TE-MSTAD fuses time-frequency features with graph-enhanced topology via RWKV and dual-branch networks to detect WSN anomalies, reporting F1 scores of 92.52% and 93.28% on public and real datasets.
A novel self- supervised learning-based anomalous node detection method based on an autoencoder for wireless sensor networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A method for detecting spatio-temporal correlation anomalies of WSN nodes based on topological information enhancement and time-frequency feature extraction
TE-MSTAD fuses time-frequency features with graph-enhanced topology via RWKV and dual-branch networks to detect WSN anomalies, reporting F1 scores of 92.52% and 93.28% on public and real datasets.