The University of Southampton
University of Southampton Institutional Repository

Source separation of foetal heart sounds and maternal activity from single-channel phongrams: A temporal independent component analysis approach

Source separation of foetal heart sounds and maternal activity from single-channel phongrams: A temporal independent component analysis approach
Source separation of foetal heart sounds and maternal activity from single-channel phongrams: A temporal independent component analysis approach
We propose a method for extracting sources from noisy single-channel abdominal phonograms such as foetal heart sounds (FHS) and maternal activity. Three single-channel abdominal phonograms, between 3 and 5 minutes in length, were used. The recordings were obtained from pregnant women with foetal gestation ages between 36 and 40 weeks using a piezoelectric transducer. The abdominal ECG was recorded simultaneously using a sampling frequency of 500 Hz. These phonograms are processed as follows: first, the single-channel phonogram is projected into a higher dimension by constructing and appropriate matrix of delays. Next, multiple independent components are calculated using a standard implementation of Independent Component Analysis. After that, these components are projected back onto the measurement space to be finally classified (according to their spectral similarity) to recover the sources contained in the phonogram. Results show successful extraction of FHS, maternal activity, line noise and some unidentified sources (probably speech and/or digestive activity). Moreover, even though it is virtually impossible to distinguish the FHS in the phonograms, their extraction looks quite good in two subjects, where S1 and S2 are evident while only S1 is visible in the third subject. The method also extracted maternal activity, composed of the respiration and/or the pulse wave sources (present from time to time with an unpredictable contribution), in all subjects. This extraction was not necessarily as separate sources such as respiration and pulse wave, but importantly isolated from the FHS. Considering the foetal and maternal activities in more detail, it is important to point out the high performance of the method extracting them as separate sources. Thus, this extraction is especially significant because the maternal pulse wave may overlap the FHS in the same way the maternal QRS overlaps the foetal QRS in the abdominal ECG. The most outstanding factor is that this separation is achieved by using a single-channel method. So, this single-channel approach extracts physiological sources from the abdominal phonogram, and we believe it will be useful for surveillance, not only on foetal well-being, but also for maternal condition. (Abstract Control Number: 238)
Jimenez-Gonzalez, A.
23899879-fed0-4ed1-bba4-181cc75c30fd
James, C.J.
b3733b1f-a6a1-4c9b-b75c-6191d4142e52
Jimenez-Gonzalez, A.
23899879-fed0-4ed1-bba4-181cc75c30fd
James, C.J.
b3733b1f-a6a1-4c9b-b75c-6191d4142e52

Jimenez-Gonzalez, A. and James, C.J. (2008) Source separation of foetal heart sounds and maternal activity from single-channel phongrams: A temporal independent component analysis approach. 35th Annual Conference of Computers in Cardiology, Bologna, Italy. 13 - 16 Sep 2008.

Record type: Conference or Workshop Item (Paper)

Abstract

We propose a method for extracting sources from noisy single-channel abdominal phonograms such as foetal heart sounds (FHS) and maternal activity. Three single-channel abdominal phonograms, between 3 and 5 minutes in length, were used. The recordings were obtained from pregnant women with foetal gestation ages between 36 and 40 weeks using a piezoelectric transducer. The abdominal ECG was recorded simultaneously using a sampling frequency of 500 Hz. These phonograms are processed as follows: first, the single-channel phonogram is projected into a higher dimension by constructing and appropriate matrix of delays. Next, multiple independent components are calculated using a standard implementation of Independent Component Analysis. After that, these components are projected back onto the measurement space to be finally classified (according to their spectral similarity) to recover the sources contained in the phonogram. Results show successful extraction of FHS, maternal activity, line noise and some unidentified sources (probably speech and/or digestive activity). Moreover, even though it is virtually impossible to distinguish the FHS in the phonograms, their extraction looks quite good in two subjects, where S1 and S2 are evident while only S1 is visible in the third subject. The method also extracted maternal activity, composed of the respiration and/or the pulse wave sources (present from time to time with an unpredictable contribution), in all subjects. This extraction was not necessarily as separate sources such as respiration and pulse wave, but importantly isolated from the FHS. Considering the foetal and maternal activities in more detail, it is important to point out the high performance of the method extracting them as separate sources. Thus, this extraction is especially significant because the maternal pulse wave may overlap the FHS in the same way the maternal QRS overlaps the foetal QRS in the abdominal ECG. The most outstanding factor is that this separation is achieved by using a single-channel method. So, this single-channel approach extracts physiological sources from the abdominal phonogram, and we believe it will be useful for surveillance, not only on foetal well-being, but also for maternal condition. (Abstract Control Number: 238)

This record has no associated files available for download.

More information

Published date: September 2008
Additional Information: SB4: Blood Flow and Pressure Session SB4.5 Wednesday, September 17, 2008, 10:15
Venue - Dates: 35th Annual Conference of Computers in Cardiology, Bologna, Italy, 2008-09-13 - 2008-09-16

Identifiers

Local EPrints ID: 65320
URI: http://eprints.soton.ac.uk/id/eprint/65320
PURE UUID: 45db09ec-46c8-42d7-b3f2-2af5f5fc6cec

Catalogue record

Date deposited: 09 Mar 2009
Last modified: 11 Dec 2021 18:30

Export record

Contributors

Author: A. Jimenez-Gonzalez
Author: C.J. James

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×