بدائل البحث:
model optimization » codon optimization (توسيع البحث), global optimization (توسيع البحث), wolf optimization (توسيع البحث)
class model » lasso model (توسيع البحث), classic models (توسيع البحث)
model optimization » codon optimization (توسيع البحث), global optimization (توسيع البحث), wolf optimization (توسيع البحث)
class model » lasso model (توسيع البحث), classic models (توسيع البحث)
-
1
-
2
-
3
-
4
-
5
The comparison of the accuracy score of the benchmark and the proposed models.
منشور في 2025الموضوعات: -
6
-
7
-
8
Comparison of baseline and hybrid machine learning models in predicting IVF outcomes (%).
منشور في 2025الموضوعات: -
9
-
10
Calibration curve of the ABC–LR–RF hybrid model for IVF outcome prediction.
منشور في 2025الموضوعات: -
11
ROC and PR–AUC curves of the ABC–LR–RF hybrid model for IVF outcome prediction.
منشور في 2025الموضوعات: -
12
The statistical description of the original data set of the patients (<i>n</i> = 162).
منشور في 2025الموضوعات: -
13
-
14
The list of parameters of the modified data set for machine learning (<i>n</i> = 162).
منشور في 2025الموضوعات: -
15
-
16
-
17
Processed dataset to train and test the WGAN-GP_IMOA_DA_Ensemble model
منشور في 2025"…This framework integrates a novel biologically inspired optimization algorithm, the Indian Millipede Optimization Algorithm (IMOA), for effective feature selection. …"
-
18
-
19
Supplementary Material 8
منشور في 2025"…In AMR studies, datasets often contain more susceptible isolates than resistant ones, leading to biased model performance. SMOTE overcomes this issue by generating synthetic samples of the minority class (resistant isolates) through interpolation rather than simple duplication, thereby improving model generalization.…"
-
20
Predictive Analysis of Mushroom Toxicity Based Exclusively on Their Natural Habitat.
منشور في 2025"…<br> <br>Conclusion<br><br>The study concludes that the habitat variable, used in isolation, is insufficient to create a safe and reliable mushroom toxicity classification model. The consistent accuracy of 70.28% does not represent a flaw in the SVM. algorithm, but rather the predictive performance ceiling of the feature itself, whose simplicity and class overlap limit the model's discriminatory ability. …"