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

In this work we propose an autoencoder based framework for simultaneousreconstruction and classification of biomedical signals. Previously these twotasks, reconstruction and classification were treated as separate problems.This is the first work to propose a combined framework to address the issue ina holistic fashion. Reconstruction techniques for biomedical signals fortele-monitoring are largely based on compressed sensing (CS) based method,these are designed techniques where the reconstruction formulation is based onsome assumption regarding the signal. In this work, we propose a new paradigmfor reconstruction we learn to reconstruct. An autoencoder can be trained forthe same. But since the final goal is to analyze classify the signal we learn alinear classification map inside the autoencoder. The ensuing optimizationproblem is solved using the Split Bregman technique. Experiments have beencarried out on reconstruction and classification of ECG arrhythmiaclassification and EEG seizure classification signals. Our proposed tool iscapable of operating in a semi-supervised fashion. We show that our proposedmethod is better and more than an order magnitude faster in reconstruction thanCS based methods; it is capable of real-time operation. Our method is alsobetter than recently proposed classification methods. Significance: This is thefirst work offering an alternative to CS based reconstruction. It also showsthat representation learning can yield better results than hand-craftedfeatures for signal analysis.

Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals