S1 Data - حسب Gaosha Li (20570760)

"…A combination of four machine learning algorithms (XGBoost、Logistic Regression、Random Forest、AdaBoost) was employed to predict NPM recurrence, and the model with the highest Area Under the Curve (AUC) in the test set was selected as the best model. …"

Supporting data for “The role of forest composition heterogeneity on temperate ecosystem carbon dynamic under climate change" حسب Ziyu Lin (9151064)

Iteration curve of the optimization process. حسب Meijun Shang (22806461)

"…The load-bearing mechanism of the proposed steel platform was analyzed theoretically, and finite element analysis (FEA) was employed to evaluate the stresses and deflections of key members. A particle swarm optimization (PSO) algorithm was integrated with the FEA model to optimize the cross-sectional dimensions of the primary beams, secondary beams, and foundation boxes, achieving a balance between load-bearing capacity and cost efficiency. …"

Error of ICESat-2 with respect to airborne data. حسب Qinghua Li (398885)

"…In the hybrid model of this paper, the choice was made to use the Densenet architecture of CNN models with LightGBM as the primary model. …"

Table_1_Application of machine learning algorithms in predicting HIV infection among men who have sex with men: Model development and validation.docx حسب Jiajin He (13386702)

The prediction error of each model. حسب Hao Yang (328526)

"…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …"

Results for model hyperparameter values. حسب Hao Yang (328526)

"…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …"

Stability analysis of each model. حسب Hao Yang (328526)

"…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …"

Robustness Analysis of each model. حسب Hao Yang (328526)

"…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …"

The workflow of the proposed model. حسب Subathra Gunasekaran (19492680)

"…Next, we employ batch normalization to smooth and enhance the collected data, followed by feature extraction using the AlexNet model. …"

Consort diagram for the study. حسب Nicola Lazzarini (3528197)

الموضوعات:

Performance confidence intervals. حسب Nicola Lazzarini (3528197)

الموضوعات:

Baseline characteristics of patients in the study cohort. حسب Nicola Lazzarini (3528197)

الموضوعات:

Input features. حسب Nicola Lazzarini (3528197)

الموضوعات:

Most important predictive features. حسب Nicola Lazzarini (3528197)

الموضوعات:

Age feature importance. حسب Nicola Lazzarini (3528197)

الموضوعات:

Machine learning vs. clinicians. حسب Nicola Lazzarini (3528197)

الموضوعات:

ROC curves. حسب Nicola Lazzarini (3528197)

الموضوعات:

PR curves. حسب Nicola Lazzarini (3528197)

الموضوعات:

Overview of the cohort definition process. حسب Nicola Lazzarini (3528197)

الموضوعات: