EUSIPCO2019 | Faculty of Electronics, Telecommunications and Informatics at the Gdańsk University of Technology

Calculations were carried out at the Academic Computer Centre in Gdańsk.

Extra materials for reviewers for EUSIPCO 2019 submission no. 1570531404

 "FULLY ADAPTIVE SAVITZKY-GOLAY TYPE SMOOTHERS"  

 Maciej Niedźwiecki and Marcin Ciołek

ABSTRACT

The problem of adaptive signal denoising is considered and solved using the weighted basis function approach. In the special case of polynomial basis and uniform weighting the proposed method reduces down to the celebrated Savitzky-Golay smoother. Data adaptiveness is achieved via parallel estimation. It is shown that for the polynomial and harmonic bases and cosinusoidal weighting sequences, the competing signal estimates can be computed in both time-recursive and order-recursive way.

The MATLAB source code for the wavelet shrinkage methods VisuShrink and BayesShrink  is provided on the web page of Stanford University repository:

 http://statweb.stanford.edu/~wavelab/Wavelab_850/, (last seen in October 2018).

All used algorithms (MATLAB code)  can be download from our repository. We used MATLAB R2017b (9.3.0.713579).