Table 7 Average model performance on PIMA dataset.

From: Optimizing imbalanced learning with genetic algorithm

Metric

SMOTE9

ADASYN11

GAN71

VAE63

SGA

EGA

SVMGA

Accuracy

71.72

72.2

71.3

74.3

70.8

73.52

77.0

Precision

62.96

62.48

61.42

64.7

65.84

64.1

66.82

Recall

68.96

73.0

77.26

70.08

70.64

70.82

75.48

F1 Score

65.9

66.56

66.9

67.7

67.53

67.08

69.78

ROC AUC

71.22

72.2

72.1

73.5

71.16

73.08

75.16

  1. This table presents the average performance metrics (accuracy, precision, recall, F1 score, and ROC AUC) for models trained with different synthetic data generation techniques (SMOTE, ADASYN, GAN, VAE, SGA, EGA, and SVMGA) on the PIMA Indian Diabetes dataset.
  2. Significant values are in bold.
Back to article page