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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

1, A. Shachikov, V. Shelofast, A. Shulyak University of Lorraine-INRIA-CNRS F-54506 Nancy, France; 2) National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine MODIFICATION OF SELECTION PROCEDURES CYCLIC CHARACTERISTICS OF BIOMEDICAL SIGNALS FOR THEIR RECOGNITION A formal statistical selection of the most informative features for usage during recognition is a productive direction of improving the quality of signal recognition in supervised learning systems. The article reveals the formation of modifications of feature selecting procedures under the correlation approach to signal recognition and the possibility of finding among these procedures ones that most adequately provide the decision regarding the feature set in accordance with the peculiarities of these signals and the composition of the software tools used. The studies are illustrated by examples of signal processing for the problem of recognition of QRS complexes of two types in the one-lead record of the patient's electrocardiogram taken as a training sample from the database. The presented procedures allow to reveal and realize the reserves of quality improvement of signal recognition by selecting the rational feature set for further usage.