Search

Machine learning (ML) accurately predicts the shear bearing capacity of steel tube‐reinforced concrete (STRC) shear walls, aiding optimization design. However, creating a database for STRC shear walls experimentally is time‐consuming and costly. The aim of this study is to propose a method for high‐accuracy prediction of STRC shear wall shear bearing capacity using a small‐sample dataset. This study employs generative adversarial network (GAN) data augmentation techniques to address the issues of insufficient ML model training and low prediction accuracy in small‐sample databases. Based on the stacking framework, a fusion model (Stacking‐XRL) combining extreme gradient boosting (XGBoost), random forest (RF), and least absolute shrinkage and selection operator (LASSO) is established to predict the shear bearing capacity of STRC shear walls. Results show that after augmenting the training set with GAN, the prediction performance of K‐nearest neighbors (KNN), backpropagation neural network (BPNN), RF, light gradient boosting machine (LightGBM), XGBoost, and stacking‐XRL models significantly improve, with average increases of 10% in R2 and average decreases of 30% and 25% in MAE and RMSE, respectively. The proposed stacking‐XRL fusion model outperforms tested models, existing formulas, and Abaqus numerical simulations for the shear bearing capacity of STRC shear walls. Model interpretation reveals that the shear span ratios as the most important factors in predicting shear bearing capacity, followed by axial force ratio and whole section configuration steel tubular index. [ABSTRACT FROM AUTHOR]

Gulfweed was used as raw material, and KOH activation method was adopted for producing activated carbons with high specific surface area.The prepared super activated carbon not only has large specific surface area, rich pore structure, but also reduces the production cost of activated carbon by using algae as precursor material. In order to explore the experimental approaches and technological conditions, single factor method was used to analyze the influence of impregnation ratio, activation time and activation temperature on specific surface area, pore structure and surface properties, and the electrochemical performance of super-capacitor based on the prepared activated carbon was studied. Measurements such as N2 adsorption, XRD, SEM, constant current charge-discharge techniques, and the cyclic voltammetry were carried out to investigate specific surface area, pore structure and electrochemical performance. The results show:the best preparation condition is concluded as:impregnation ratio at 4:1, activation time for 120 min and activation temperature at 800℃, on the occasion, the largest specific surface area is 2926m2/g, and the biggest pore volume is 1.536cm3/g with all the pore diameters almost under 4nm evenly. The super-capacitor has a large specific capacitance as 358.5F/g in the 6mol/L KOH electrolyte, which means a very good performance.

Abstract Background With DNA microarray data, selecting a compact subset of discriminative genes from thousands of genes is a critical step for accurate classification of phenotypes for, e.g., disease diagnosis. Several widely used gene selection methods often select top-ranked genes according to their individual discriminative power in classifying samples into distinct categories, without considering correlations among genes. A limitation of these gene selection methods is that they may result in gene sets with some redundancy and yield an unnecessary large number of candidate genes for classification analyses. Some latest studies show that incorporating gene to gene correlations into gene selection can remove redundant genes and improve classification accuracy. Results In this study, we propose a new method, Based Bayes error Filter (BBF), to select relevant genes and remove redundant genes in classification analyses of microarray data. The effectiveness and accuracy of this method is demonstrated through analyses of five publicly available microarray datasets. The results show that our gene selection method is capable of achieving better accuracies than previous studies, while being able to effectively select relevant genes, remove redundant genes and obtain efficient and small gene sets for sample classification purposes. Conclusion The proposed method can effectively identify a compact set of genes with high classification accuracy. This study also indicates that application of the Bayes error is a feasible and effective wayfor removing redundant genes in gene selection.