Skip to content
/ TeVAE Public

TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-state Multivariate Time-series Data

License

Notifications You must be signed in to change notification settings

lcs-crr/TeVAE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TeVAE

TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-state Multivariate Time-series Data

Paper corresponding to source code is submitted to the Studies in Computational Intelligence journal.

Working scripts can be found in the src folder. The data.py script outlines the pre-processing of the data. The training.py script automates model training for all models across different seeds and data splits. The evaluation.py script outlines the steps taken to evaluate the models discussed.

Utility scripts can be found in the utils folder.

Custom model classes for each of the tested approaches can be found in the models folder.

requirements.txt contains all libraries used.

About

TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-state Multivariate Time-series Data

Resources

License

Stars

Watchers

Forks

Languages