ADAPTIVE RECOGNITION AND FILTERING OF NOISE USING WAVELETS

We combine wavelet transform and adaptive recognition techniques to in troduce a filtering process able to analyze, categorize, and remove ad ditive noise from experimental time series, without previous informati on either on the correlation properties of noise or on the dimension o f the deterministic signal. The method is applied to a high dimensiona l delayed chaotic time series affected by additive white and colored n oises. The obtained results show that the reconstruction of the signal both in real and in Fourier space is effective through the discrimina tion of noise from the deterministic part.