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

Detecting anomalies in large complex systems is a critical and challengingtask. The difficulties arise from several aspects. First, collecting groundtruth labels or prior knowledge for anomalies is hard in real-world systems,which often lead to limited or no anomaly labels in the dataset. Second,anomalies in large systems usually occur in a collective manner due to theunderlying dependency structure among devices or sensors. Lastly, real-timeanomaly detection for high-dimensional data requires efficient algorithms thatare capable of handling different types of data (i.e. continuous and discrete).We propose a correlation structure-based collective anomaly detection (CSCAD)model for high-dimensional anomaly detection problem in large systems, which isalso generalizable to semi-supervised or supervised settings. Our frameworkutilize graph convolutional network combining a variational autoencoder tojointly exploit the feature space correlation and reconstruction deficiency ofsamples to perform anomaly detection. We propose an extended mutual information(EMI) metric to mine the internal correlation structure among different datafeatures, which enhances the data reconstruction capability of CSCAD. Thereconstruction loss and latent standard deviation vector of a sample obtainedfrom reconstruction network can be perceived as two natural anomalous degreemeasures. An anomaly discriminating network can then be trained using lowanomalous degree samples as positive samples, and high anomalous degree samplesas negative samples. Experimental results on five public datasets demonstratethat our approach consistently outperforms all the competing baselines.

CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System