About Using of Autoencoders for Anomaly Detection in Cyber-physical Systems
DOI:
https://doi.org/10.17072/1993-0550-2022-4-89-94Keywords:
deep learning, autoencoders, anomaly detection in technological process, time seriesAbstract
Using of autoencoder for anomaly detection in cyberphysical systems was investigated. Some popular methods and datasets were observed. Suggested approach was applied to data and task from SWAT dataset. Achieved results was compared with existing baselines.References
TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks. URL: https://arxiv.org/abs/2009.07769 (дата обращения: 01.11.2022).
An Introductory Study on Time Series Modeling and Forecasting: описание SARIMA URL: https://arxiv.org/ftp/arxiv/papers/ 1302/1302.6613.pdf (дата обращения: 01.11.2022).
A. Nanduri and L. Sherry. Anomaly detection in aircraft data using Recurrent Neural Networks (RNN). 2016. Integrated Communications Navigation and Surveillance (ICNS). 2016;5C2-1-5C2-8. doi: 10.1109/ICNSURV.2016.7486356.
P. Malhotra, L. Vig, G. Shroff, and P. Agarwal. Long Short Term Memory Networks for Anomaly Detection in Time Series, in European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2015.
T. Schlegl, P. Seebock, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery, in International Conference on Information Processing in Medical Imaging. Springer. 2017; 146–157.
Работа с автокодировщиками в Tensor-Flow. URL: https://www.tensorflow.org/ tutorials/generative/autoencoder (дата обращения: 01.11.2022).
Описание датасета SWAT от Сингапурского университета технологии и дизайна (SUTD). URL: https://www.researchgate.net/
publication/305809559_A_Dataset_to_ Sup-port_Research_in_the_Design_of_Secure_Water_Treatment_Systems (дата обращения: 01.11.2022).
Датасет SKAB (Skoltech Anomaly Benchmark). URL: https://paperswithcode. com/dataset/skab (дата обращения: 01.11.2022).
Библиотека Orion для распознавания аномалий https://pypi.org/project/orion-ml/.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Юрий Юрьевич Чернышов
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are published under license Creative Commons Attribution 4.0 International (CC BY 4.0).
