作者: Ferran Galán , Francesc Oliva , Joan Guàrdia
DOI: 10.1007/S11517-007-0197-7
关键词:
摘要: This paper presents an algorithm based on canonical variates transformation (CVT) and distance discriminant analysis (DBDA) combined with a mental tasks transitions detector (MTTD) to classify spontaneous activities in order operate brain-computer interface working under asynchronous protocol. The won the BCI Competition III -Data Set V: Multiclass Problem, Continous EEG- achieving averaged classification accuracy over three subjects of 68.65% (79.60, 70.31 56.02%, respectively) three-class problem.