ICA based ECG signal denoising

Significant diagnostic information in healthcare is obtained from Electrocardiogram (ECG) signals, so improvements in their analysis are also of growing importance. In the field of signal processing, the rapidly developing signal technology and flourishing variety of algorithms have proved successful targets for research in healthcare. During the acquisition of ECG signal it gets corrupted due to different types of artifacts and interferences that may hide important diagnostic information. Independent Component Analysis (ICA) is a blind source separation technique that can be used for the removal of such noises and artifacts. In this paper, different ICA schemes such as JADE algorithm and Fast ICA are discussed and applied for ECG denoising. Also made an attempt to apply constrained ICA (cICA) for ECG signal denoising which was used for fetal ECG extraction. The database used is MIT-BIH database.