Fetal Signal Reconstruction Based on Independent Components Analysis

Author

Lee, Yapeng ; Jiang, Shiqin

Author_Institution

Sch. of Electron. & Inf. Eng., Tongji Univ., Shanghai, China

fYear

2009

fDate

11-13 June 2009

Firstpage

1

Lastpage

3

Abstract

Independent component analysis (ICA) is an effective source separation method, and has been widely used in fetal signal detection from abdominal maternal electrocardiogram (ECG) and magnetocardiography (MCG). One difficulty with the application of ICA is to determine the character information of independent components. A method, based on a simple statistical parameter-kurtosis, is proposed in this paper to solve the problem. It has been successfully applied to remove the maternal signal and the noise from the raw fetal MCG (fMCG) data of a 28-week pregnant woman through a 5-channel fMCG detector. The method offers potential applications for online processing of fMCG using ICA.

Keywords

independent component analysis; medical signal processing; obstetrics; signal reconstruction; ECG; ICA; MCG; effective source separation method; electrocardiogram; fMCG; fetal MCG; fetal signal reconstruction; independent components analysis; kurtosis; magnetocardiography; Electrocardiography; Fetus; Filters; Independent component analysis; Magnetic separation; Neural networks; Pregnancy; Signal analysis; Signal reconstruction; Source separation;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics and Biomedical Engineering , 2009. ICBBE 2009. 3rd International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-2901-1

Electronic_ISBN

978-1-4244-2902-8

Type

conf

DOI

10.1109/ICBBE.2009.5162857

Filename

5162857