Increasing the Classification Accuracy of EEG based Brain-computer Interface Signals

Abstract

In the recent years the attention to Brain-Computer Interface (BCI) devices and their potential for decoding human brain signals have risen considerably. The achieved results find application in the spheres of medicine, Smart IoT, machinery management, automobiles etc. In this article our team research the impact of additional visual stimulation on the accuracy of the classification of human brain signals. Experimental data is obtained by using Emotiv Epoc 14+. The data is processed in OpenVibe platform. The results of the research show considerable quality improvement in classifier training when additional visual stimulation is introduced. This leads to improved accuracy of incoming signal classification when applied in practice.