An adaptive filter method based on the dyadic wavelet transform

An adaptive filter method, which is based on the different characteristic of signal with noise in different wavelet scales, was founded. The method was directly comparing the absolute values of Corr(2) (m, n) after being rescaled and W(m, n) to determine whether the data point W( m, n) should be kept. The standard deviation a. of noise at each scale m was employed to stop the iterating. The de-noising process, the effect of the full width at half-maximum and noise quantum were investigated, and before and after de-noise results for simulated and capillary electrophoresis signals were compared. The experimental results show that it is a better adaptive filter method and can be used to wipe off the noise effectively.