Calculation of Analogs of Lyapunov Exponents for Different Types of EEG Time Series using Artificial Neural Networks

German A. Chernykh, Ludmila A. Dmitrieva, Yuri A. Kuperin

Результат исследований: Научные публикации в периодических изданияхстатьярецензирование


The relevance of the study is due to the need to develop reliable methods of classification of relatively
short and complex time series, where known methods do not always give an acceptable result. The study aims at
developing a method for constructing new numerical characteristics of time series, which are analogs of Lyapunov
exponents for complex dynamic systems in their physical and mathematical sense.
The developed method is new because it is based on the use of committees of artificial neural networks. The method
was tested on time series of electroencephalograms, in particular, for comparative analysis of electroencephalograms
of subjects in a state of meditation with their background records of electroencephalograms. Statistically significant
results are obtained, on the basis of which, on the one hand, it can be concluded that the developed technique can be
effectively applied to the time series of electroencephalograms. On the other hand, the developed technique allows
drawing certain conclusions about the specifics of synchronization of large ensembles of neurons for the subjects
practicing meditation. The developed methods and the results are of theoretical interest for researchers involved in
the analysis of time series. Also, these methods and results are of practical value for neurophysiologists who study
the processes of meditation by quantitative methods.
Язык оригиналаанглийский
Страницы (с-по)2553-2569
Номер выпуска28
СостояниеОпубликовано - 2019

Fingerprint Подробные сведения о темах исследования «Calculation of Analogs of Lyapunov Exponents for Different Types of EEG Time Series using Artificial Neural Networks». Вместе они формируют уникальный семантический отпечаток (fingerprint).