Fig 1.
The global model collects local models updates.
Fig 2.
The proposed federated model for classifying COVID-19 cases from patient’s chest x-ray images.
Fig 3.
The proposed federated model for classifying COVID-19 cases from patient’s descriptive data.
Fig 4.
The proposed traditional model for classifying COVID-19 cases from chest x-ray images.
Fig 5.
The proposed traditional model for classifying COVID-19 cases from patient’s descriptive dataset.
Fig 6.
Model accuracy, loss and time comparison on descriptive patient’s dataset.
Table 1.
Comparison between proposed models accuracy and loss on patient’s descriptive COVID-19 datasets.
Fig 7.
Model accuracy, loss and time comparison on patient’s chest x-rays dataset.
Table 2.
Comparison between proposed models accuracy and loss on patient’s chest x-ray datasets.
Fig 8.
Model accuracy, loss and time comparison on patient’s chest x-rays dataset.
Table 3.
Comparison between proposed models accuracy and loss on patient’s chest x-ray.
Table 4.
Hardware specifications for the machine used during about experiments.
Table 5.
Patients descriptive datasets contains COVID-19 infected cases which reported in Wuhan City.
Fig 9.
Optimizer loss comparison.
Fig 10.
Learning rate comparison.
Fig 11.
Model loss comparison for 10, 50 round.
Fig 12.
Model accuracy and loss comparison for 500 round.
Fig 13.
Model loss comparison for 10, 50 round.
Fig 14.
Model accuracy and loss comparison for 100 times data size.