Abstract
This paper introduces a method to analyze an individual difference in an electroencephalogram (EEG) using a self-organizing map (SOM). The EEG recording position is a left prefrontal pole (Fp1) in the international 10-20 system. The device for recording the EEG uses dry-type sensor and a small number of electrodes. The EEG data is analyzed through the FFT and EEG features are extracted by calculating the time average of the power spectrum of five frequency bands which are theta, low-alpha, high-alpha, low-beta and high-beta, respectively. In order to confirm the individual difference in the EEG, the EEG patterns are classified using the SOM. The EEG patterns are based on human responses on sounds listened to. Finally, we conduct experiments using real EEG data. The experimental results suggest that it is possible to express the individual differences in the EEG using SOM.
