Cargando…

Anomaly Detection Using an Ensemble of Multi-Point LSTMs

As technologies for storing time-series data such as smartwatches and smart factories become common, we are collectively accumulating a great deal of time-series data. With the accumulation of time-series data, the importance of time-series abnormality detection technology that detects abnormal patt...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Geonseok, Yoon, Youngju, Lee, Kichun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10670439/
https://www.ncbi.nlm.nih.gov/pubmed/37998172
http://dx.doi.org/10.3390/e25111480
_version_ 1785139923596083200
author Lee, Geonseok
Yoon, Youngju
Lee, Kichun
author_facet Lee, Geonseok
Yoon, Youngju
Lee, Kichun
author_sort Lee, Geonseok
collection PubMed
description As technologies for storing time-series data such as smartwatches and smart factories become common, we are collectively accumulating a great deal of time-series data. With the accumulation of time-series data, the importance of time-series abnormality detection technology that detects abnormal patterns such as Cyber-Intrusion Detection, Fraud Detection, Social Networks Anomaly Detection, and Industrial Anomaly Detection is emerging. In the past, time-series anomaly detection algorithms have mainly focused on processing univariate data. However, with the development of technology, time-series data has become complicated, and corresponding deep learning-based time-series anomaly detection technology has been actively developed. Currently, most industries rely on deep learning algorithms to detect time-series anomalies. In this paper, we propose an anomaly detection algorithm with an ensemble of multi-point LSTMs that can be used in three cases of time-series domains. We propose our anomaly detection model that uses three steps. The first step is a model selection step, in which a model is learned within a user-specified range, and among them, models that are most suitable are automatically selected. In the next step, a collected output vector from M LSTMs is completed by stacking ensemble techniques of the previously selected models. In the final step, anomalies are finally detected using the output vector of the second step. We conducted experiments comparing the performance of the proposed model with other state-of-the-art time-series detection deep learning models using three real-world datasets. Our method shows excellent accuracy, efficient execution time, and a good F1 score for the three datasets, though training the LSTM ensemble naturally requires more time.
format Online
Article
Text
id pubmed-10670439
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106704392023-10-26 Anomaly Detection Using an Ensemble of Multi-Point LSTMs Lee, Geonseok Yoon, Youngju Lee, Kichun Entropy (Basel) Article As technologies for storing time-series data such as smartwatches and smart factories become common, we are collectively accumulating a great deal of time-series data. With the accumulation of time-series data, the importance of time-series abnormality detection technology that detects abnormal patterns such as Cyber-Intrusion Detection, Fraud Detection, Social Networks Anomaly Detection, and Industrial Anomaly Detection is emerging. In the past, time-series anomaly detection algorithms have mainly focused on processing univariate data. However, with the development of technology, time-series data has become complicated, and corresponding deep learning-based time-series anomaly detection technology has been actively developed. Currently, most industries rely on deep learning algorithms to detect time-series anomalies. In this paper, we propose an anomaly detection algorithm with an ensemble of multi-point LSTMs that can be used in three cases of time-series domains. We propose our anomaly detection model that uses three steps. The first step is a model selection step, in which a model is learned within a user-specified range, and among them, models that are most suitable are automatically selected. In the next step, a collected output vector from M LSTMs is completed by stacking ensemble techniques of the previously selected models. In the final step, anomalies are finally detected using the output vector of the second step. We conducted experiments comparing the performance of the proposed model with other state-of-the-art time-series detection deep learning models using three real-world datasets. Our method shows excellent accuracy, efficient execution time, and a good F1 score for the three datasets, though training the LSTM ensemble naturally requires more time. MDPI 2023-10-26 /pmc/articles/PMC10670439/ /pubmed/37998172 http://dx.doi.org/10.3390/e25111480 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lee, Geonseok
Yoon, Youngju
Lee, Kichun
Anomaly Detection Using an Ensemble of Multi-Point LSTMs
title Anomaly Detection Using an Ensemble of Multi-Point LSTMs
title_full Anomaly Detection Using an Ensemble of Multi-Point LSTMs
title_fullStr Anomaly Detection Using an Ensemble of Multi-Point LSTMs
title_full_unstemmed Anomaly Detection Using an Ensemble of Multi-Point LSTMs
title_short Anomaly Detection Using an Ensemble of Multi-Point LSTMs
title_sort anomaly detection using an ensemble of multi-point lstms
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10670439/
https://www.ncbi.nlm.nih.gov/pubmed/37998172
http://dx.doi.org/10.3390/e25111480
work_keys_str_mv AT leegeonseok anomalydetectionusinganensembleofmultipointlstms
AT yoonyoungju anomalydetectionusinganensembleofmultipointlstms
AT leekichun anomalydetectionusinganensembleofmultipointlstms