Genetic Algorithms in EEG Feature Selection for the Classification of Movements of the Left and Right Hand

摘要: The crucial problem which has to be solved when an effective brain-computer interface (BCI) is design is: how reduce the huge space of features extracted from raw EEG signals? One techniques feature selection often used by BCI researches are genetic algorithms (GA). This approach, in its classic form, allows obtaining a set gives high classification precision, however, dimension this still too large create reliable classifier. paper presents modified version algorithm, capable choosing sets slightly lower precision but significantly smaller number features. practical application proposed algorithm will presented via benchmark submitted second Competition (data III - motor imaginary).