Wavelets Comparison at Hurst Exponent Estimation

In this paper we present Discrete Wavelet Transformation based on Hurst exponent estimation and compare different wavelets used in the process. Self-similar behavior mostly associated with fractals can be found in broad range of areas. For self-affine processes the local properties are reflected in the global ones and the Hurst exponent is related to fractal dimension, where fractal dimension is a measure of the roughness of a surface. For usually non-stationary time series the Hurst exponent is a measure of long term memory of time series. From former works mentioned in references we know that Discrete Wavelet Transformation provides better accuracy compared to Continuous Wavelet Transformation and that it outperforms methods based on the Fourier spectral analysis and R/S analysis.