Experiments on classification of electroencephalography (EEG) signals in imagination of direction using a wireless portable EEG headset

Abstract

Here we present experimental results of classification methods for brain activity in the imagination of direction. In anticipation of its adequate performance, we used a wireless portable electroencephalography (EEG) headset to collect EEG data from subjects in the experiments, during which the subjects imagined arrows indicating one of the four directions: up, down, right, and left. The classification methods estimated the direction that the subjects imagined on the basis of their brain wave signals measured by an electrode on the portable EEG headset. We implemented several classification methods, which basically followed those of a previous study that used a medical EEG device. The classification methods consisted of a band-pass filter, fast Fourier transformation, principal component analysis, and neural network. The experimental results showed that the neural network trained with the EEG data of all subjects achieved a 52.00% classification rate. When using the EEG data of each subject, the best classification rate was 55.00%. The results using the portable EEG headset were comparable with those of the previous study.