Table 3 Accuracy and test metric comparison against DenseNet121 and ResNet50 architectures.
Metric | DenseNet121 | ResNet50 | ||||
|---|---|---|---|---|---|---|
| Â | Precision | Recall | F1-score | Precision | Recall | F1-score |
0 (fake) | 0.98 | 0.77 | 0.86 | 0.99 | 0.99 | 0.99 |
1 (real) | 0.81 | 0.99 | 0.89 | 0.99 | 0.99 | 0.99 |
Accuracy | – | – | 0.88 | – | – | 0.99 |
Macro Average | 0.9 | 0.88 | 0.88 | 0.99 | 0.99 | 0.99 |
Weighted Average | 0.9 | 0.88 | 0.88 | 0.99 | 0.99 | 0.99 |
Test Accuracy | 0.8769 | 0.9885 | ||||
Test Loss | 0.4602 | 0.05 | ||||
Area Under Curve (AUC) | 0.9838 | 0.9885 | ||||
