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

Nowadays, multivariate time series data are increasingly collected in variousreal world systems, e.g., power plants, wearable devices, etc. Anomalydetection and diagnosis in multivariate time series refer to identifyingabnormal status in certain time steps and pinpointing the root causes. Buildingsuch a system, however, is challenging since it not only requires to capturethe temporal dependency in each time series, but also need encode theinter-correlations between different pairs of time series. In addition, thesystem should be robust to noise and provide operators with different levels ofanomaly scores based upon the severity of different incidents. Despite the factthat a number of unsupervised anomaly detection algorithms have been developed,few of them can jointly address these challenges. In this paper, we propose aMulti-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to performanomaly detection and diagnosis in multivariate time series data. Specifically,MSCRED first constructs multi-scale (resolution) signature matrices tocharacterize multiple levels of the system statuses in different time steps.Subsequently, given the signature matrices, a convolutional encoder is employedto encode the inter-sensor (time series) correlations and an attention basedConvolutional Long-Short Term Memory (ConvLSTM) network is developed to capturethe temporal patterns. Finally, based upon the feature maps which encode theinter-sensor correlations and temporal information, a convolutional decoder isused to reconstruct the input signature matrices and the residual signaturematrices are further utilized to detect and diagnose anomalies. Extensiveempirical studies based on a synthetic dataset and a real power plant datasetdemonstrate that MSCRED can outperform state-of-the-art baseline methods.

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data