Denoising of discrete-time chaotic signals using echo state networks

Noise reduction is a relevant topic when considering the application of chaotic signals in practical problems, such as communication systems or modeling biomedical signals. In this paper an echo state network (ESN) is employed to denoise a discrete-time chaotic signal corrupted by additive white Gaussian noise. The choice for applying ESNs in this context is motivated by their successful exploitation for separation and prediction of chaotic signals. The results show that the processing gain of ESN is higher than that of the Wiener filter, especially when the power spectral density of the chaotic signals is white.