P300 Evoked Potential Detection Method Using the MSI Algorithm in the Problem of Human-Computer Interaction

The paper presents a method for detecting evoked potentials from a background electroencephalogram based on one iteration of brain electrical activity in response to the stimulation process. The basis of the method is the formation of a quasi-periodic sequence of the component of the evoked potential (EP) of interest to the researcher, due to the addition of reference fragments of the EP with a given time shift. The resulting sequence is compared with the reference EP accumulated within the framework of the coherent accumulation approach and appropriately transformed so that the period of the desired component coincides with that in the signal under study. The comparison is carried out taking into account the Multivariate Synchronization Index (MSI) method, which is a further development of the canonical correlation method. The results obtained can be applied to the tasks of brain-computer interfaces (BCI) based on the P300 potential. In addition, this solution is applicable to the isolation of any biomedical signal containing single or non-periodic components.