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

Early recognition of abnormal rhythms in ECG signals is crucial formonitoring and diagnosing patients' cardiac conditions, increasing the successrate of the treatment. Classifying abnormal rhythms into exact categories isvery challenging due to the broad taxonomy of rhythms, noises and lack oflarge-scale real-world annotated data. Different from previous methods thatutilize hand-crafted features or learn features from the original signaldomain, we propose a novel ECG classification method by learning deeptime-frequency representation and progressive decision fusion at differenttemporal scales in an end-to-end manner. First, the ECG wave signal istransformed into the time-frequency domain by using the Short-Time FourierTransform. Next, several scale-specific deep convolutional neural networks aretrained on ECG samples of a specific length. Finally, a progressive onlinedecision fusion method is proposed to fuse decisions from the scale-specificmodels into a more accurate and stable one. Extensive experiments on bothsynthetic and real-world ECG datasets demonstrate the effectiveness andefficiency of the proposed method.

Deep Time-Frequency Representation and Progressive Decision Fusion for ECG Classification