English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Mechanical defects in real situations affect observation values and causeabnormalities in multivariate time series, such as sensor values or networkdata. To perceive abnormalities in such data, it is crucial to understand thetemporal context and interrelation between variables simultaneously. Theanomaly detection task for time series, especially for unlabeled data, has beena challenging problem, and we address it by applying a suitable datadegradation scheme to self-supervised model training. We define four types ofsynthetic outliers and propose the degradation scheme in which a portion ofinput data is replaced with one of the synthetic outliers. Inspired by theself-attention mechanism, we design a Transformer-based architecture torecognize the temporal context and detect unnatural sequences with highefficiency. Our model converts multivariate data points into temporalrepresentations with relative position bias and yields anomaly scores fromthese representations. Our method, AnomalyBERT, shows a great capability ofdetecting anomalies contained in complex time series and surpasses previousstate-of-the-art methods on five real-world benchmarks. Our code is availableat https://github.com/Jhryu30/AnomalyBERT.

AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Scheme