Results 171 to 180 of about 72,345 (262)

Performance and safety of a fine-tuned small language model for pediatric emergency triage: A benchmark study. [PDF]

PLoS One
Lee EJ, Jung JY, Kim DK, Park JW, Kwak YH.   +4 more
europepmc   +1 more source

Probabilistic prediction of rate‐dependent rock strength using natural gradient boosting and Gaussian process regression

Deep Underground Science and Engineering, EarlyView.
Probabilistic natural gradient boosting and Gaussian process regression models accurately predict rate‐dependent rock strength across lithologies. Static strength and strain rate dominate, while geometric factors have minimal influence, enabling interpretable and uncertainty‐aware predictions for dynamic geomechanical applications. Abstract The dynamic
Hadi Fathipour‐Azar
wiley   +1 more source

XGBoost prediction of adverse neurodevelopmental outcomes in hypoxic-ischemic encephalopathy neonates. [PDF]

Medicine (Baltimore)
Kim TY, Park HM, Youn YA.
europepmc   +1 more source

Explainable hybrid stacking ensemble method for hard rock pillar stability prediction and engineering applications

Deep Underground Science and Engineering, EarlyView.
This research proposes an interpretable hybrid stacking ensemble framework, optimized by the Sparrow Search Algorithm, to enhance hard rock pillar stability prediction. By integrating six machine learning models—k‐nearest neighbors, support vector machines, random forests, Gradient Boosting Decision Tree, eXtreme Gradient Boosting, and Light Gradient ...
Ning Wang, Guoyan Zhao, Meng Wang, Taraka Pattela   +3 more
wiley   +1 more source

An explainable AI framework for enhanced software defect prediction using transformer-assisted boosting. [PDF]

Sci Rep
Kun Q, Shaikh ZA, Yang J, Kumar G, Mohammed HA, Yee PL.   +5 more
europepmc   +1 more source

A Review of Grain Boundaries: Formation Mechanism, Synthesis Strategy, and Application in Electrocatalysis

EcoEnergy, EarlyView.
An overview of grain boundary engineering in the field of electrocatalysis. ABSTRACT Key electrocatalytic reactions such as HER, OER, ORR, CO2RR, and NRR offer promising routes for storing renewable energy as chemical fuels. However, their widespread application is constrained due to the lack of highly active and stable catalysts. Grain boundaries (GBs)
Jingyu Gao, Fengming Zhou, Xinying Li, Ying Deng, Zexing Wu, Siyuan Feng, Yujing Zhu, Dan Zhang, Zhenyu Xiao   +8 more
wiley   +1 more source

Graph informed biomarker discovery framework using transcriptomic machine learning for glioblastoma prognosis. [PDF]

Sci Rep
Mahmoud O, Mounir M, Gad W.
europepmc   +1 more source

‘biomod2' – extending presence–absence species distribution models to multiple data types

Ecography, EarlyView.
The R package ‘biomod2' is one of the most widely used and versatile tools for species distribution modelling (SDM), enabling ecologists to calibrate, evaluate, and project species–environment relationships across space and time using multiple modelling algorithms and ensemble forecasting.
Maya Guéguen, Hélène Blancheteau, Rémi Lemaire‐Patin, Wilfried Thuiller   +3 more
wiley   +1 more source

Machine Learning and SHAP Value Interpretation for Predicting Hepatic Steatosis Using Vibration-Controlled Transient Elastography. [PDF]

Int J Endocrinol
Lu Z, He C, Wang M, He W, Wang S, Xie Y, Pan X.   +6 more
europepmc   +1 more source

Toward a Paradigm Shift in Low‐Temperature SCR Catalyst Design: Defect Engineering and Data‐Driven Integration

ENERGY &ENVIRONMENTAL MATERIALS, EarlyView.
This work systematically reviews the key factors influencing the performance of low‐temperature NH3‐SCR. The mechanism and challenges of defect engineering strategies, such as oxygen vacancies, heteroatom doping, crystal facet exposure, and surface reconstruction, in controlling both activity and selectivity were analyzed.
Rongrong Kan, Pinjing He, Fan Lü, Hua Zhang   +3 more
wiley   +1 more source