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

Time series motifs play an important role in the time series analysis. Themotif-based time series clustering is used for the discovery of higher-orderpatterns or structures in time series data. Inspired by the convolutionalneural network (CNN) classifier based on the image representations of timeseries, motif difference field (MDF) is proposed. Compared to other imagerepresentations of time series, MDF is simple and easy to construct. With theFully Convolution Network (FCN) as the classifier, MDF demonstrates thesuperior performance on the UCR time series dataset in benchmark with othertime series classification methods. It is interesting to find that the triadictime series motifs give the best result in the test. Due to the motifclustering reflected in MDF, the significant motifs are detected with the helpof the Gradient-weighted Class Activation Mapping (Grad-CAM). The areas in MDFwith high weight in Grad-CAM have a high contribution from the significantmotifs with the desired ordinal patterns associated with the signature patternsin time series. However, the signature patterns cannot be identified with theneural network classifiers directly based on the time series.

Motif Difference Field: A Simple and Effective Image Representation of Time Series for Classification