Specificities of ERD lateralization during motion execution
Smirnov N.,1 Kurkin S.A.,1,2 Hramov A.E.,1,2 1 Innopolis University, Innopolis, Russia 2 Immanuel Kant Baltic Federal University, Kaliningrad, Russia
Abstract
When creating motor imagery brain-computer interfaces (BCI), there is a problem with the accuracy of determining which limb made the movement. Usually, the accuracy of the classifiers does not exceed 80-85%. In this work, we examined this problem from the point of view of the well-known phenomenon of lateralization during motor movements. Several algorithms were used to investigate the proportion of contralateral and ipsilateral responses based on event-related desynchronization (ERD) calculations using EEG data gathered throughout motor function-related experiments. This paper aims to show that proportion and explain how this may be related to the low accuracy of BCI classifiers.
File with abstract
Speaker
Smirnov Nikita
Innopolis University
Russia
Discussion
Ask question