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

In this work we search for best practices in pre-processing ofElectrocardiogram (ECG) signals in order to train better classifiers for thediagnosis of heart conditions. State of the art machine learning algorithmshave achieved remarkable results in classification of some heart conditionsusing ECG data, yet there appears to be no consensus on pre-processing bestpractices. Is this lack of consensus due to different conditions andarchitectures requiring different processing steps for optimal performance? Isit possible that state of the art deep-learning models have renderedpre-processing unnecessary? In this work we apply down-sampling, normalization,and filtering functions to 3 different multi-label ECG datasets and measuretheir effects on 3 different high-performing time-series classifiers. We findthat sampling rates as low as 50Hz can yield comparable results to the commonlyused 500Hz. This is significant as smaller sampling rates will result insmaller datasets and models, which require less time and resources to train.Additionally, despite their common usage, we found min-max normalization to beslightly detrimental overall, and band-passing to make no measurabledifference. We found the blind approach to pre-processing of ECGs formulti-label classification to be ineffective, with the exception of sample ratereduction which reliably reduces computational resources, but does not increaseaccuracy.

Exploring Best Practices for ECG Pre-Processing in Machine Learning