Temporal convolutional autoencoders outperform isolation forests and other autoencoder variants for unsupervised anomaly detection on a real-world industrial dataset with non-periodic multi-scale dynamics.
Process data based estimation of tool wear on punching machines using TCN-autoencoder from raw time-series information,
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
-
Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study
Temporal convolutional autoencoders outperform isolation forests and other autoencoder variants for unsupervised anomaly detection on a real-world industrial dataset with non-periodic multi-scale dynamics.