HIGHLIGHTS
- who: Sajjad Ahmad and colleagues from the Department of Electrical, Electronic and Computer Engineering, University of, have published the paper: A Centrifugal Pump Fault Diagnosis Framework Based on Supervised Contrastive Learning, in the Journal: Sensors 2022, 22, 6448. of /2022/
- what: The proposed model also showed stability when the experiment was repeated 10 times; the model had higher accuracy than the referenced methods because the authors used contrastive learning that provided the classifier with highly discriminant features, while the other methods provided non-discriminant and indifferentiable features to the classifier, which resulted in low accuracy . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.