Impact of age, sex and hair type on SSVEP-based EEG signals analysis

Abstract

The Brain Computer Interface (BCI) creates an alternative communication channel for individuals who cannot speak or provide their own physical needs, despite having regular conscious and brain activity. The processing of individual Electroencephalogram (EEG) data is a frequently used method in the literature to create this alternative communication channel. In this paper, EEG data of subjects whose details are given in the following sections were examined by steady-state visually evoked potentials (SSVEP) technique and the impact of age, sex and hair type on the accuracy of classification of these data was investigated. The results show that high classification accuracy can be achieved with the implementation of SSVEP, and different demographic characteristics may affect this accuracy rate positively/negatively.