Decomposed Transformer with Frequency Attention for Multivariate Time Series Anomaly Detection

Qin, Shuxin; Zhu, Jing; Wang, Dan; Ou, Liang; Gui, Hongxin; Tao, Gaofeng

doi:10.1109/bigdata55660.2022.10021063

Cited by 5 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each generator consists of an inflated convolutional neural network and a transform module to obtain both fine-grained and coarse-grained information of the time series. Qin, S. et al [27] proposed a novel method for time series anomaly detection based on transformer and signal decomposition.…”

Section: The Methods For Spatial-temporal Correlation Fusionmentioning

confidence: 99%

DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion

Yang

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

The detection of anomalies in multivariate time-series data is becoming increasingly important in the automated and continuous monitoring of complex systems and devices due to the rapid increase in data volume and dimension. To address this challenge, we present a multivariate time-series anomaly detection model based on a dual-channel feature extraction module. The module focuses on the spatial and time features of the multivariate data using spatial short-time Fourier transform (STFT) and a graph attention network, respectively. The two features are then fused to significantly improve the model’s anomaly detection performance. In addition, the model incorporates the Huber loss function to enhance its robustness. A comparative study of the proposed model with existing state-of-the-art ones was presented to prove the effectiveness of the proposed model on three public datasets. Furthermore, by using in shield tunneling applications, we verify the effectiveness and practicality of the model.

show abstract

Section: The Methods For Spatial-temporal Correlation Fusionmentioning

confidence: 99%

DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion

Yang

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Two different views of the same timestamp t are positive sample pairs; otherwise, they are negative sample pairs, as shown in Eq. (9).…”

Section: Joint Optimizationmentioning

confidence: 99%

“…Normally, RNN is always used to deal with time series-related tasks. RNN-based models [7,8] often fail to model long-term dependencies and suffer from poor computational efficiency [9,10]. The model [2] constructed with AE has the advantage of low overhead, which makes up for the defect of low computational efficiency [11].…”

Section: Introductionmentioning

confidence: 99%

A Memory-Guided Anomaly Detection Model with Contrastive Learning for Multivariate Time Series

Zhang,

He,

et al. 2023

CMC

View full text Add to dashboard Cite

Some reconstruction-based anomaly detection models in multivariate time series have brought impressive performance advancements but suffer from weak generalization ability and a lack of anomaly identification. These limitations can result in the misjudgment of models, leading to a degradation in overall detection performance. This paper proposes a novel transformer-like anomaly detection model adopting a contrastive learning module and a memory block (CLME) to overcome the above limitations. The contrastive learning module tailored for time series data can learn the contextual relationships to generate temporal fine-grained representations. The memory block can record normal patterns of these representations through the utilization of attention-based addressing and reintegration mechanisms. These two modules together effectively alleviate the problem of generalization. Furthermore, this paper introduces a fusion anomaly detection strategy that comprehensively takes into account the residual and feature spaces. Such a strategy can enlarge the discrepancies between normal and abnormal data, which is more conducive to anomaly identification. The proposed CLME model not only efficiently enhances the generalization performance but also improves the ability of anomaly detection. To validate the efficacy of the proposed approach, extensive experiments are conducted on well-established benchmark datasets, including SWaT, PSM, WADI, and MSL. The results demonstrate outstanding performance, with F1 scores of 90.58%, 94.83%, 91.58%, and 91.75%, respectively. These findings affirm the superiority of the CLME model over existing stateof-the-art anomaly detection methodologies in terms of its ability to detect anomalies within complex datasets accurately.

show abstract

Unravel Anomalies: an End-to-End Seasonal-Trend Decomposition Approach for Time Series Anomaly Detection

Zhang,

Wang,

Ding

et al. 2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Decomposed Transformer with Frequency Attention for Multivariate Time Series Anomaly Detection

Cited by 5 publications

References 29 publications

DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion

DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion

A Memory-Guided Anomaly Detection Model with Contrastive Learning for Multivariate Time Series

Unravel Anomalies: an End-to-End Seasonal-Trend Decomposition Approach for Time Series Anomaly Detection

Contact Info

Product

Resources

About