Semisupervised anomaly detection of multivariate time series based on a variational autoencoder

Chen, Ningjiang; Tu, Huan; Duan, Xiaoyan; Hu, Liangqing; Guo, Chengxiang

doi:10.1007/s10489-022-03829-1

Cited by 20 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10) GTA [16]: GTA learns the relationship between sensors and combines graph convolution and a transformer to build a single-step time series prediction model; the prediction error is considered an anomaly score. 11) DVGCRN [33]: DVGCRN combines a probabilistic generative network with a variational graph convolutional recurrent network to model both spatial and temporal fine-grained correlations and considers both reconstruction-based and forecasting-based losses to optimize MTS representations. 3) Implementation Details: The proposed method was implemented based on PyTorch 1.9.0 with CUDA 10.2.…”

Section: Methodsmentioning

confidence: 99%

“…These methods are specialized for feature engineering in the prediction of the next timestamp. Reconstruction-based and prediction-based methods have their own advantages, but few methods consider joint reconstruction and prediction tasks to simultaneously characterize multivariate time series data [32], [33]. In addition to reconstructionbased and prediction-based anomaly detection, many novel anomaly detection methods have emerged, including base classification anomaly detection [34] and contrast learningbased anomaly detection [35].…”

Section: B Multivariate Time Series Anomaly Detectionmentioning

confidence: 99%

“…GTA [16] uses a transformer-based architecture to model temporal correlation and proposes a self-learning graph structure to capture bidirectional links between sensors. DVGCRN [33] designs adaptive variational graph convolutional recurrent networks to model spatial and temporal finegrained correlations and capture multilevel information at different layers.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT

Chen

Zhang

et al. 2022

IEEE Internet Things J.

265

View full text Add to dashboard Cite

Multivariate time series anomaly detection (MTAD) plays a vital role in a wide variety of real-world application domains. Over the past few years, MTAD has attracted rapidly increasing attention from both academia and industry. Many deep learning and graph learning models have been developed for effective anomaly detection in multivariate time series data, which enable advanced applications such as smart surveillance and risk management with unprecedented capabilities. Nevertheless, MTAD is facing critical challenges deriving from the dependencies among sensors and variables, which often change over time. To address this issue, we propose a coupled attentionbased neural network framework (CAN) for anomaly detection in multivariate time series data featuring dynamic variable relationships. We combine adaptive graph learning methods with graph attention to generate a global-local graph that can represent both global correlations and dynamic local correlations among sensors. To capture inter-sensor relationships and temporal dependencies, a convolutional neural network based on the global-local graph is integrated with a temporal self-attention module to construct a coupled attention module. In addition, we develop a multilevel encoder-decoder architecture that accommodates reconstruction and prediction tasks to better characterize multivariate time series data. Extensive experiments on real-world datasets have been conducted to evaluate the performance of the proposed CAN approach, and the results show that CAN significantly outperforms state-of-the-art baselines.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: B Multivariate Time Series Anomaly Detectionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT

Chen

Zhang

et al. 2022

IEEE Internet Things J.

265

View full text Add to dashboard Cite

show abstract

“…Consequently, anomalies can be detected using the reconstruction error. A popular technique that is used to reconstruct the input is through the use of autoencoders [27].…”

Section: Deep Autoencoder-based Anomaly Detectionmentioning

confidence: 99%

“…Therefore, the output dimension is similar to the input one [24]. Different types of deep autoencoder, such as the LSTM autoencoder, convolutional autoencoder, variational autoencoder, and LSTM variational autoencoder, can be found in the literature [27]. Compared to statistical models, an important reason for the use of the deep learning method in this contribution is the effectiveness and simplicity of deep-learning-based methods.…”

Section: Introductionmentioning

confidence: 99%

Using Deep Learning to Detect Anomalies in On-Load Tap Changer Based on Vibro-Acoustic Signal Features

Dabaghi-Zarandi,

Behjat,

Gauvin

et al. 2024

Energies

View full text Add to dashboard Cite

An On-Load Tap Changer (OLTC) that regulates transformer voltage is one of the most important and strategic components of a transformer. Detecting faults in this component at early stages is, therefore, crucial to prevent transformer outages. In recent years, Hydro Quebec initiated a project to monitor the OLTC’s condition in power transformers using vibro-acoustic signals. A data acquisition system has been installed on real OLTCs, which has been continuously measuring their generated vibration signal envelopes over the past few years. In this work, the multivariate deep autoencoder, a reconstruction-based method for unsupervised anomaly detection, is employed to analyze the vibration signal envelopes generated by the OLTC and detect abnormal behaviors. The model is trained using a dataset obtained from the normal operating conditions of the transformer to learn patterns. Subsequently, kernel density estimation (KDE), a nonparametric method, is used to fit the reconstruction errors (regarding normal data) obtained from the trained model and to calculate the anomaly scores, along with the static threshold. Finally, anomalies are detected using a deep autoencoder, KDE, and a dynamic threshold. It should be noted that the input variables responsible for anomalies are also identified based on the value of the reconstruction error and standard deviation. The proposed method is applied to six different real datasets to detect anomalies using two distinct approaches: individually on each dataset and by comparing all six datasets. The results indicate that the proposed method can detect anomalies at an early stage. Also, three alarms, including ignorable anomalies, long-term changes, and significant alterations, were introduced to quantify the OLTC’s condition.

show abstract

MADMM: microservice system anomaly detection via multi-modal data and multi-feature extraction

Wang,

Zhang,

Cao

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

Semisupervised anomaly detection of multivariate time series based on a variational autoencoder

Cited by 20 publications

References 19 publications

Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT

Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT

Using Deep Learning to Detect Anomalies in On-Load Tap Changer Based on Vibro-Acoustic Signal Features

MADMM: microservice system anomaly detection via multi-modal data and multi-feature extraction

Contact Info

Product

Resources

About