Fetal ECG extraction using multi-layer perceptron neural networks with Bayesian approach

S. Mojtaba Golzan, Farzaneh Hakimpour, Mohammad Mikaili, Alireza Toolou

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

2 Citations (Scopus)

Abstract

In this paper, we investigate the application of neural networks to the problem of extracting fetal ECG from Maternal ECG early in pregnancy. The proposed extractor consists of a segmentation, feature extraction and Classification stage. For the feature extraction stage, coefficients of the Wavelet Transform (WT), real and imaginary parts of the Fast Fourier Transform and raw ECG data recorded from the abdomen of a pregnant woman were all found to be well-suited to FECG classification. Principal Component Analysis was used to reduce the dimensionality of the features. For the classification stage, Multi-Layer Perceptron neural networks were implemented according to Maximum Likelihood and Bayesian Learning formulations. The latter was found to make better use of training data and consequently produced better trained neural networks. Rejection thresholds of 0.9 were applied to the network output as a doubt level in order to ensure that only reliable classification decisions are made. A maximum classifier accuracy of 94.86% was achieved with 23.42% of patterns not being classified. Bayesian moderated outputs could not improve on these classification predictions significantly enough to warrant their added computational Overhead.

Original languageEnglish
Title of host publication4th European Conference of the International Federation for Medical and Biological Engineering - ECIFMBE 2008
Place of PublicationHeidelberg
PublisherSpringer, Springer Nature
Pages1378-1385
Number of pages8
Volume22
ISBN (Electronic)9783540892083
ISBN (Print)9783540892076
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event4th European Conference of the International Federation for Medical and Biological Engineering, ECIFMBE 2008 - Antwerp, Belgium
Duration: 23 Nov 200827 Nov 2008

Other

Other4th European Conference of the International Federation for Medical and Biological Engineering, ECIFMBE 2008
CountryBelgium
CityAntwerp
Period23/11/0827/11/08

    Fingerprint

Keywords

  • Bayesian Formulation
  • Fetal electrocardiogram
  • Maternal electrocardiogram
  • Maximum Likelihood Formulation
  • Neural Networks

Cite this

Golzan, S. M., Hakimpour, F., Mikaili, M., & Toolou, A. (2008). Fetal ECG extraction using multi-layer perceptron neural networks with Bayesian approach. In 4th European Conference of the International Federation for Medical and Biological Engineering - ECIFMBE 2008 (Vol. 22, pp. 1378-1385). Heidelberg: Springer, Springer Nature. https://doi.org/10.1007/978-3-540-89208-3_327