Comparison of areas under the ROC and PR curves, for each replica of the dataset. حسب João Albuquerque (12936572)

Modeling CO₂ solubility in polyethylene glycol polymer using data driven methods حسب YunLi Lei (21458056)

"…In this research, a Random Forest (RF) machine learning model is meticulously tuned through four sophisticated optimization algorithms: Batch Bayesian Optimization (BBO), Self-Adaptive Differential Evolution (SADE), Bayesian Probability Improvement (BPI), and Gaussian Processes Optimization (GPO). …"

Paeameter ranges and optimal values. حسب Zhen Zhao (159931)

"…Additionally, considering the imbalanced in population spatial distribution, we used the K-means ++ clustering algorithm to cluster the optimal feature subset, and we used the bootstrap sampling method to extract the same amount of data from each cluster and fuse it with the training subset to build an improved random forest model. …"

Thesis-RAMIS-Figs_Slides حسب Felipe Santibañez-Leal (10967991)

"…In addition, the practical benefits for \emph{<i>MPS</i>} in the context of simulating channelized facies models is demonstrated using synthetic data and real geological facies. Importantly, this strategy locates samples adaptively on the transition between facies which improves the performance of conventional \emph{<i>MPS</i>} algorithms. …"

Cell-free DNA coverage and fragmentomic profiles produced under various sequencing protocols حسب Antoine Passemiers (17302912)

Hierarchical clustering to infer a binary tree with <i>K</i> = 4 sampled populations. حسب Tristan Mary-Huard (3864)

MLP vs classification algorithms. حسب Mohd Mustaqeem (19106494)

"…We propose SPAM-XAI, a hybrid model integrating novel sampling, feature selection, and eXplainable-AI (XAI) algorithms to address these challenges. …"

Image 1_Prediction of outpatient rehabilitation patient preferences and optimization of graded diagnosis and treatment based on XGBoost machine learning algorithm.tif حسب Xuehui Fan (10762662)

Multimodal Mass Spectrometry Imaging of Rat Brain Using IR-MALDESI and NanoPOTS-LC-MS/MS حسب Crystal L. Pace (9105558)

"…The aim of this work was to create a multimodal MSI approach that measures metabolomic and proteomic data from a single biological organ by combining infrared matrix-assisted laser desorption electrospray ionization (IR-MALDESI) for metabolomic MSI and nanodroplet processing in one pot for trace samples (nanoPOTS) LC-MS/MS for spatially resolved proteome profiling. …"

Multimodal Mass Spectrometry Imaging of Rat Brain Using IR-MALDESI and NanoPOTS-LC-MS/MS حسب Crystal L. Pace (9105558)

"…The aim of this work was to create a multimodal MSI approach that measures metabolomic and proteomic data from a single biological organ by combining infrared matrix-assisted laser desorption electrospray ionization (IR-MALDESI) for metabolomic MSI and nanodroplet processing in one pot for trace samples (nanoPOTS) LC-MS/MS for spatially resolved proteome profiling. …"

REDUCTION OF SAMPLE SIZE IN THE ANALYSIS OF SPATIAL VARIABILITY OF NONSTATIONARY SOIL CHEMICAL ATTRIBUTES حسب Tamara C. Maltauro (7366898)

"…<div><p>ABSTRACT In the study of spatial variability of soil attributes, it is essential to define a sampling plan with adequate sample size. This study aimed to evaluate, through simulated data, the influence of parameters of the geostatistical model and sampling configuration on the optimization process, and resize and reduce the sample size of a sampling configuration of a commercial area composed of 102 points. …"

Parameter sensitivity analysis and optimization improves model fit to <i>in vitro</i> data. حسب Nikita Sivakumar (14186176)

Technical approach. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

Pearson correlation coefficient matrix plot. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

SHAP of stacking. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

Stacking ROC curve chart. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

Confusion matrix. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

GA-XGBoost feature importances. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

Partial results of the chi-square test. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"

Stacking confusion matrix. حسب Wenguang Li (6528113)

"…The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model’s predictive accuracy. …"