Table 2 Performance Metrics of Two Similarity Functions.

From: Intelligent diagnosis of gearbox in data heterogeneous environments based on federated supervised contrastive learning framework

Datasets

DDS

WTDS

Metrics

Similarity function

Cosine similarity

Euclidean distance

Cosine similarity

Euclidean distance

Accuracy

0.9936

0.9872

0.9507

0.9502

Specificity

0.9958

0.9923

0.9574

0.9454

Sensitivity

0.9764

0.9461

0.8978

0.9322

AUC

0.9995

0.9978

0.9741

0.9708

F1

0.9718

0.9422

0.8472

0.8497

Back to article page