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

Sensor-based remote health monitoring is used in industrial, urban andhealthcare settings to monitor ongoing operation of equipment and human health.An important aim is to intervene early if anomalous events or adverse health isdetected. In the wild, these anomaly detection approaches are challenged bynoise, label scarcity, high dimensionality, explainability and wide variabilityin operating environments. The Contextual Matrix Profile (CMP) is aconfigurable 2-dimensional version of the Matrix Profile (MP) that uses thedistance matrix of all subsequences of a time series to discover patterns andanomalies. The CMP is shown to enhance the effectiveness of the MP and otherSOTA methods at detecting, visualising and interpreting true anomalies in noisyreal world data from different domains. It excels at zooming out andidentifying temporal patterns at configurable time scales. However, the CMPdoes not address cross-sensor information, and cannot scale to high dimensionaldata. We propose a novel, self-supervised graph-based approach for temporalanomaly detection that works on context graphs generated from the CMP distancematrix. The learned graph embeddings encode the anomalous nature of a timecontext. In addition, we evaluate other graph outlier algorithms for the sametask. Given our pipeline is modular, graph construction, generation of graphembeddings, and pattern recognition logic can all be chosen based on thespecific pattern detection application. We verified the effectiveness ofgraph-based anomaly detection and compared it with the CMP and 3 state-of-theart methods on two real-world healthcare datasets with different anomalies. Ourproposed method demonstrated better recall, alert rate and generalisability.

G-CMP: Graph-enhanced Contextual Matrix Profile for unsupervised anomaly detection in sensor-based remote health monitoring