Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b

• Published in: Frontiers in neuroscience Vol. 6; p. 39
• Main Authors: Ang, Kai Keng, Chin, Zheng Yang, Wang, Chuanchu, Guan, Cuntai, Zhang, Haihong
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 01.01.2012; Frontiers Media S.A
• Subjects: Algorithms; Bayesian classification; Brain; Brain-computer interface; Competition; Computer applications; Datasets; EEG; Electroencephalogram; Electroencephalography; Feature Selection; Implants; Mental task performance; mutual information; Neuroscience; mutual information; Bayesian classification; brain-computer interface; electroencephalogram; feature selection

The Common Spatial Pattern (CSP) algorithm is an effective and popular method for classifying 2-class motor imagery electroencephalogram (EEG) data, but its effectiveness depends on the subject-specific frequency band. This paper presents the Filter Bank Common Spatial Pattern (FBCSP) algorithm to o...