SAGE decomposes univariate time-series anomaly detection into four specialized LLM analyzers plus an evidence-grounded detector and supervisor, achieving the highest average performance on three benchmarks while using only normal data for in-context examples.
LSTM-based encoder-decoder for multi-sensor anomaly detection.CoRR, abs/1607.00148
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine. However, there are often external factors or variables which are not captured by sensors leading to time-series which are inherently unpredictable. For instance, manual controls and/or unmonitored environmental conditions or load may lead to inherently unpredictable time-series. Detecting anomalies in such scenarios becomes challenging using standard approaches based on mathematical models that rely on stationarity, or prediction models that utilize prediction errors to detect anomalies. We propose a Long Short Term Memory Networks based Encoder-Decoder scheme for Anomaly Detection (EncDec-AD) that learns to reconstruct 'normal' time-series behavior, and thereafter uses reconstruction error to detect anomalies. We experiment with three publicly available quasi predictable time-series datasets: power demand, space shuttle, and ECG, and two real-world engine datasets with both predictive and unpredictable behavior. We show that EncDec-AD is robust and can detect anomalies from predictable, unpredictable, periodic, aperiodic, and quasi-periodic time-series. Further, we show that EncDec-AD is able to detect anomalies from short time-series (length as small as 30) as well as long time-series (length as large as 500).
verdicts
UNVERDICTED 6representative citing papers
PhaseNet++ detects anomalies in industrial control systems by processing both magnitude and phase from STFT using a Phase Coherence Index graph and dual-head decoder, achieving 90.98% F1 on the SWaT benchmark.
A transformer model guided by a causal graph prior achieves state-of-the-art anomaly detection and root-cause attribution on ASD and SMD benchmarks by restricting main predictions to graph-supported causes while using an isolated shadow path for residual correlations.
T-BiGAN integrates window-attention Transformers in a BiGAN to achieve ROC-AUC 0.95 and average precision 0.996 for unsupervised spatiotemporal anomaly detection in PMU data.
ATSDLN uses FCN representation learning plus detector and parameter selection sub-networks to adaptively choose anomaly detectors for time series, claiming better performance and expandability via transfer learning on public datasets.
Encoder-decoder model detects synthetic anomalies in additive manufacturing image sequences unsupervised and surfaces previously unnoticed temperature non-uniformity.
citing papers explorer
-
Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
SAGE decomposes univariate time-series anomaly detection into four specialized LLM analyzers plus an evidence-grounded detector and supervisor, achieving the highest average performance on three benchmarks while using only normal data for in-context examples.
-
PhaseNet++: Phase-Aware Frequency-Domain Anomaly Detection for Industrial Control Systems via Phase Coherence Graphs
PhaseNet++ detects anomalies in industrial control systems by processing both magnitude and phase from STFT using a Phase Coherence Index graph and dual-head decoder, achieving 90.98% F1 on the SWaT benchmark.
-
Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection
A transformer model guided by a causal graph prior achieves state-of-the-art anomaly detection and root-cause attribution on ASD and SMD benchmarks by restricting main predictions to graph-supported causes while using an isolated shadow path for residual correlations.
-
Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN
T-BiGAN integrates window-attention Transformers in a BiGAN to achieve ROC-AUC 0.95 and average precision 0.996 for unsupervised spatiotemporal anomaly detection in PMU data.
-
An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series
ATSDLN uses FCN representation learning plus detector and parameter selection sub-networks to adaptively choose anomaly detectors for time series, claiming better performance and expandability via transfer learning on public datasets.
-
An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
Encoder-decoder model detects synthetic anomalies in additive manufacturing image sequences unsupervised and surfaces previously unnoticed temperature non-uniformity.