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

Deep learning has seen increasing applications in time series in recentyears. For time series anomaly detection scenarios, such as in finance,Internet of Things, data center operations, etc., time series usually show veryflexible baselines depending on various external factors. Anomalies unveilthemselves by lying far away from the baseline. However, the detection is notalways easy due to some challenges including baseline shifting, lacking oflabels, noise interference, real time detection in streaming data, resultinterpretability, etc. In this paper, we develop a novel deep architecture toproperly extract the baseline from time series, namely Deep Baseline Network(DBLN). By using this deep network, we can easily locate the baseline positionand then provide reliable and interpretable anomaly detection result. Empiricalevaluation on both synthetic and public real-world datasets shows that ourpurely unsupervised algorithm achieves superior performance compared withstate-of-art methods and has good practical applications.

Deep Baseline Network for Time Series Modeling and Anomaly Detection