Evolutionay wavelet networks for statistical time series analysis
Tommaso Minerva · IRIS UNIMORE (University of Modena and Reggio Emilia) · 2010
In this paper I describe an evolutionary wavelet network to optimize the filtering of a statistical time series into separate contributions. The wavelet base is regarded as a neural network where the network nodes are discrete wavelet transforms, the wavelon, and the network structure and parameters are selected through evolutionary techniques. With this combined approach I can separate stochastic from structural components within an optimized framework and finally I can perform optimized predictive analysis on the time series components.