Fetal ECG extraction using an FIR neural network

Author

Camps, G. ; Martínez, M. ; Soria, E.

Author_Institution

Facultat de Fisica, Valencia Univ., Spain

fYear

2001

fDate

2001

Firstpage

249

Lastpage

252

Abstract

Non-invasive electrocardiography reveals itself as a very interesting method to obtain reliable information about the state of the fetus, thus assuring its well-being during pregnancy. In this paper, a finite impulse response (FIR) neural network is included in the familiar adaptive noise cancellation scheme in order to provide highly nonlinear dynamic capabilities to the recovery model. A novel methodology for selecting the optimal topology is also presented. Results from its application to both simulated and real registers are shown and benchmarked with the classical LMS (least mean squares) and normalized LMS (NLMS) algorithms. Outcomes indicate that the FIR network is a reliable method for the fetal electrocardiogram recovery

Keywords

FIR filters; adaptive signal processing; electrocardiography; interference suppression; least mean squares methods; medical signal processing; network topology; neural chips; obstetrics; FIR neural network; adaptive noise cancellation; electrocardiogram recovery model; finite impulse response network; foetal ECG extraction; noninvasive electrocardiography; nonlinear dynamic capabilities; normalized least mean squares algorithm; optimal topology selection methodology; pregnancy; registers; Adaptive filters; Electrocardiography; Fetus; Filtering; Finite impulse response filter; Neural networks; Neurons; Noise cancellation; Pregnancy; Proposals;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers in Cardiology 2001

Conference_Location

Rotterdam

ISSN

0276-6547

Print_ISBN

0-7803-7266-2

Type

conf

DOI

10.1109/CIC.2001.977639

Filename

977639