caa a22 4500 445294884 CHVBK 20180317142538.0 cr unu---uuuuu 170323e20100901xx s 000 0 eng 10.1007/s11571-010-9117-x doi (NATIONALLICENCE)springer-10.1007/s11571-010-9117-x Model based generalization analysis of common spatial pattern in brain computer interfaces [Elektronische Daten] [Gan Huang, Guangquan Liu, Jianjun Meng, Dingguo Zhang, Xiangyang Zhu] In the motor imagery based Brain Computer Interface (BCI) research, Common Spatial Pattern (CSP) algorithm is used widely as a spatial filter on multi-channel electroencephalogram (EEG) recordings. Recently the overfitting effect of CSP has been gradually noticed, but what influence the overfitting is still unclear. In this work, the generalization of CSP is investigated by a simple linear mixing model. Several factors in this model are discussed, and the simulation results indicate that channel numbers and the correlation between signals influence the generalization of CSP significantly. A larger number of training trials and a longer time length of the trial would prevent overfitting. The experiments on real data also verify our conclusion. Springer Science+Business Media B.V., 2010 Brain Computer Interfaces nationallicence Common Spatial Pattern nationallicence Generalization nationallicence Huang Gan State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut Liu Guangquan State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut Meng Jianjun State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut Zhang Dingguo State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut Zhu Xiangyang State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut Cognitive Neurodynamics Springer Netherlands 4/3(2010-09-01), 217-223 1871-4080 4:3<217 2010 4 11571 https://doi.org/10.1007/s11571-010-9117-x text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11571-010-9117-x text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Huang Gan State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut NATIONALLICENCE 700 1- Liu Guangquan State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut NATIONALLICENCE 700 1- Meng Jianjun State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut NATIONALLICENCE 700 1- Zhang Dingguo State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut NATIONALLICENCE 700 1- Zhu Xiangyang State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, 200240, Shanghai, China aut NATIONALLICENCE 773 0- Cognitive Neurodynamics Springer Netherlands 4/3(2010-09-01), 217-223 1871-4080 4:3<217 2010 4 11571 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer