Anomaly detection using 1D-CNN

Implementation of a two-step method for anomaly detection using deep 1D-CNN architectures: Implementation of a two-step method for anomaly detection using deep 1D-CNN architectures:
1) Learning step : use pretext tasks to learn a representation of the data in a self-supervised way
2) Anomaly detection step : raise an anomaly each time the data reconstruction score is greater than a given threshold

Documentation

Methodological Guidelines

• Methodological Guideline for Anomaly Detection Models
• Methodological Guideline for Time Series Anomaly Detection

Benchmarks

• Unsupervised Anomaly Detection and Explainability tools for Time Series

Applications over use-cases

• Anomaly Detection Models Use Case level document

A restricted demonstrator is available here. It relies on a time-series data quality use-case.

Support

Support for Anomaly detection using 1D-CNN must be obtained directly from the component owners.