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

This paper proposes a low-cost and highly accurate ECG-monitoring systemintended for personalized early arrhythmia detection for wearable mobilesensors. Earlier supervised approaches for personalized ECG monitoring requireboth abnormal and normal heartbeats for the training of the dedicatedclassifier. However, in a real-world scenario where the personalized algorithmis embedded in a wearable device, such training data is not available forhealthy people with no cardiac disorder history. In this study, (i) we proposea null space analysis on the healthy signal space obtained via sparsedictionary learning, and investigate how a simple null space projection oralternatively regularized least squares-based classification methods can reducethe computational complexity, without sacrificing the detection accuracy, whencompared to sparse representation-based classification. (ii) Then we introducea sparse representation-based domain adaptation technique in order to projectother existing users' abnormal and normal signals onto the new user's signalspace, enabling us to train the dedicated classifier without having anyabnormal heartbeat of the new user. Therefore, zero-shot learning can beachieved without the need for synthetic abnormal heartbeat generation. Anextensive set of experiments performed on the benchmark MIT-BIH ECG datasetshows that when this domain adaptation-based training data generator is usedwith a simple 1-D CNN classifier, the method outperforms the prior work by asignificant margin. (iii) Then, by combining (i) and (ii), we propose anensemble classifier that further improves the performance. This approach forzero-shot arrhythmia detection achieves an average accuracy level of 98.2% andan F1-Score of 92.8%. Finally, a personalized energy-efficient ECG monitoringscheme is proposed using the above-mentioned innovations.

A Personalized Zero-Shot ECG Arrhythmia Monitoring System: From Sparse  Representation Based Domain Adaption to Energy Efficient Abnormal Beat  Detection for Practical ECG Surveillance