[ENH] Add DL anomaly detection algorithms: LSTM-AD

aeon-toolkit / aeon

A toolkit for machine learning from time series

https://aeon-toolkit.org/

BSD 3-Clause "New" or "Revised" License

1.02k stars 122 forks source link

[ENH] Add DL anomaly detection algorithms: LSTM-AD #1637

Open SebastianSchmidl opened 5 months ago

SebastianSchmidl commented 5 months ago

Describe the feature or idea you want to propose

Add LSTM-AD as an anomaly detector to aeon. Reference paper: http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2015-56.pdf

Describe your proposed solution

TimeEval implementation: https://github.com/TimeEval/TimeEval-algorithms/tree/main/lstm_ad
there is no reference implementation

Describe alternatives you've considered, if relevant

No response

Additional context

No response

itsdivya1309 commented 1 month ago

Hi, could you please provide a link to the paper? The above link seems to be broken.

SebastianSchmidl commented 1 month ago

Sorry, the paper was moved to a "legacy"-URL 🤷🏼 : https://www.esann.org/sites/default/files/proceedings/legacy/es2015-56.pdf

This is the reference:

Malhotra, Pankaj, Lovekesh Vig, Gautam Shroï¬€, and Puneet Agarwal. â€œLong Short Term Memory Networks for Anomaly Detection in Time Series.â€ In Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Vol. 23, 2015.