Table 9.
Comparison of the proposed models with previous studies
| Study | Methodology | Accuracy (%) |
|---|---|---|
| Rehman et al. (2020) | ResNet101, MobileNet | 98.75 |
| Shorfuzzaman and Masud (2020) | VGG16, ResNet50, Xception, MobileNet, and DenseNet121 | 99.26 |
| Degadwala et al. (2021) | FT CNN | 90.70 |
| Minaee et al. (2020) | ResNet, SqueezeNet, and DenseNet121 | 98.00 |
| Iskanderani et al. (2021) | DenseNet | 96.25 |
| Pathak et al. (2020) | ResNet32 | 96.22 |
| Apostolopoulos and Mpesiana (2020) | MobileNetV2 | 96.78 |
| Kaur et al. (2021) | AlexNet | 99.52 |
| Wang et al. (2020) | ResNet101 and ResNet152 | 96.10 |
| Misra et al. (2020) | ResNet18 | 93.90 |
| Punn and Agarwal (2021) | ResNet, Inception-v3, and NASNetLarge | 97.00 |
| Ucar and Korkmaz (2020) | Bayes-SqueezeNet(CNN) | 98.30 |
| Narin et al. (2021) | ResNets and Inception | 96.10 |
| Lee et al. (2020) | VGG16 | 95.00 |
| Ismael and Şengür (2021) | ResNet50 | 92.60 |
| Wang et al. (2020) | COVID-Net | 94.00 |
| Nishio et al. (2020) | VGG16 | 86.30 |
| Monshi et al. (2021) | CovidX-RayNet | 95.82 |
| Das et al. (2021) | VGG16 | 97.67 |
| Rahaman et al. (2020) | VGG19 | 89.30 |
| Moujahid et al. (2020) | VGG19 | 96.97 |
| Khan et al. (2020) | Coro-Net | 95.00 |
| Ohata et al. (2020) | DenseNet201 | 95.60 |
| Manokaran et al. (2021) | DenseNet201 | 92.19 |
| Garg et al. (2020) | DenseNet121 | 94.00 |
| Naronglerdrit et al. (2021) | MobileNet | 96.76 |
| Xu et al. (2020) | ResNet + Location Attention | 86.70 |
| Ozturk et al. (2020) | DarkCovidNet | 87.02 |
| Asif and Wenhui (2020) | InceptionV3 | 96.00 |
| Luz et al. (2021) | EfficientNet | 93.90 |
| Bargshady et al. (2022) | CycleGAN | 94.20 |
| Rahimzadeh and Attar (2020) | Xception + ResNet50V2 | 91.40 |
| Model 1 | MobileNetV2+Classical fine-tuning | 95.62 |
| Model 2 | MobileNetV2+Step fine-tuning | 96.10 |
| Model 3 | MobileNetV2+Exponential fine-tuning | 97.61 |