A Permanency Investigation of SSVEP Signals in Brain Biometrics

Electroencephalograph (EEG) which reflects brain electrical activity has recently been found to have great potential in the field of biometric identification due to its unique advantages compared with traditional biometric (fingerprint, face) identification methods, such as strong concealment, unable to steal, and difficult to forge. Many studies have proposed that EEG features are sufficiently distinct across individuals but lack multiple recording sessions to demonstrate the permanency of EEG features in time dimensions. In this study, we performed steady-state visual evoked potential (SSVEP) experiments at a variety of frequencies and found that individuals have specific EEG spectrum sensitivity in response to SSVEP visual stimuli at 7-12Hz. Furthermore, this paper explores the permanency of the proposed SSVEP feature. By conducting multiple experiments on 15 subjects in five different time points (morning and afternoon of the same day, an interval of one day, an interval of one week, an interval of one month), the results demonstrate that the proposed individual EEG features are repeatable. Due to the widespread use of SSVEP in brain-computer interfaces (BCI), the features are expected to be used to improve the security and confidentiality of devices in terms of identity recognition and operational authorization.