Anomaly detection model for multivariate time series based on stochastic Transformer
Aiming at the problem that the existing multivariate time series anomaly detection models based on variational autoencoders could not propagate long-term temporal dependencies between stochastic variables in latent space, the stochastic Transformer for MTS anomaly detection (ST-MTS-AD) model which c...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-02-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023042/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540018948014080 |
|---|---|
| author | Weigang HUO Rui LIANG Yonghua LI |
| author_facet | Weigang HUO Rui LIANG Yonghua LI |
| author_sort | Weigang HUO |
| collection | DOAJ |
| description | Aiming at the problem that the existing multivariate time series anomaly detection models based on variational autoencoders could not propagate long-term temporal dependencies between stochastic variables in latent space, the stochastic Transformer for MTS anomaly detection (ST-MTS-AD) model which combined Transformer encoder with VAE was proposed.In the inference network of the ST-MTS-AD, the MTS long-term temporal dependent features generated by Transformer encoder and the sampled values of the stochastic variables at the previous moment were inputted into the multilayer perceptron, the approximate posterior distribution of the stochastic variables at the current moment was generated by the multilayer perceptron, and the temporal dependencies between stochastic variables were realized.The gated transition function(GTF) was used to generate the prior distribution of stochastic variables.The generation network of the ST-MTS-AD reconstructed the distribution of the MTS values at each moment by the multilayer perceptron whose input was the MTS long-term temporal dependent features generated by the inference network and the approximate posterior sampling values of stochastic variables.The distribution of normal MTS dataset was learned by the variational inference technology, and the abnormal MTS segment was determined by the log-likelihood of the reconstruction probability.Experiments on four public datasets show that the ST-MTS-AD model significantly improves the F1 score over the typical baseline models. |
| format | Article |
| id | doaj-art-164b793500264ee999fe57e53edd6e24 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-02-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-164b793500264ee999fe57e53edd6e242025-01-14T06:23:08ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-02-01449410359387033Anomaly detection model for multivariate time series based on stochastic TransformerWeigang HUORui LIANGYonghua LIAiming at the problem that the existing multivariate time series anomaly detection models based on variational autoencoders could not propagate long-term temporal dependencies between stochastic variables in latent space, the stochastic Transformer for MTS anomaly detection (ST-MTS-AD) model which combined Transformer encoder with VAE was proposed.In the inference network of the ST-MTS-AD, the MTS long-term temporal dependent features generated by Transformer encoder and the sampled values of the stochastic variables at the previous moment were inputted into the multilayer perceptron, the approximate posterior distribution of the stochastic variables at the current moment was generated by the multilayer perceptron, and the temporal dependencies between stochastic variables were realized.The gated transition function(GTF) was used to generate the prior distribution of stochastic variables.The generation network of the ST-MTS-AD reconstructed the distribution of the MTS values at each moment by the multilayer perceptron whose input was the MTS long-term temporal dependent features generated by the inference network and the approximate posterior sampling values of stochastic variables.The distribution of normal MTS dataset was learned by the variational inference technology, and the abnormal MTS segment was determined by the log-likelihood of the reconstruction probability.Experiments on four public datasets show that the ST-MTS-AD model significantly improves the F1 score over the typical baseline models.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023042/stochastic Transformervariational autoencodermultivariate time seriesanomaly detection |
| spellingShingle | Weigang HUO Rui LIANG Yonghua LI Anomaly detection model for multivariate time series based on stochastic Transformer Tongxin xuebao stochastic Transformer variational autoencoder multivariate time series anomaly detection |
| title | Anomaly detection model for multivariate time series based on stochastic Transformer |
| title_full | Anomaly detection model for multivariate time series based on stochastic Transformer |
| title_fullStr | Anomaly detection model for multivariate time series based on stochastic Transformer |
| title_full_unstemmed | Anomaly detection model for multivariate time series based on stochastic Transformer |
| title_short | Anomaly detection model for multivariate time series based on stochastic Transformer |
| title_sort | anomaly detection model for multivariate time series based on stochastic transformer |
| topic | stochastic Transformer variational autoencoder multivariate time series anomaly detection |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023042/ |
| work_keys_str_mv | AT weiganghuo anomalydetectionmodelformultivariatetimeseriesbasedonstochastictransformer AT ruiliang anomalydetectionmodelformultivariatetimeseriesbasedonstochastictransformer AT yonghuali anomalydetectionmodelformultivariatetimeseriesbasedonstochastictransformer |