ISSN 0869-6632 (Print)
ISSN 2542-1905 (Online)


частотно-временной анализ

Математическая модель для выявления эпилептических приступов на записи ЭЭГ

Цель настоящего исследования - анализ возможности использования сверточных нейронных сетей в качестве модели для выявления эпилептических приступов на реальных данных ЭЭГ.
Методы. Для частотно-временного анализа используется вейвлет-анализ. Для локализации эпилептических разрядов задача их детектирования была сведена к задаче классификации и использовалась модель нейронной сети архитектуры ResNet18. Были использованы техники для аугментации и балансировки рассматриваемого датасета биомедицинских данных.

Thalamo-cortical dysrhythmia and its diagnostic principles

Aim. In the brain of mammals and humans, several widespread neuronal networks are capable of generating spontaneous rhythmic activity. Among them is the thalamo-cortical network, which involves neurons of the thalamus (diencephalon) and in the neocortex and characterized by hierarchical organization. The thalamo-cortical network generates alpha rhythms with a frequency of about 8...14 Hz. Various neurological and psychiatric disorders are known to associate with similar disturbances of thalamo-cortical rhythms, i.e. the thalamo-cortical dysrhythmia.

Time­frequency analysis of nonstationary processes: concepts of wavelets and empirical modes

A comparation of wavelets and empirical modes concepts is performed that represent the most perspective tools to study the structure of nonstationary multimode processes. Their advantages over the classical methods for time series analysis and restrictions of both approaches are discussed that needs to be known for correct interpretation of the obtained results. New possibilities in the study of signals structure at the presence of noise are illuctrated for digital single-channel experimental data of prospecting seismology.