Open AccessDesign and implementation of EEMD-assisted ICA joint denoising scheme for ECG signals
Author(s) -
Hanlin Chen,
Cheng Zhao,
Jingyi Yin
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/569/3/032059
Subject(s) - independent component analysis , noise reduction , hilbert–huang transform , computer science , pattern recognition (psychology) , artificial intelligence , noise (video) , blind signal separation , joint (building) , signal (programming language) , signal processing , speech recognition , scheme (mathematics) , engineering , computer vision , mathematics , digital signal processing , channel (broadcasting) , telecommunications , filter (signal processing) , architectural engineering , mathematical analysis , computer hardware , image (mathematics) , programming language
Independent Component Analysis (ICA) algorithm is a signal processing method for solving blind source separation(BSS) problem, which can remove noises in observed signals and obtain original signals. This paper designs and implements an EEMD-assisted ICA joint denoising scheme for ECG signals. Firstly, Ensemble Empirical Mode Decomposition (EEMD) is used to perform noise-assisted data analysis on ECG signals, completing pre-denoising of ECG signals and pre-processing for subsequent ICA analysis. Next, to more thoroughly remove noises in ECG signals, ICA separates independent components from pre-denoised signals. Finally, signal reconstruction restores original ECG signals, so as to realize ECG denoising. Experimental results show that the scheme can effectively remove common noises, and get clean ECG signals, which lay a good foundation for accurate diagnosis of heart patients.