Neurodynamic non-invasive fetal electrocardiogram extraction

Dmitriy Devyatykh, Olga Gerget

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Fetal electrocardiography in contrary to adult is not that well represented in publications, yet circulatory system of the fetus is probably the most valuable and crucial biological infrastructure. Fetal heart ratio, form of QRS-wave and dynamics of cardiovascular system activity allow estimating fetus state, maturity, possibilities of heart abnormality occasion. This information can be received with guaranteed accuracy through Doppler-ultrasound procedure, however duration of such kind of monitoring is limited. Fetal electrocardiogram is an obvious source of information about fetal heart activity. However, because of low signal-to-noise ratio and prevailing of maternal component, non-invasive ways of acquiring this signal do not guarantee absolute accuracy. Problems of non-invasive electrocardiography demand complex mathematical approaches because maternal and fetal R-peaks overlap in time and frequency domains and have similar morphological structure of heart waves. In this paper we propose approach for extracting fetal electrocardiography from abdominal signal, which is based on dynamic neural network. The common problem for both dynamic and deep learning is caused by linearity of backpropagation and thus vanishing or exploding of gradients occurs. We proposed resilient propagation through time approach that unites training based on sign of derivative and parallel unfolding. We compared developed algorithm with blind source separation through independent component analysis and noted several important advantages that our model delivers - accuracy does not depend on: length of signal; amount of independent channels.

Original languageEnglish
Title of host publicationIISA 2016 - 7th International Conference on Information, Intelligence, Systems and Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509034291
DOIs
Publication statusPublished - 14 Dec 2016
Event7th International Conference on Information, Intelligence, Systems and Applications, IISA 2016 - Chalkidiki, Greece
Duration: 13 Jul 201615 Jul 2016

Publication series

NameIISA 2016 - 7th International Conference on Information, Intelligence, Systems and Applications

Conference

Conference7th International Conference on Information, Intelligence, Systems and Applications, IISA 2016
CountryGreece
CityChalkidiki
Period13.7.1615.7.16

Keywords

  • blind source separation
  • dynamic neural network
  • fetal electrocardiogram
  • resilient propagation
  • vanishing gradient

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Artificial Intelligence
  • Social Sciences (miscellaneous)

Fingerprint Dive into the research topics of 'Neurodynamic non-invasive fetal electrocardiogram extraction'. Together they form a unique fingerprint.

Cite this