Table 6.
Comparison of the results with state-of-the art CNN methods for COVID-19 dataset
| Source | Models/methods | Number of classes | Overall acc (%) |
|---|---|---|---|
| Song et al. [78] | DRE-Net |
2 3 |
86 93 |
| Ozturk et al.[79] | DarkCovidNet |
3 2 |
87.02 98.08 |
| Wang et al. [80] | CNNs, transfer learning | 2 | 89.5 |
| Keidar et al.[81] | Data augmentation, segmentation and CNN | 2 | 90.3 |
| Wang et al. [50] | Customized CNN architectur | 3 | 93.33 |
| Zhang et al.[82] | COVID19XrayNet | 2 | 91.92 |
| Goel et al.[83] | OptCoNet | 3 | 97.78 |
| Proposed | COVID-CCD-Net | 3 | 98.107 |