Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the pro...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kamil Faber, Marcin Pietron, Dominik Zurek
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	neuroevolution anomaly detection ensemble model CNN time series deep learning Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/57ccd6b520bd427bb61eadc5f01c1e0c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:57ccd6b520bd427bb61eadc5f01c1e0c
record_format	dspace
spelling	oai:doaj.org-article:57ccd6b520bd427bb61eadc5f01c1e0c2021-11-25T17:29:53ZEnsemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection10.3390/e231114661099-4300https://doaj.org/article/57ccd6b520bd427bb61eadc5f01c1e0c2021-11-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1466https://doaj.org/toc/1099-4300Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern failure prevention systems. Therefore, many machine learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. This work shows a framework that incorporates neuroevolution methods to boost the anomaly detection scores of new and already known models. The presented approach adapts evolution strategies for evolving an ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimize the architecture and hyperparameters such as the window size, the number of layers, and the layer depths. The proposed framework shows that it is possible to boost most anomaly detection deep learning models in a reasonable time and a fully automated mode. We ran tests on the SWAT and WADI datasets. To the best of our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.Kamil FaberMarcin PietronDominik ZurekMDPI AGarticleneuroevolutionanomaly detectionensemble modelCNNtime seriesdeep learningScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1466, p 1466 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	neuroevolution anomaly detection ensemble model CNN time series deep learning Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	neuroevolution anomaly detection ensemble model CNN time series deep learning Science Q Astrophysics QB460-466 Physics QC1-999 Kamil Faber Marcin Pietron Dominik Zurek Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
description	Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern failure prevention systems. Therefore, many machine learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. This work shows a framework that incorporates neuroevolution methods to boost the anomaly detection scores of new and already known models. The presented approach adapts evolution strategies for evolving an ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimize the architecture and hyperparameters such as the window size, the number of layers, and the layer depths. The proposed framework shows that it is possible to boost most anomaly detection deep learning models in a reasonable time and a fully automated mode. We ran tests on the SWAT and WADI datasets. To the best of our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.
format	article
author	Kamil Faber Marcin Pietron Dominik Zurek
author_facet	Kamil Faber Marcin Pietron Dominik Zurek
author_sort	Kamil Faber
title	Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
title_short	Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
title_full	Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
title_fullStr	Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
title_full_unstemmed	Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
title_sort	ensemble neuroevolution-based approach for multivariate time series anomaly detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/57ccd6b520bd427bb61eadc5f01c1e0c
work_keys_str_mv	AT kamilfaber ensembleneuroevolutionbasedapproachformultivariatetimeseriesanomalydetection AT marcinpietron ensembleneuroevolutionbasedapproachformultivariatetimeseriesanomalydetection AT dominikzurek ensembleneuroevolutionbasedapproachformultivariatetimeseriesanomalydetection
_version_	1718412283835580416

Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Ejemplares similares