作者: E. Yorn-Tov , G.F. Inbar
DOI: 10.1109/IEMBS.2001.1020450
关键词:
摘要: Classification of movement-related potentials recorded from the scalp to their corresponding limb is a crucial task in brain-computer interfaces based on such potentials. This paper demonstrates how features for can be selected large bank using genetic algorithm. We show that it possible differentiate between movements contralateral fingers with classification accuracy 77% small number (10-20) containing roughly 1000 features.