Adaptive Hausdorff Estimation of Movement-Related Eeg Patterns for Brain-Computer Interfaces

Abstract

The study was aimed at developing a new automatic search technique for specific invariant patterns associated with the execution of voluntary motor activity (Readiness potentials, RP) reflected in multidimensional electroencephalogram (EEG) signals. The Hausdorff metric was used as a criterion function for searching specific movement-related EEG patterns in brain activity. To increase the metric sensitivity, an adaptive low-pass filter was synthesized with the multivariate singular spectrum analysis (SSA). It has been experimentally demonstrated that significant temporal characteristics of the brain potentials preceding movement execution in the frontal, central and parietal areas of the cerebral cortex, on average, were 240±90 ms. It is shown that the synthesized adaptive filter has provided a reliable automatic search for induced pre-movement EEG patterns and the correct determination of their time boundaries (accuracy up to 96%). The developed method expands the existing tools to improve the functionality and reliability of various Brain-computer interfaces including those based on randomly generated, user-induced patterns of brain activity associated with voluntary motor activity.