Calculation of the Exact Value of the Fractal Dimension in the Time Series for the Box-Counting Method
Анотація
In this paper, the problem of precise determination of the size of the fractal dimension of the time series is considered. The bottom line is that the classical box method equally takes into account both filled and not filled boxes of the superimposed grid. In the proposed method, the size of the boxes is tied to the scale of the values of the time series levels. As a result, there is a minimum coverage of the graph, which provides the exact value of the fractal dimension. The comparison of estimates of fractal dimension calculated by classical and proposed methods is given.
Класифікація
Ідентифікатори
Рецензії (0)
Написати рецензіюРецензій ще немає. Будьте першим!
Схожі роботи
Predictive clustering on non-successive observations for multi-step ahead chaotic time series prediction
Схоже за: Neural Networks and Applications · Complex Systems and Time Series Analysis
Fractal-Entropy Analysis of the Results of Measurements in Nonlinear Dynamical Systems
Схоже за: Neural Networks and Applications · Complex Systems and Time Series Analysis
Financial time series prediction with the technology of complex Markov chains
Схоже за: Neural Networks and Applications · Complex Systems and Time Series Analysis
The forecastings of future changes in the trend's direction of stock quotes by neural networks and fuzzy systems
Схоже за: Neural Networks and Applications · Complex Systems and Time Series Analysis
Spectra of pulse signals formed on the basis of the fractal brownian signals (FBS)
Схоже за: Neural Networks and Applications · Complex Systems and Time Series Analysis
Generalized Approach to Analysis of Multifractal Properties from Short Time Series
Схоже за: Statistical and Computational Modeling · Complex Systems and Time Series Analysis