Situation-Aware Multivariate Time Series Anomaly Detection Through Active Learning and Contrast VAE-Based Models in Large Distributed Systems

Zhao, Youjian; Geng, Yitong; Zhao, Zhanxiang; Wang, Hanzhang; Jiang, Huai; Vaidya, Amber; Su, Liangfei; Pei, Dan

doi:10.1109/jsac.2022.3191341

Cited by 20 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the consistency of the user interaction will have a large impact on the performance of the suggested method because it affects the possibility to optimize the threshold after the validation procedure. The time cost of the suggested method is of importance to consider but has not been explored, similarly to other user interaction studies [18], [19]. The reason for this was the use of a simulated user where conversion to human interaction time cannot be properly translated.…”

Section: Discussionmentioning

confidence: 99%

“…While active learning for anomaly detection is an area studied before, such as [18] and [19], user active schemes for threshold-setting is something, that to the best of our knowledge, has not been researched to any great extent before. The difference is that the active learning procedure changes the underlying model to better separate anomalous from non-anomalous points while an interactive thresholdsetting schema only changes aspects of an already trained model.…”

Section: Extended Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

An Interactive Threshold-Setting Procedure for Improved Multivariate Anomaly Detection in Time Series

Lundström,

O’Nils,

Qureshi

2023

IEEE Access

View full text Add to dashboard Cite

Anomaly detection in multivariate time series is valuable for many applications. In this context, unsupervised and semi-supervised deep learning methods that estimate how normal a new observation is have shown promising results on benchmark datasets. These methods are dependent on a threshold that determines which points should be regarded as anomalous and not be anomalous. However, finding the optimal threshold is not easy since no information about the ground truth is known in advance, which implies that there are limitations to automatic threshold-setting methods available today. An alternative is to utilize the expertise of users that can interact in a threshold-setting procedure, but for this to be practically feasible, the method needs to be both accurate and efficient in relation to the state-of-the-art automatic methods. Therefore, this study develops an interactive threshold-setting schema and examines to what extent it can outperform the current state-of-the-art automatic threshold-setting methods. The result of the study strongly indicates that the suggested method with little effort can provide higher accuracy than the automatic threshold-setting methods on a general basis. INDEX TERMSAnomaly detection, Anomaly scoring, Deep learning, Multivariate time series (MVTS).

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Extended Backgroundmentioning

confidence: 99%

An Interactive Threshold-Setting Procedure for Improved Multivariate Anomaly Detection in Time Series

Lundström,

O’Nils,

Qureshi

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Donut puts forward innovations such as M-ELBO and MCMC iteration based on VAE, which has excellent performance on periodic KPIs. Li et al [ 17 ] proposed ACVAE, a KPI anomaly detection algorithm through active learning and contrast-VAE-based detection models. The out-of-band information (including background information and feedback information) is integrated in VAE, so it has a better detection effect.…”

Section: Related Workmentioning

confidence: 99%

DA-LSTM-VAE: Dual-Stage Attention-Based LSTM-VAE for KPI Anomaly Detection

Zhao

Zhang

Shang

et al. 2022

Entropy

View full text Add to dashboard Cite

To ensure the normal operation of the system, the enterprise’s operations engineer will monitor the system through the KPI (key performance indicator). For example, web page visits, server memory utilization, etc. KPI anomaly detection is a core technology, which is of great significance for rapid fault detection and repair. This paper proposes a novel dual-stage attention-based LSTM-VAE (DA-LSTM-VAE) model for KPI anomaly detection. Firstly, in order to capture time correlation in KPI data, long–short-term memory (LSTM) units are used to replace traditional neurons in the variational autoencoder (VAE). Then, in order to improve the effect of KPI anomaly detection, an attention mechanism is introduced into the input stage of the encoder and decoder, respectively. During the input stage of the encoder, a time attention mechanism is adopted to assign different weights to different time points, which can adaptively select important input sequences to avoid the influence of noise in the data. During the input stage of the decoder, a feature attention mechanism is adopted to adaptively select important latent variable representations, which can capture the long-term dependence of time series better. In addition, this paper proposes an adaptive threshold method based on anomaly scores measured by reconstruction probability, which can minimize false positives and false negatives and avoid adjustment of the threshold manually. Experimental results in a public dataset show that the proposed method in this paper outperforms other baseline methods.

show abstract

Behavioral Authentication for Security and Safety

Wang,

Zhu

2024

Universal Behavior Computing for Security and Safety

View full text Add to dashboard Cite

Situation-Aware Multivariate Time Series Anomaly Detection Through Active Learning and Contrast VAE-Based Models in Large Distributed Systems

Cited by 20 publications

References 35 publications

An Interactive Threshold-Setting Procedure for Improved Multivariate Anomaly Detection in Time Series

An Interactive Threshold-Setting Procedure for Improved Multivariate Anomaly Detection in Time Series

DA-LSTM-VAE: Dual-Stage Attention-Based LSTM-VAE for KPI Anomaly Detection

Behavioral Authentication for Security and Safety

Contact Info

Product

Resources

About