Results 91 to 100 of about 110,856 (309)

Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials

open access: yesAdvanced Science, EarlyView.
Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan   +8 more
wiley   +1 more source

Influence-Balanced XGBoost: Improving XGBoost for Imbalanced Data Using Influence Functions

open access: yesIEEE Access
Decision tree boosting algorithms, such as XGBoost, have demonstrated superior predictive performance on tabular data for supervised learning compared to neural networks. However, recent studies on loss functions for imbalanced data have primarily focused on deep learning.
Akiyoshi Sutou, Jinfang Wang
openaire   +2 more sources

Evaluation metrics—XGBoost, SVM, RF, and GAM.

open access: yes, 2020
Evaluation metrics—XGBoost, SVM, RF, and GAM.
Yuepeng Song (410775)   +6 more
core   +1 more source

Efficient Screening of Organic Singlet Fission Molecules Using Graph Neural Networks

open access: yesAdvanced Science, EarlyView.
A high‐throughput screening framework based on graph neural networks (GNNs) and multi‐level validation facilitates the identification of singlet fission (SF) candidates. By efficiently predicting excitation energies across 20 million molecules, and integrating TDDFT calculations, synthetic accessibility assessments, and GW+BSE calculations, this ...
Li Fu   +5 more
wiley   +1 more source

Comparative Study of Linear Regression, SVR, and XGBoost for Stock Price Prediction After a Stock Split

open access: yesJournal of Applied Informatics and Computing
This study aims to identify the most effective regression method for predicting the closing stock price of Bank Central Asia (BBCA) following the stock split event on October 12, 2021.
Muhammad Yusuf Andrika, Majid Rahardi
doaj   +1 more source

High‐Throughput Screening and Interpretable Machine Learning for Rational Design of Bimetallic Catalysts for Methane Activation

open access: yesAdvanced Science, EarlyView.
ABSTRACT Methane's efficient catalytic removal is vital for sustainable development. Bimetallic catalysts, though promising for methane activation, pose a design challenge due to their complex compositional space. This work introduces an integrated framework that combines high‐throughput density functional theory (DFT) and interpretable machine ...
Mingzhang Pan   +8 more
wiley   +1 more source

DMGutierrezz/XGB_globaldef_2023: XGBoost global deforestation analysis

open access: yes
<p>This code allows you to run a series of XGBoost models in R with random parameter settings using a 10-fold adaptive resampling procedure with Root Mean Square Error (RMSE) as the evaluation criterion.</p ...
DMGutierrezz
core   +1 more source

Physics‐Informed Machine Learning for Sustainable Alloy Design: Toward a Recyclable Unified Q&P Steel

open access: yesAdvanced Science, EarlyView.
A physics‐informed property‐bridging framework links high‐throughput hardness screening to tensile performance in quenching and partitioning steels. By transferring metallurgically guided representations across properties, a single alloy composition is designed to achieve multiple strength grades through heat‐treatment tuning alone, offering a ...
Xiaolu Wei   +7 more
wiley   +1 more source

Prediction of Dye Removal Using Machine Learning Techniques

open access: yesSakarya University Journal of Computer and Information Sciences
This study aims to predict the removal efficiency of methylene blue dye using experimental data collected from adsorption processes involving acorn-based biosorbents.
Dilay Bozdağ Ak, İhsan Hakan Selvi
doaj   +1 more source

DMGutierrezz/XGB_globaldef_2023: XGBoost global deforestation analysis code

open access: yes
<p>This code allows you to run a series of XGBoost models with random parameter settings using a 10-fold adaptive resampling procedure with Root Mean Square Error (RMSE) as the evaluation criterion.</p ...
DMGutierrezz
core   +1 more source

Home - About - Disclaimer - Privacy