Table 9 Accuracy demonstrated by the proposed federated learning for training and testing with lesser number of class samples and compare with earlier reported work.
From: Leveraging federated learning and edge computing for pandemic-resilient healthcare
Class | ClassName | No.of female | No.of male | ProposedFederated learning accuracy (%) for | Previous federated learning work | References | ||
|---|---|---|---|---|---|---|---|---|
Female | Male | Method | Accuracy (%) | |||||
0 | NotWearing | 725 | 6275 | 92.9 | 93.5 | SRNet20-FL | 98.5 | |
1 | Wearing | 5375 | 1625 | 95.2 | 94.5 | Federated Multi-mask | 94.1 | |
2 | NotProperly Wearing | 2750 | 4250 | 90.3 | 92.1 | Federated Learning | 93 | |
Lung Cancer | 2145 (Training) | 2845 (validation) | – | – | Federated Learning + CapsNet | 99.6 | ||
Face Recognition | Federated Learning +fedFace | 99.28 | ||||||
