Estimation of Parameters of Non-Stationary Information Processes Using Wavelet Analysis

Abstract

The paper proposes an algorithm for estimation the parameters of information processes based on a wavelet analysis apparatus suitable for non-stationary and non-Markov control processes. Comparative analysis with algorithms based on the Fourier transform and the fast Fourier transform is carried out. The analysis shows that the proposed algorithm improves the accuracy of processing complex and non-stationary processes. For processing a variable frequency signal the error of the results obtained using the synthesized algorithm is 20% lower than when using the fast Fourier transform and 10% lower than using the Fourier transform.