Перегляд за автором "Bulakh, V."

Зараз показано 1 - 4 з 4
  • Зображення мініатюри
    Публікація
    Comparative analysis of machine learning classification оf time series with fractal properties
    (2019) Radivilova, T.; Kirichenko, L.; Bulakh, V.
    The article analyses the classification of time series according to their fractal properties by machine learning. The classification was carried out using neural networks and the random forest method. Objects were the model fractal time series with given the Hurst exponent. Each class was a set of time series with the Hurst exponent values in a predetermined range. Input features were the values of time series. It was demonstrated that in this case the classification accuracy is high enough. The most accurate classification results were obtained using recurrent neural network. The proposed method can be readily used in practice for recognition, classification and clustering of time series with fractal properties.
  • Зображення мініатюри
    Публікація
    Fractal time series analysis of social network activities
    (2017) Kirichenko, L.; Radivilova, T.; Bulakh, V.
    In the work, a comparative correlation and fractal analysis of time series of Bitcoin crypto currency rate and community activities in social networks associated with Bitcoin was conducted. A significant correlation between the Bitcoin rate and the community activities was detected. Time series fractal analysis indicated the presence of self-similar and multifractal properties. The results of researches showed that the series having a strong correlation dependence have a similar multifractal structure.
  • Зображення мініатюри
    Публікація
    Generalized approach to Hurst exponent estimating by time series
    (2018) Kirichenko, L.; Radivilova, T.; Bulakh, V.
    This paper presents a generalized approach to the fractal analysis of self-similar random processes by short time series. Several stages of the fractal analysis are proposed. Preliminary time series analysis includes the removal of short-term dependence, the identification of true long-term dependence and hypothesis test on the existence of a self-similarity property. Methods of unbiased interval estimation of the Hurst exponent in cases of stationary and non-stationary time series are discussed. Methods of estimate refinement are proposed. This approach is applicable to the study of self-similar time series of different nature.
  • Зображення мініатюри
    Публікація
    Machine Learning Classification of Multifractional Brownian Motion Realizations
    (ХНУРЕ, 2020) Kirichenko, L.; Radivilova, T.; Bulakh, V.
    A comparative analysis of machine learning classification of stochastic time series based on their multifractal properties is proposed. Multifractal time series were obtained by generating realizations of fractional Brownian motion in multifractal time. The features for classification were statistical, fractal and recurrent characteristics calculated for each time series. The various machine learning classifiers were chosen for classification: bagging with classification and regression decision trees, random forest with classification and regression decision trees, fully connected perceptron and recurrent neural network. Both cumulative time series of multifractal Brownian motion and time series increments were carried out. It was shown that in general, classification accuracy is higher when using series of increments. When classifying realizations of multifractional Brownian motion, bagging and recurrent neural network showed the best accuracy.