Anomaly Detection in Industrial Software Systems - Using Variational Autoencoders

Tharindu Kumarage, Nadun De Silva, Malsha Ranawaka, Chamal Kuruppu, Surangika Ranathunga

Abstract

Industrial software systems are known to be used for performing critical tasks in numerous fields. Faulty conditions in such systems can cause system outages that could lead to losses. In order to prevent potential system faults, it is important that anomalous conditions that lead to these faults are detected effectively. Nevertheless, the high complexity of the system components makes anomaly detection a high dimensional machine learning problem. This paper presents the application of a deep learning neural network known as Variational Autoencoder (VAE), as the solution to this problem. We show that, when used in an unsupervised manner, VAE outperforms the well-known clustering technique DBSCAN.Moreover, this paper shows that higher recall can be achieved using the semi-supervised one class learning of VAE, which uses only the normal data to train the model. Additionally, we show that one class learning of VAE outperforms semi-supervised one class SVM when training data consist of only a very small amount of anomalous samples. When a tree based ensemble technique is adopted for feature selection, the obtained results evidently demonstrate that the performance of the VAE is highly positively correlated with the selected feature set.

Download


Paper Citation


in Harvard Style

Kumarage T., De Silva N., Ranawaka M., Kuruppu C. and Ranathunga S. (2018). Anomaly Detection in Industrial Software Systems - Using Variational Autoencoders.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 440-447. DOI: 10.5220/0006600304400447


in Bibtex Style

@conference{icpram18,
author={Tharindu Kumarage and Nadun De Silva and Malsha Ranawaka and Chamal Kuruppu and Surangika Ranathunga},
title={Anomaly Detection in Industrial Software Systems - Using Variational Autoencoders},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={440-447},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006600304400447},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Anomaly Detection in Industrial Software Systems - Using Variational Autoencoders
SN - 978-989-758-276-9
AU - Kumarage T.
AU - De Silva N.
AU - Ranawaka M.
AU - Kuruppu C.
AU - Ranathunga S.
PY - 2018
SP - 440
EP - 447
DO - 10.5220/0006600304400447