Noninvasive Cardiac Signal Analysis Using Data Decomposition Techniques - Modeling in Computational Biology and Biomedicine - page 109

3.5 Online Resources

The RobustICA algorithm
http://www.i3s.unice.fr/ ∼ zarzoso/robustica.html
This website proposes a Matlab implementation of the RobustICA algorithm
described in Sect. 3.3.3

The LVA Central website
http://lvacentral.inria.fr
This website contains a variety of algorithms for latent variable analysis and signal
separation, including ICA, as well as datasets for evaluating their performance

The PhysioNet database
http://www.physionet.org
This website, maintained by the MIT, features a large collection of recorded
physiological signals and related open-source software, including but not limited
to ECG signal processing

Inria's CardioSense3D project
http://www-sop.inria.fr/CardioSense3D
This project aims at modeling cardiac electrical and mechanical activity simultane-
ously

Acknowledgements Part of the work summarized in this chapter is supported by the French
National Research Agency under contract ANR 2010 JCJC 0303 01 “PERSIST”.

List of Acronyms

AF Atrial fibrillation

BSS Blind source separation

ECG Electrocardiogram

EVD Eigenvalue decomposition

ICA Independent component analysis

KM Kurtosis maximization

MaxViT Maximum variance in tails

MSE Mean square error

PCA Principal component analysis

SOBI Second-order blind identification

STC Spatio-temporal QRST cancellation

SVD Singular value decomposition

TWA T-wave alternans