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

Learning compressed representations of multivariate time series (MTS)facilitates data analysis in the presence of noise and redundant information,and for a large number of variates and time steps. However, classicaldimensionality reduction approaches are designed for vectorial data and cannotdeal explicitly with missing values. In this work, we propose a novelautoencoder architecture based on recurrent neural networks to generatecompressed representations of MTS. The proposed model can process inputscharacterized by variable lengths and it is specifically designed to handlemissing data. Our autoencoder learns fixed-length vectorial representations,whose pairwise similarities are aligned to a kernel function that operates ininput space and that handles missing values. This allows to learn goodrepresentations, even in the presence of a significant amount of missing data.To show the effectiveness of the proposed approach, we evaluate the quality ofthe learned representations in several classification tasks, including thoseinvolving medical data, and we compare to other methods for dimensionalityreduction. Successively, we design two frameworks based on the proposedarchitecture: one for imputing missing data and another for one-classclassification. Finally, we analyze under what circumstances an autoencoderwith recurrent layers can learn better compressed representations of MTS thanfeed-forward architectures.

Learning representations for multivariate time series with missing data using Temporal Kernelized Autoencoders