A federated learning setup with decentralized validation and four noise-robust aggregation rules improves remaining useful life predictions for five of six simulated airlines on the N-CMAPSS engine dataset compared with isolated training.
Arias Chao, C
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated learning framework for collaborative remaining useful life prognostics: an aircraft engine case study
A federated learning setup with decentralized validation and four noise-robust aggregation rules improves remaining useful life predictions for five of six simulated airlines on the N-CMAPSS engine dataset compared with isolated training.