of Forecasting, EarlyView.
ABSTRACT Volatility clustering and spillovers are key features of financial time series with many cross‐sectional assets. While network analysis links similar or correlated stocks and helps trace volatility spillovers, contemporary multivariate ARCH‐GARCH formulations struggle to represent structured network dependence and remain parsimonious.
Peiyi Zhou
wiley   +1 more source

Interface Engineering of Boron Nitride–Polymer Composites for High Thermal Conductivity

Information &Functional Materials, EarlyView.
This review comprehensively discusses the impacts of interfacial design and fabrication strategies on boron nitride–polymer composites, and systematically classifies and summarizes recent advances in interfacial engineering based on the interaction modes between boron nitride fillers and polymer matrices.
Zhao Chen, Yuhang Meng, Chenyu Zhao, Xiangfen Jiang, Xuebin Wang   +4 more
wiley   +1 more source

Microbiome‐mediated plant‐soil feedbacks as a tool for resilient agriculture

iMetaOmics, EarlyView.
Translating plant‐soil feedbacks (PSFs) into reliable agricultural management requires shifting from input‐dependent practices toward endogenous, process‐driven crop resilience. To bridge this gap, we propose a predictive framework centered on three strategic interventions: engineering the crop holobiont, diversifying the soil habitat, and deploying ...
Muhammad Asif, Hazrat Bilal, Min Xiao, Lei Dong, Wen‐Jun Li   +4 more
wiley   +1 more source

Microbiome and aging: Trajectories of microbiome age across human ecosystems and their systemic effects

iMeta, EarlyView.
Microbiome age (MA) has emerged as an innovative biomarker of biological aging, reflecting host aging trajectories through dynamic alterations in microbial composition, function, and host–microbe interactions across multiple body ecosystems. Diverse computational strategies—including traditional machine learning, deep learning, and multi‐omics ...
Zhexin Ni, Jiaojiao Xie, Zhichun Zhang, Keming Zhang, Jie Ding, Mingyang Chang, Ying Su, Yunan Zhang, Mingfei Yao, Chengyuan Wang, Yan Yan, Wenjie Fang, Hainv Gao, Xuecong Tian, Yangshuo Li, Xinlin Zhu, Wen Zhang, Wanqing Liao, Gaoyuan Xu, Guojing Chen, Xiaoyi Lv, Chaoqin Yu, Weihua Pan, Vadim Molodtsov, Lanjuan Li, Yue Gao, Wei Zhou   +26 more
wiley   +1 more source