A frequency-matrix plus SENet-LSTM pipeline is proposed for time-series anomaly detection and reported to beat five baselines, but the comparison is compromised by overlapping-window data leakage.
Kay, Robust detection by autoregressive spectrum analysis, IEEE Transactions on Acoustics, Speech, and Signal Processing 30 (2) (1982) 256–269
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
F-SE-LSTM: A Time Series Anomaly Detection Method with Frequency Domain Information
A frequency-matrix plus SENet-LSTM pipeline is proposed for time-series anomaly detection and reported to beat five baselines, but the comparison is compromised by overlapping-window data leakage.