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

Large network logs, recording multivariate time series generated fromheterogeneous devices and sensors in a network, can often reveal importantinformation about abnormal activities, such as network intrusions and devicemalfunctions. Existing machine learning methods for anomaly detection onmultivariate time series typically assume that 1) normal sequences would haveconsistent behavior for training unsupervised models, or 2) require a large setof labeled normal and abnormal sequences for supervised models. However, inpractice, normal network activities can demonstrate significantly varyingsequence patterns (e.g., before and after rerouting partial network traffic).Also, the recorded abnormal events can be sparse. This paper presents a novelsemi-supervised method that efficiently captures dependencies between networktime series and across time points to generate meaningful representations ofnetwork activities for predicting abnormal events. The method can use thelimited labeled data to explicitly learn separable embedding space for normaland abnormal samples and effectively leverage unlabeled data to handle trainingdata scarcity. The experiments demonstrate that our approach significantlyoutperformed state-of-the-art approaches for event detection on a largereal-world network log.

A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data