Higher Order Statistics and Phase Synchronization as Features in a Motor Imagery Paradigm

The paper proposes an approach based on higher order statistics and phase synchronization for detection classification of relevant features in electroencephalographic (EEG) signals recorded during the subjects are performing motor tasks. method was tested two different datasets performance evaluated using k nearest neighbor classifier. results (classification rates than 90%) have shown that can be used discriminating right left imagery tasks as offline analysis EEG a brain computer interface system.