Permanence and Uniqueness of EEG Brain Signals as a Biometric Signature, Part-I: Template-based Techniques

The utilization of electroencephalography as a potential biometric tool has been garnering significant attention, leveraging the distinct signatures embedded in human brain activity. The effectiveness of such characteristic patterns, however, hinges on their stability over time. In this study, we aim to explore the permanence and the uniqueness of neural patterns. A comprehensive comparison is conducted on a spatio-temporal space across various stimuli protocols. Summarizing our findings regarding the agreement of different time-series techniques for measuring intra- and inter-subject similarity, we present our approach and outcomes in two parts. In this first part, we employed two template-based time series similarity measures, namely normalized Dynamic Time Warping, and normalized Cross-Correlation. Additionally, we enhance our analysis by applying two time-domain filters- Adjusted Laplacian of Mean and Laplacian of Gaussian- for the extraction of specific spectral neural activity, followed by similarity measures. Our preliminary findings indicate that the proposed template-based pipeline can achieve an 86% accuracy rate in identifying individuals over the course of a week. This suggests that the pipeline shows promise in its ability to reliably distinguish between individuals based on the data it processes. However, further validation and testing may be necessary to confirm and refine these findings.