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

This paper introduces a hybrid attention and autoencoder (AE) model forunsupervised online anomaly detection in time series. The autoencoder captureslocal structural patterns in short embeddings, while the attention model learnslong-term features, facilitating parallel computing with positional encoding.Unique in its approach, our proposed hybrid model combines attention andautoencoder for the first time in time series anomaly detection. It employs anattention-based mechanism, akin to the deep transformer model, with keyarchitectural modifications for predicting the next time step window in theautoencoder's latent space. The model utilizes a threshold from the validationdataset for anomaly detection and introduces an alternative method based onanalyzing the first statistical moment of error, improving accuracy withoutdependence on a validation dataset. Evaluation on diverse real-world benchmarkdatasets and comparing with other well-established models, confirms theeffectiveness of our proposed model in anomaly detection.

Attention and Autoencoder Hybrid Model for Unsupervised Online Anomaly Detection