Separation of cardiac and respiratory components from the electrical bio-impedance signal using PCA and fast ICA

Yar Muhammad, Andrei Krivoshei, Paul Annus

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

Abstract

This paper is an attempt to separate cardiac and respiratory signals from an electrical bio-impedance (EBI) dataset. For this two well-known algorithms, namely Principal Component Analysis (PCA) and Independent Component Analysis (ICA), were used to accomplish the task. The ability of the PCA and the ICA methods first reduces the dimension and attempt to separate the useful components of the EBI, the cardiac and respiratory ones accordingly. It was investigated with an assumption, that no motion artefacts are present. To carry out this procedure the two channel complex EBI measurements were provided using classical Kelvin type four electrode configurations for the each complex channel. Thus four real signals were used as inputs for the PCA and fast ICA. The results showed, that neither PCA nor ICA nor combination of them can not accurately separate the components at least are used only two complex (four real valued) input components.
Original languageEnglish
Title of host publicationInternational Conference on Control, Engineering & Information Technology (CEIT’13)
Number of pages4
Publication statusPublished - 3 Jul 2013
EventInternational Conference on Control, Engineering & Information Technology 2013 - Sousse, Tunisia
Duration: 4 Jun 20137 Jun 2013

Conference

ConferenceInternational Conference on Control, Engineering & Information Technology 2013
Abbreviated titleCEIT'13
Country/TerritoryTunisia
CitySousse
Period4/06/137/06/13

Fingerprint

Dive into the research topics of 'Separation of cardiac and respiratory components from the electrical bio-impedance signal using PCA and fast ICA'. Together they form a unique fingerprint.

Cite this