Biometric authentication using evoked potentials stimulated by personal ultrasound

Abstract

In recent years, biometrics such as fingerprints and iris scans has been used in authentication. However, conventional biometrics is vulnerable to identity theft, especially in user management systems. As a new biometric without this vulnerability, we focused on brain waves. In this paper, we show that individuals can be authenticated using evoked potentials when they are subjected to ultrasound. We measured the electroencephalograms (EEGs) of 10 experimental subjects. Individual features were extracted from the power spectra of the EEGs using the principle component analysis and verification was achieved using the support vector machine. We found that for the proposed authentication method, the equal error rate for a single electrode was about 22-32 %. For a multi-electrode, the equal error rate was 4.4 % using the majority decision rule.