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

Physiological signals are high-dimensional time series of great practicalvalues in medical and healthcare applications. However, previous works on itsclassification fail to obtain promising results due to the intractable datacharacteristics and the severe label sparsity issues. In this paper, we try toaddress these challenges by proposing a more effective and interpretable schemetailored for the physiological signal classification task. Specifically, weexploit the time series shapelets to extract prominent local patterns andperform interpretable sequence discretization to distill the whole-seriesinformation. By doing so, the long and continuous raw signals are compressedinto short and discrete token sequences, where both local patterns and globalcontexts are well preserved. Moreover, to alleviate the label sparsity issue, amulti-scale transformation strategy is adaptively designed to augment data anda cross-scale contrastive learning mechanism is accordingly devised to guidethe model training. We name our method as ShapeWordNet and conduct extensiveexperiments on three real-world datasets to investigate its effectiveness.Comparative results show that our proposed scheme remarkably outperforms fourcategories of cutting-edge approaches. Visualization analysis further witnessesthe good interpretability of the sequence discretization idea based onshapelets.

ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classification