Design and implementation of EEMD-assisted ICA joint denoising scheme for ECG signals

2019 2nd International Conference on Advanced Materials, Intelligent Manufacturing and Automation

Chen, Hanlin^1 ; Zhao, Cheng^1 ; Yin, Jingyi^1

Department of Electronics and Communication Engineering, Beijing Electronic Science and Technology Institute, Beijing

100070, China^1

关键词: De-noised signals;    Design and implementations;    Ensemble empirical mode decompositions (EEMD);    Heart patients;    Independent component analysis(ICA);    Independent components;    Original signal;    Pre-processing;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/569/3/032059/pdf
DOI  :  10.1088/1757-899X/569/3/032059

来源: IOP

【 摘 要 】

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.