ECG Signal Processing using Basis Function of Independent Component Analysis

K.L. Park, J. Lee, and K.J. Lee (Korea)


Electrocardiogram signal processing, independent component analysis and basis functions


This paper is about the study on signal processing of electrocardiogram (ECG) using basic functions extracted by independent component analysis (ICA). The study assumed ECG signals were mixed signals that combined various source signals linearly and used 12 channel signals at sampling rate of 600Hz. Using Independent Component Analysis (ICA), basis functions were extracted that could isolate and detect source signals of ECG signals - QRS complex, P wave, T wave and so on. By applying extracted basis functions to normal and abnormal waveforms, it provided the feature points necessary for diagnosis and separating normal and abnormal signals. It not only showed the method to resolve the problem that signals with specific frequencies were hardly isolated in the ECG signal processing using a wavelet transformation technique, but also indicated ICA could be a useful technique in the ECG signal analysis.

Important Links:

Go Back