Robustness of functional connectivity metrics for EEG-based personal identification over task-induced intra-class and inter-class variations

Abstract Growing interest is devoted to understanding in which situations and with what accuracy brain signals recorded from scalp electroencephalography (EEG) may represent unique fingerprints of individual neural activity. In this context, the present paper aims to investigate the impact of some of the most commonly used metrics to estimate functional connectivity on the ability to unveil personal distinctive patterns of inter-channel interactions. Different metrics were compared in terms of equal error rate. It is widely accepted that each connectivity metric carries specific information in respect to the underlying interactions. Experimental results on publicly available EEG recordings show that different connectivity metrics define peculiar subjective profile of connectivity and show different mechanisms to detect subject-specific patterns of inter-channel interactions. Moreover, these findings highlight that some measures are more accurate and more robust than others, regardless of the task performed by the user. Finally, it is important to consider that frequency content and spurious connectivity may still play a relevant role in determining subject-specific characteristics.