CNN variants with reordered temporal and channel operations plus per-pulse reweighting reach pooled AUC-PR 0.816 on public HVCM dataset, beating prior methods on most subsystems and five fault families.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lightweight CNN-Based Anomaly Detection for High Voltage Converter Modulators in the Spallation Neutron Source
CNN variants with reordered temporal and channel operations plus per-pulse reweighting reach pooled AUC-PR 0.816 on public HVCM dataset, beating prior methods on most subsystems and five fault families.