The impact of segmentation and replication on non-overlapping windows: An EEG study

作者: Adham Atyabi , David M W Powers

DOI: 10.1109/ICIST.2012.6221730

关键词:

摘要: It is a common phenomenon that classification techniques applied to human EEG data are often more successful for some subjects than others. One reason may be differ in the degree and length of time they can continue engaged with experimental task at hand. recording time-consuming, tedious challenging procedure involves having remain physically still extended periods while repeatedly performing various mental, computational, imagery or other tasks. Hence, it expected their level involvement fluctuate, causing difficulties using from entire period classification. This effect likely appear on recordings which longer usual as dataset IVa BCI competition III duration set 3.5s. study investigates impact performance fragments complete period. The goal improve by providing higher concentration segments results indicate importance focusing middle final sub-epochs, poorer during earlier sub-windows.

参考文章(5)
Günter Edlinger, Clemens Holzner, Christoph Groenegress, Christoph Guger, Mel Slater, Goal-Oriented Control with Brain-Computer Interface Foundations of Augmented Cognition. Neuroergonomics and Operational Neuroscience. pp. 732- 740 ,(2009) , 10.1007/978-3-642-02812-0_83
Wenting Tu, Shiliang Sun, A subject transfer framework for EEG classification Neurocomputing. ,vol. 82, pp. 109- 116 ,(2012) , 10.1016/J.NEUCOM.2011.10.024
B. Blankertz, K.R. Muller, D.J. Krusienski, G. Schalk, J.R. Wolpaw, A. Schlogl, G. Pfurtscheller, J.D.R. Millan, M. Schroder, N. Birbaumer, The BCI competition III: validating alternative approaches to actual BCI problems international conference of the ieee engineering in medicine and biology society. ,vol. 14, pp. 153- 159 ,(2006) , 10.1109/TNSRE.2006.875642
Minfen Shen, Jialiang Chen, Patch J. Beadle, Analysis of Time-Varying EEG Based on Wavelet Packet Entropy international symposium on neural networks. pp. 21- 28 ,(2009) , 10.1007/978-3-642-01507-6_3