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/

Zendy Plus

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

Zendy Tools

Zendy Open

We propose a new model based on the deconvolutional networks and SAXdiscretization to learn the representation for multivariate time series.Deconvolutional networks fully exploit the advantage the powerfulexpressiveness of deep neural networks in the manner of unsupervised learning.We design a network structure specifically to capture the cross-channelcorrelation with deconvolution, forcing the pooling operation to perform thedimension reduction along each position in the individual channel.Discretization based on Symbolic Aggregate Approximation is applied on thefeature vectors to further extract the bag of features. We show how thisrepresentation and bag of features helps on classification. A full comparisonwith the sequence distance based approach is provided to demonstrate theeffectiveness of our approach on the standard datasets. We further build theMarkov matrix from the discretized representation from the deconvolution tovisualize the time series as complex networks, which show more class-specificstatistical properties and clear structures with respect to different labels.

Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization