Title :
Blind Extraction for Noisy Fetal Electrocardiogram by Using Gaussian Moments
Author :
Yang, Yumin ; Guo, Chonghui
Author_Institution :
Inst. of Syst. Eng., Dalian Univ. of Technol., Dalian
Abstract :
Non-invasive fetal electrocardiogram (FECG) extraction is a vital issue in biomedical signal processing and analysis. A promising approach is blind source extraction and many algorithms have been proposed in recent years. In this paper, we consider the blind extraction when Gaussian noise is present and the source signals combine the non-Gaussianity and the autocorrelations. According to the useful properties of Gaussian moments, a simple gradient algorithm is developed for noisy blind extraction. Validity and performance of the described algorithm are demonstrated by computer simulations.
Keywords :
Gaussian processes; electrocardiography; medical signal processing; Gaussian moments; biomedical signal processing; blind extraction; noisy fetal electrocardiogram; noninvasive fetal electrocardiogram extraction; Autocorrelation; Biomedical engineering; Biomedical signal processing; Data mining; Delay effects; Gaussian noise; Independent component analysis; Signal analysis; Signal processing algorithms; Systems engineering and theory; Blind source extraction; FECG; Independent component analysis;
Conference_Titel :
Natural Computation, 2008. ICNC '08. Fourth International Conference on
Print_ISBN :
978-0-7695-3304-9
DOI :
10.1109/ICNC.2008.476