MIXAD: Memory-Induced Explainable Time Series Anomaly Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912095672467456 |
|---|---|
| author | Kim, Minha Bhaumik, Kishor Kumar Ali, Amin Ahsan Woo, Simon S. |
| author_facet | Kim, Minha Bhaumik, Kishor Kumar Ali, Amin Ahsan Woo, Simon S. |
| contents | For modern industrial applications, accurately detecting and diagnosing anomalies in multivariate time series data is essential. Despite such need, most state-of-the-art methods often prioritize detection performance over model interpretability. Addressing this gap, we introduce MIXAD (Memory-Induced Explainable Time Series Anomaly Detection), a model designed for interpretable anomaly detection. MIXAD leverages a memory network alongside spatiotemporal processing units to understand the intricate dynamics and topological structures inherent in sensor relationships. We also introduce a novel anomaly scoring method that detects significant shifts in memory activation patterns during anomalies. Our approach not only ensures decent detection performance but also outperforms state-of-the-art baselines by 34.30% and 34.51% in interpretability metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22735 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MIXAD: Memory-Induced Explainable Time Series Anomaly Detection Kim, Minha Bhaumik, Kishor Kumar Ali, Amin Ahsan Woo, Simon S. Machine Learning For modern industrial applications, accurately detecting and diagnosing anomalies in multivariate time series data is essential. Despite such need, most state-of-the-art methods often prioritize detection performance over model interpretability. Addressing this gap, we introduce MIXAD (Memory-Induced Explainable Time Series Anomaly Detection), a model designed for interpretable anomaly detection. MIXAD leverages a memory network alongside spatiotemporal processing units to understand the intricate dynamics and topological structures inherent in sensor relationships. We also introduce a novel anomaly scoring method that detects significant shifts in memory activation patterns during anomalies. Our approach not only ensures decent detection performance but also outperforms state-of-the-art baselines by 34.30% and 34.51% in interpretability metrics. |
| title | MIXAD: Memory-Induced Explainable Time Series Anomaly Detection |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.22735 |