Morphologically constrained ICA for extracting weak temporally correlated signals

Recently the constrained ICA (cICA) algorithm has been widely applied to many applications. But a crucial problem to the algorithm is how to design a reference signal in advance, which should be closely related to the desired source signal. If the desired source signal is very weak in mixed signals and there is no enough a priori information about it, the reference signal is difficult to design. With some detailed discussions on the cICA algorithm, the paper proposes a second-order statistics based approach to reliably find suitable reference signals for weak temporally correlated source signals. Simulations on synthetic data and real-world data have shown its validity and usefulness.

[1]  Lawrence R. Rabiner,et al.  On the use of autocorrelation analysis for pitch detection , 1977 .

[2]  Zhang Yi,et al.  Extraction of temporally correlated sources with its application to non-invasive fetal electrocardiogram extraction , 2006, Neurocomputing.

[3]  M. Ramasubba Reddy,et al.  A cepstral transformation technique for dissociation of wide QRS-type ECG signals using DCT , 1999, Signal Process..

[4]  Wei Lu,et al.  Approach and applications of constrained ICA , 2005, IEEE Transactions on Neural Networks.

[5]  Erkki Oja,et al.  Independent Component Analysis , 2001 .

[6]  Wei Lu,et al.  ICA with Reference , 2006, Neurocomputing.

[7]  Asoke K. Nandi,et al.  Noninvasive fetal electrocardiogram extraction: blind separation versus adaptive noise cancellation , 2001, IEEE Transactions on Biomedical Engineering.

[8]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[9]  Zhang Yi,et al.  Robust extraction of specific signals with temporal structure , 2006, Neurocomputing.

[10]  Jonathon A. Chambers,et al.  Fetal electrocardiogram extraction by sequential source separation in the wavelet domain , 2005, IEEE Transactions on Biomedical Engineering.

[11]  Wei Lu,et al.  Constrained Independent Component Analysis , 2000, NIPS.

[12]  Allan Kardec Barros,et al.  Heart instantaneous frequency (HIF): an alternative approach to extract heart rate variability , 2001, IEEE Transactions on Biomedical Engineering.

[13]  Bart De Schutter,et al.  DAISY : A database for identification of systems , 1997 .

[14]  Liqing Zhang,et al.  A Two-Stage Based Approach for Extracting Periodic Signals , 2006, ICA.

[15]  Allan Kardec Barros,et al.  Analysis on EEG Signals in Visually and Auditorily Guided Saccade Task by FICAR , 2006, ICA.

[16]  Allan Kardec Barros,et al.  Extraction of Specific Signals with Temporal Structure , 2001, Neural Computation.

[17]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[18]  J.C. Rajapakse,et al.  Extraction of event-related potentials from EEG signals using ICA with reference , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[19]  Allan Kardec Barros,et al.  Extraction of event-related signals from multichannel bioelectrical measurements , 2000, IEEE Trans. Biomed. Eng..

[20]  Andrzej Cichocki,et al.  Sequential blind source separation based exclusively on second-order statistics developed for a class of periodic signals , 2006, IEEE Transactions on Signal Processing.

[21]  Matti Karjalainen,et al.  A computationally efficient multipitch analysis model , 2000, IEEE Trans. Speech Audio Process..

[22]  Christopher J. James,et al.  Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis , 2003, IEEE Transactions on Biomedical Engineering.

[23]  Lars Kai Hansen,et al.  Exploring fMRI data for periodic signal components , 2002, Artif. Intell. Medicine.