A Prediction-Augmented AutoEncoder for Multivariate Time Series Anomaly Detection

Gong, Sawenbo; Wu, Zhihao; Liu, Yunxiao; Lin, Youfang; Wang, Jing

doi:10.1007/978-3-030-92185-9_56

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We additionally compared our framework with other traditional machine learning models and more recent deep learning approaches. Specifically, we have integrated both classic deep learning models such as LSTM and VAE and a GAN-based model of USAD [25], as well as anomaly detection models based on Transformers such as Anomaly Transformer [26] and MEMTO [27]. These methods primarily rely on the reconstruction error between original input samples and their reconstructed counterparts for anomaly detection but showed lower performance in hypotension prediction.…”

Section: Comparison With Other Approachesmentioning

confidence: 99%

Frequency Domain Deep Learning With Non-Invasive Features for Intraoperative Hypotension Prediction

Moon,

Lee,

Lee

et al. 2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Background: Intraoperative hypotension can lead to postoperative organ dysfunction. Previous studies primarily used invasive arterial pressure as the key biosignal for the detection of hypotension. However, these studies had limitations in incorporating different biosignal modalities and utilizing the periodic nature of biosignals. To address these limitations, we utilized frequency-domain information, which provides key insights that time-domain analysis cannot provide, as revealed by recent advances in deep learning. With the frequency-domain information, we propose a deep-learning approach that integrates multiple biosignal modalities. Methods: We used the discrete Fourier transform technique, to extract frequency information from biosignal data, which we then combined with the original time-domain data as input for our deep learning model. To improve the interpretability of our results, we incorporated recent interpretable modules for deep-learning models into our analysis. Results: We constructed 75,994 segments from the data of 3,226 patients to predict hypotension during surgery. Our proposed frequency-domain deep-learning model outperformed conventional approaches that rely solely on time-domain information. Notably, our model achieved a greater increase in AUROC performance than the time-domain deep learning models when trained on non-invasive biosignal data only (AUROC 0.898 [95%

show abstract

Section: Comparison With Other Approachesmentioning

confidence: 99%

Frequency Domain Deep Learning With Non-Invasive Features for Intraoperative Hypotension Prediction

Moon,

Lee,

Lee

et al. 2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

Can Industrial Intrusion Detection Be SIMPLE?

Wolsing

Thiemt

Sloun

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Online Time-series Anomaly Detection: A Survey of Modern Model-based Approaches

Correia

Goos

Kononova

et al. 2022

Preprint

View full text Add to dashboard Cite

This survey provides an extensive overview of the state-of-the-art model-based online semi-supervised and unsupervised anomaly detection algorithms used on multivariate time series. It also outlines the most popular benchmark datasets used in literature, as well as a novel taxonomy where a distinction between online and offline, and training and inference is made. To achieve this, almost 50 peer-reviewed publications are surveyed and categorised into different model families to paint a clear picture of the anomaly detection landscape for the reader. Then, where possible, a comparison of the anomaly detection performance of the surveyed approaches is provided and the key research gaps are highlighted. It is concluded that few approaches propose any enhancements that involve the user feedback. In addition to that, transformer-based models seem to have found little application in anomaly detection so far, though this is most likely due to the novelty of the model type, not necessarily due to the lack of potential. Moreover, there is no standard benchmark procedure to assess anomaly detection performance. A variety of different datasets and evaluation metrics used for evaluation are used hence it is difficult to draw conclusions from comparisons between papers. Lastly, the rarity of approaches trained and inferred in an online manner is also pointed out, possibly explained by the lower performance compared to offline trained approaches.

show abstract

A Prediction-Augmented AutoEncoder for Multivariate Time Series Anomaly Detection

Cited by 3 publications

References 13 publications

Frequency Domain Deep Learning With Non-Invasive Features for Intraoperative Hypotension Prediction

Frequency Domain Deep Learning With Non-Invasive Features for Intraoperative Hypotension Prediction

Can Industrial Intrusion Detection Be SIMPLE?

Online Time-series Anomaly Detection: A Survey of Modern Model-based Approaches

Contact Info

Product

Resources

About