Table 8 Comparative analysis of ablation analysis for different parameters on skin dataset.

From: A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameters optimization

Metric

Hybrid U-Net

MobileNet-V3

Augmentation

Batch Normalization

Hyperparameters

Without Hybrid U-Net

With Hybrid U-Net

Without MobileNet-V3

With MobileNet-V3

Without Augmentation

With Augmentation

Without Batch Normalization

With Batch Normalization

Default Hyperparameters

Optimized Hyperparameters

Accuracy

85.25

92.4

88.32

94.38

86.38

92.38

87.37

93.25

89.37

94.39

Precision

78.2

89.14

85.27

92.2

80.28

88.18

82.27

91.71

86.67

92.37

Recall

92.15

95.93

94.69

97.38

91.37

95.33

90.37

95.37

93.4

96.92

F1-Score

84.24

92.96

89.35

94.13

85.37

91.2

86.38

92.75

89.17

94.37

Back to article page