A parameter optimization nonlinear adaptive denoising algorithm for chaotic signals

Abstract

In the parameter optimization issue of nonlinear adaptive denoising algorithm for chaotic signals, the window length is affected by different factors. In this paper, a criterion is proposed for selecting the optimal window length. According to the difference in autocorrelation function between chaotic signal and noise, first, the different window sizes are used for denoising noisy chaotic signals. Then, the residual autocorrelation degree (RAD) of each window length is computed. Finally, the optimal window length is obtained by shrinking the window length corresponding to the minimum RAD. Simulation results show that this criterion can automatically optimize the window length efficiently under different conditions, which improves the adaptivity of the denoising algorithm of chaotic signals.