Adaptive filter support selection for signal denoising based on the improved ICI rule

Performance and simulation-based optimization of the improved intersection of confidence intervals (ICI) rule for adaptive filter support selection are presented. The improved ICI rule (refereed to as the relative intersection of confidence intervals (RICI) rule) is combined with the local polynomial approximation (LPA) method and applied to signal denoising, with the aim to enhance the signal estimation accuracy and reduce the estimation error energy. The results achieved using the RICI rule are compared to those obtained using the classical ICI rule, showing the reduction of the root mean-square error (RMSE) of up to 10 times for various classes of analyzed signals. The proposed procedure for the selection of the RICI parameters Γ and Rc, for which the RMSE is minimum, has been shown to significantly improve the quality of denoised signals.