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

Asynchronous Time Series is a multivariate time series where all the channelsare observed asynchronously-independently, making the time series extremelysparse when aligning them. We often observe this effect in applications withcomplex observation processes, such as health care, climate science, andastronomy, to name a few. Because of the asynchronous nature, they pose asignificant challenge to deep learning architectures, which presume that thetime series presented to them are regularly sampled, fully observed, andaligned with respect to time. This paper proposes a novel framework, that wecall Deep Convolutional Set Functions (DCSF), which is highly scalable andmemory efficient, for the asynchronous time series classification task. Withthe recent advancements in deep set learning architectures, we introduce amodel that is invariant to the order in which time series' channels arepresented to it. We explore convolutional neural networks, which are wellresearched for the closely related problem-classification of regularly sampledand fully observed time series, for encoding the set elements. We evaluate DCSFfor AsTS classification, and online (per time point) AsTS classification. Ourextensive experiments on multiple real-world and synthetic datasets verify thatthe suggested model performs substantially better than a range ofstate-of-the-art models in terms of accuracy and run time.

DCSF: Deep Convolutional Set Functions for Classification of Asynchronous Time Series