Table 5 Performance evaluation of the proposed FDEIoL using various DL models on the CXR images dataset.

From: Advanced federated ensemble internet of learning approach for cloud based medical healthcare monitoring system

Classifiers

Evaluation Parameters

Classes

Overall

Accuracy

Error Rate

Cohen’s Kappa

Average F1Score

Covid-19

PNA

TB

Normal

HincV3XGBoost

Precision

0.99

0.98

1.00

1.00

0.9888

0.0112

0.990001

0.9925

Recall

0.99

0.99

1.00

0.99

F1-Score

0.99

0.99

1.00

0.99

Specificity

0.99

0.99

1.00

1.00

LT-ViT

Precision

0.90

0.92

0.96

0.98

0.9429

0.0571

0.9171

0.9375

Recall

0.95

0.89

0.97

0.94

F1-Score

0.92

0.91

0.96

0.96

Specificity

0.97

0.96

0.98

0.99

BM-Net

Precision

0.99

0.98

1.00

0.99

 

0.0085

0.9932

0.99

Recall

0.99

0.98

1.00

0.99

0.9915

F1-Score

0.99

0.98

1.00

0.99

 

Specificity

0.99

1.00

1.00

1.00

VGG-SCNets

Precision

1.00

0.97

0.97

1.00

 

0.0208

0.9700

0.985

Recall

1.00

0.97

0.98

1.00

0.9792

F1-Score

1.00

0.97

0.97

1.00

 

Specificity

0.99

0.99

0.99

0.98

MEEDNets

Precision

0.98

1.00

1.00

1.00

0.9919

0.0081

0.9932

0.9925

Recall

0.99

0.99

1.00

0.99

F1-Score

0.99

0.99

1.00

0.99

Specificity

0.99

1.00

1.00

1.00

ResGANet

Precision

0.96

0.97

1.00

0.96

 

0.021

0.9666

0.975

Recall

0.96

0.96

1.00

0.98

0.9790

F1-Score

0.96

0.97

1.00

0.97

 

Specificity

0.98

0.99

1.00

0.98

Ensemble Except FL Modeling

Precision

0.98

0.99

0.99

0.98

0.9795

0.0205

0.980002

0.96

Recall

0.98

0.96

1.00

1.00

F1-Score

0.98

0.98

0.89

0.99

Specificity

0.99

0.99

0.99

0.99

Proposed FDEIoL

Precision

1.00

0.99

1.00

1.00

0.9924

0.0076

0.996667

0.995

Recall

1.00

1.00

1.00

0.99

F1-Score

1.00

0.99

1.00

0.99

Specificity

1.00

1.00

1.00

1.00