Denoising using local projective subspace methods

Abstract

In this paper we present denoising algorithms for enhancing noisy signals based on Local ICA (LICA), Delayed AMUSE (dAMUSE) and Kernel PCA (KPCA). The algorithm LICA relies on applying ICA locally to clusters of signals embedded in a high-dimensional feature space of delayed coordinates. The components resembling the signals can be detected by various criteria like estimators of kurtosis or the variance of autocorrelations depending on the statistical nature of the signal. The algorithm proposed can be applied favorably to the problem of denoising multi-dimensional data. Another projective subspace denoising method using delayed coordinates has been proposed recently with the algorithm dAMUSE. It combines the solution of blind source separation problems with denoising efforts in an elegant way and proofs to be very efficient and fast. Finally, KPCA represents a non-linear projective subspace method that is well suited for denoising also. Besides illustrative applications to toy examples and images, we provide an application of all algorithms considered to the analysis of protein NMR spectra. r

Denoising based on time-shift PCA

“…This new MEG denoising technique is related to dynamic PCA used in process control (Ku et al, 1995), singular spectrum analysis (SSA) used in geophysics (Allen and Smith, 1997;Ghil et al, 2002;Vautard and Ghil, 1989), the delayed coordinate methods of Gruber et al (2006), or the delayed correlation ICA methods of Ziehe et al (2000) or Sander et al (2002). All of these techniques involve augmenting a set of signals with delayed versions.…”

Time-shift denoising source separation

“…The initial two steps of TSDSS correspond to the spatiotemporal whitening proposed by Beucker and Schlitt (1997). Time delays are involved in various other analysis techniques (Friman et al, 2002;Gruber et al, 2006;Sander et al, 2002;Woon and Lowe, 2004;Ziehe et al, 2000). TSDSS exploits the serial correlation structure of the data, that can also be captured in the frequency domain (Anemüller et al, 2003) or by multichannel linear prediction (e.g.…”

Hybridizing sparse component analysis with genetic algorithms for microarray analysis

“…ICA can also be used to reduce noise [40], [35], [12] or artifacts [36,37] if generated from independent sources. Usually a linear superposition of the underlying unknown source signals is assumed but nonlinear ICA algorithms also exist.…”