Open AccessOptimization of pathology diagnosis by applying chaos theory and fractal analysis to EEG-signal processing
Author(s) -
V.S. Kornilov,
Maxim Ostroukhov,
A. V. Dmitriev
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1298/1/012015
Subject(s) - electroencephalography , epilepsy , multifractal system , chaos theory , fractal , mechanism (biology) , computer science , artificial intelligence , neuroscience , recurrence quantification analysis , artificial neural network , pattern recognition (psychology) , psychology , nonlinear system , mathematics , chaotic , physics , mathematical analysis , quantum mechanics
By 2018, there are more than 70 million people suffering from various forms of one of the most common neurological diseases – epilepsy. In fact, epipelsy is a central nervous system (neurological) disorder, manifesting itself in anomalous brain activity. Nowadays, most of the patients do not have the ability to foresee the onset of an attack in advance, which is due to the complex symptoms that are difficult to predict. One of the best way to analyze such kind of behaviour is electroencephalography (EEG). This research paper considers the problem of EEG epileptic seizures prediction from the point of the theory of nonlinear dynamical systems. According to the study, signals of cerebral cortex neural networks corresponds to multifractal nature which gives an opportunity to analyze changes between states in phase space during the abnormal electrical activity. Therefore, monitoring the preictal stage and early indication of an attack may help patients to avoid problems related to sudden seizures. This research will provide valuable information regarding the mechanism of epilepsy onset and introduce a prediction model using machine learning algorithm based on fractal analysis of RQA.