Fetal ECG Signal Extraction from Maternal Abdominal Recording Using Source Separation Methods

Please enable javascript in your browser.

Akhavan Amjadi, Majid | 2015

609 Viewed

Type of Document: M.Sc. Thesis
Language: English
Document No: 47795 (55)
University: Sharif University of Technology, International Campus, Kish Island
Department: Science and Engineering
Advisor(s): Shamsollahi, Mohammad Bagher
Abstract:
Analysis of performance of fetal heart is very important for monitoring its health. In recent years a lot of research is performed on recording electronic signals from mother abdomen which consist of combination of maternal ECG and fetal ECG. Purpose of this thesis is investigating methods. For evaluation of different methods simulated ECG dataset and Dalsy dataset as real data were used. In this thesis Wavelet and EMD denoising as single channel methods and ICA, PiCA and deflation as multichannel methods are used. At last novel combinations of these methods is proposed which outperforms existing methods
Keywords:
Wavelets ; Independent Component Analysis (ICA) ; Periodic Component Analysis ; Deflagration ; Empirical Modes Decomposition (EMD)Method

No TOC