「Examination and It’s Evaluation of Preprocessing Method for Individual Identification in EEG 」

［Journal of Information Processing Vol.28, pp.239-246］

［Abstract］

　Recently, the technology of BMI that communicates with humans and operates a robot using human brain information has been actively studied. The authentification function using BMI has been studied by previous research. Although many studies focus on feature extraction and learning model creation, there are few studies that discuss the effectiveness of preprocessing. In this study, we implemented an EEG biometric function using image stimulation method. In this paper, we proposed biometric authentication system system using EEG at time of image stimulus. At the same time, we evaluated the change in authentication accuracy in order to verify the preprocessing (digital filter, artifact countermeasure, epoch) method in the authentication system. As a result, authentication accuracy is improved by performing the proposed preprocessing. In addition, it was shown that convenience and security were improved when using the system.

［Reasons for the award］

　Brain Machine Interface (BMI) is a direct communication method between a human brain and an external device to expand capability of human beings. In recent years, non-invasive devices measuring electroencephalogram (EEG) data in real time has been released as consumer products, and machine learning-based EEG data analysis methods have been actively studied. This paper proposes and evaluates a new BMI-based biometric identification system using EEG data of image stimulus presentation. The proposed system using BMI is difficult to be eavesdropped and achieves 98% accuracy of the personal identification. The paper gives insights to readers in this research field, and may have a great impact in practical application. For the above reasons, this paper deserves an Outstanding Paper Award.