Predicting early‐age stress evolution in restrained concrete by thermo‐chemo‐mechanical model and active ensemble learning

Abstract

B. (2022). Predicting early-age stress evolution in restrained concrete by thermo-chemo-mechanical model and active ensemble learning.

A hybrid ontology‐based semantic and machine learning model for the prediction of spring breakup

“… $$$$\begin{equation}{r}_k\ \left( z \right) = \frac{1}{{\mathop \sum \nolimits_{\left( {x,h} \right)\epsilon {D}_k} h}}\ \mathop \sum \limits_{\left( {x,h} \right)\epsilon {D}_k,x < z} h\end{equation}$$$$ $$$$\begin{eqnarray} &&\hspace*{14pt} \left| {{r}_k\left( {{s}_{k.j}} \right) - {r}_k\left( {{s}_{k,j + 1}} \right)} \right| < \epsilon ,\nonumber\\ &&{s}_{k1} = \min \left( {{x}_{ik}} \right),\quad {s}_{kl} = \max \left( {{x}_{ik}} \right) \end{eqnarray}$$$$where the rank function is $${r}_k:R \to [ 0 , { + \infty } )$$, representing the proportion of instances with a feature value k smaller than z , h i is the weight of each point, and ε is an approximation factor indicating that there is 1/ ε candidate points. XGBoost has been successfully applied to flood mapping on rivers (Abedi et al., 2021), prediction of ice phenomena (Graf et al., 2022), and stress evolution on concrete (Liang et al., 2022).…”

“…XGBoost has been successfully applied to flood mapping on rivers (Abedi et al, 2021), prediction of ice phenomena (Graf et al, 2022), and stress evolution on concrete (Liang et al, 2022).…”