Person identification via the EEG using computational geometry algorithms

A direct connection between the electroencephalogram (EEG) and the genetic information of an individual has been suspected and investigated by neurophysiologists and psychiatrists since 1960. However, most of this early as well as more recent research focuses on the classification of pathological EEG cases, aiming to construct diagnosis tests from the EEG. The present work aims to establish an one-to-one correspondence between the genetic information of a (healthy) individual and certain features of his/her EEG, and — as a further goal — to develop a test for person identification based on EEG-extracted features. At the present stage the proposed method uses spectral information extracted from the EEG via the FFT and employs computational geometry algorithms to classify an unknown EEG as belonging to one of a finite number of individuals. Correct classification scores at the level of 95%, in a limited scale experiment conducted on real data, show evidence that the EEG indeed carries genetic information and that the proposed method can be used to construct person identification tests based on EEG features.