Skip to content

In this paper, we propose the use of Echo State Networks, for anomaly detection on-the-edge in aerospace applications. The anomaly detection method uses a nonparametric dynamic threshold to detect anomalous behaviours from the observed data by comparing it to the model's predictions.

Notifications You must be signed in to change notification settings

Sopralapanca/thesis-anomaly-detection-esn

Repository files navigation

Efficient Anomaly Detection on Temporal Data via Echo State Networks and Dynamic Thresholding

This repository provides code for the experiments done in the paper Efficient Anomaly Detection on Temporal Data via Echo State Networks and Dynamic Thresholding

Citation

@inproceedings{carta2022efficient,
  title={Efficient Anomaly Detection on Temporal Data via Echo State Networks and Dynamic Thresholding.},
  author={Carta, Antonio and Carf{\`\i}, Giacomo and De Caro, Valerio and Gallicchio, Claudio and others},
  booktitle={CI4PM/PAI@ WCCI},
  pages={56--67},
  year={2022}
}

About

In this paper, we propose the use of Echo State Networks, for anomaly detection on-the-edge in aerospace applications. The anomaly detection method uses a nonparametric dynamic threshold to detect anomalous behaviours from the observed data by comparing it to the model's predictions.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published