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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Robust anomaly detection is a requirement for monitoring complex modernsystems with applications such as cyber-security, fraud prevention, andmaintenance. These systems generate multiple correlated time series that arehighly seasonal and noisy. This paper presents a novel unsupervised deeplearning architecture for multivariate time series anomaly detection, calledRobust Seasonal Multivariate Generative Adversarial Network (RSM-GAN). Itextends recent advancements in GANs with adoption of convolutional-LSTM layersand an attention mechanism to produce state-of-the-art performance. We conductextensive experiments to demonstrate the strength of our architecture inadjusting for complex seasonality patterns and handling severe levels oftraining data contamination. We also propose a novel anomaly score assignmentand causal inference framework. We compare RSM-GAN with existing classical anddeep-learning based anomaly detection models, and the results show that ourarchitecture is associated with the lowest false positive rate and improvesprecision by 30% and 16% in real-world and synthetic data, respectively.Furthermore, we report the superiority of RSM-GAN regarding accurate root causeidentification and NAB scores in all data settings.

RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series