Assessment of permanence of non-volitional EEG brainwaves as a biometric

Electrical brain activities can be measured noninvasively using electroencephalogram (EEG). This electric signal changes for different tasks, and also changes from subject to subject. Previous studies have shown that the EEG signal is unique enough to be used as a biometric characteristic. However, it is well known that the brain activity can change according to our emotion or stress status, among many other factors. The stability of EEG signals as a biometric has not yet been well explored and understood. In this work, we explicitly investigated and assessed the permanence of the non-volitional EEG brainwaves over the course of time. Specifically, we analyzed how much the EEG signal changes over a period of six months, since any drastic change would make it unusable as an authentication method. The results are very encouraging, yielding high accuracy throughout the six-month period.