Table 8.
Average test result for pre-trained and ensemble model for the main dataset in five runs. Bold indicates the model holds the highest accuracy.
| Model | Accuracy | Precision | Sensitivity | F1 | Specificity |
|---|---|---|---|---|---|
| ResNet50V2 | 0.9408 | 0.9306 | 0.9502 | 0.9403 | 0.9320 |
| DenseNet201 | 0.9388 | 0.9610 | 0.9231 | 0.9412 | 0.9565 |
| MobileNet | 0.9510 | 0.9383 | 0.9661 | 0.9520 | 0.9407 |
| F-EDNC | 0.9775 | 0.9755 | 0.9795 | 0.9775 | 0.9756 |
| O-EDNC | 0.9612 | 0.9592 | 0.9631 | 0.9611 | 0.9593 |
| FC-EDNC | 0.9755 | 0.9836 | 0.9679 | 0.9757 | 0.9834 |
| CANet | 0.9224 | 0.9347 | 0.9124 | 0.9234 | 0.9331 |