The reduction of learning sample in information-measuring and control systems based on brain-computer interface technology

Abstract

The brain-computer interface (BCI) is a technology that enables communication between the brain and the external environment on basis of registration of the electroencephalogram (EEG) signals only. The functioning of the BCI system is a cycle, in which each iteration consists of EEG signal measurement, its preprocessing, features selection, classification and generation of control action corresponding to the recognized operator command. Commands recognition requires creation of the learning set used to configure the classifier. This article describes a method of the learning sample reduction. It is based on the analogy between the clusters and graphs and designed for use in the BCI systems based on microprocessor devices with low performance and memory capacity. Using the proposed method will improve the performance of data measuring and control systems based on the BCI technology.