MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern

Currently, multivariate time series anomaly detection has made great progress in many fields and occupied an important position. The common limitation of many related studies is that there is only temporal pattern without capturing the relationship between variables and the loss of information leads...

Full description

Saved in:
Bibliographic Details
Main Authors: Q. He, Y. J. Zheng, C.L. Zhang, H. Y. Wang
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/8846608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849306168427544576
author Q. He
Y. J. Zheng
C.L. Zhang
H. Y. Wang
author_facet Q. He
Y. J. Zheng
C.L. Zhang
H. Y. Wang
author_sort Q. He
collection DOAJ
description Currently, multivariate time series anomaly detection has made great progress in many fields and occupied an important position. The common limitation of many related studies is that there is only temporal pattern without capturing the relationship between variables and the loss of information leads to false warnings. Our article proposes an unsupervised multivariate time series anomaly detection. In the prediction part, multiscale convolution and graph attention network are mainly used to capture information in temporal pattern with feature pattern. The threshold selection part uses the root mean square error between the predicted value and the actual value to perform extreme value analysis to obtain the threshold. Finally, the model in this paper outperforms other latest models on actual datasets.
format Article
id doaj-art-388c78e7ea9e44c2939bc888c1f1e22a
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-388c78e7ea9e44c2939bc888c1f1e22a2025-08-20T03:55:11ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88466088846608MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature PatternQ. He0Y. J. Zheng1C.L. Zhang2H. Y. Wang3School of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaCurrently, multivariate time series anomaly detection has made great progress in many fields and occupied an important position. The common limitation of many related studies is that there is only temporal pattern without capturing the relationship between variables and the loss of information leads to false warnings. Our article proposes an unsupervised multivariate time series anomaly detection. In the prediction part, multiscale convolution and graph attention network are mainly used to capture information in temporal pattern with feature pattern. The threshold selection part uses the root mean square error between the predicted value and the actual value to perform extreme value analysis to obtain the threshold. Finally, the model in this paper outperforms other latest models on actual datasets.http://dx.doi.org/10.1155/2020/8846608
spellingShingle Q. He
Y. J. Zheng
C.L. Zhang
H. Y. Wang
MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern
Complexity
title MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern
title_full MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern
title_fullStr MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern
title_full_unstemmed MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern
title_short MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern
title_sort mtad tf multivariate time series anomaly detection using the combination of temporal pattern and feature pattern
url http://dx.doi.org/10.1155/2020/8846608
work_keys_str_mv AT qhe mtadtfmultivariatetimeseriesanomalydetectionusingthecombinationoftemporalpatternandfeaturepattern
AT yjzheng mtadtfmultivariatetimeseriesanomalydetectionusingthecombinationoftemporalpatternandfeaturepattern
AT clzhang mtadtfmultivariatetimeseriesanomalydetectionusingthecombinationoftemporalpatternandfeaturepattern
AT hywang mtadtfmultivariatetimeseriesanomalydetectionusingthecombinationoftemporalpatternandfeaturepattern