EEG based user recognition using BUMP modelling

In this paper the use of electroencephalogram (EEG) as biometric identifier is investigated. The use of EEG within the biometric framework has already been introduced in the recent past although it has not been extensively analyzed. In this contribution we apply the “bump” modelling analysis for the feature extraction stage within an identification framework, in order to reduce the huge amount of data recorded through EEG. For the purpose of this study we rely on the “resting state with eyes closed” protocol. The employed database is composed of 36 healthy subjects whose EEG signals have been acquired in an ad hoc laboratory. Different electrodes configurations pertinent with the employed protocol have been considered. A classifier based on Mahalanobis distance have been tested for the enrollment of the subjects and their identification. An information fusion performed at the score level has shown to improve correct classification performance. The obtained results show that an identification accuracy of 99.69% can be achieved. It represents an high degree of accuracy, given the current state of research on EEG biometrics.